Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift

Abstract

Training Deep Neural Networks is complicated by the fact that the distribution of each layer's inputs changes during training, as the parameters of the previous layers change. This slows down the training by requiring lower learning rates and careful parameter initialization, and makes it notoriously hard to train models with saturating nonlinearities. We refer to this phenomenon as internal covariate shift, and address the problem by normalizing layer inputs. Our method draws its strength from making normalization a part of the model architecture and performing the normalization for each training mini-batch. Batch Normalization allows us to use much higher learning rates and be less careful about initialization. It also acts as a regularizer, in some cases eliminating the need for Dropout. Applied to a state-of-the-art image classification model, Batch Normalization achieves the same accuracy with 14 times fewer training steps, and beats the original model by a significant margin. Using an ensemble of batch-normalized networks, we improve upon the best published result on ImageNet classification: reaching 4.9% top-5 validation error (and 4.8% test error), exceeding the accuracy of human raters.

References in corpus (5)

• On the difficulty of training Recurrent Neural Networks
• Going Deeper with Convolutions
• Deep Image: Scaling up Image Recognition
• Knowledge Matters: Importance of Prior Information for Optimization
• Natural Neural Networks

Cited by in corpus (3268)

• Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
• Deep Residual Learning for Image Recognition
• Generative Adversarial Networks: An Overview
• A Survey on Visual Transformer
• Knowledge Distillation: A Survey
• Deep learning with convolutional neural networks for EEG decoding and visualization
• Efficient Multi-Scale 3D CNN with Fully Connected CRF for Accurate Brain Lesion Segmentation
• Bootstrap your own latent: A new approach to self-supervised Learning
• Deep learning for time series classification: a review
• A Comprehensive Review of YOLO Architectures in Computer Vision: From YOLOv1 to YOLOv8 and YOLO-NAS
• ICLabel: An automated electroencephalographic independent component classifier, dataset, and website
• MultiResUNet : Rethinking the U-Net Architecture for Multimodal Biomedical Image Segmentation
• Object Detection in Optical Remote Sensing Images: A Survey and A New Benchmark
• Barren plateaus in quantum neural network training landscapes
• Deep Visual Domain Adaptation: A Survey
• Deep Speech 2: End-to-End Speech Recognition in English and Mandarin
• Generative Adversarial Text to Image Synthesis
• ResUNet-a: a deep learning framework for semantic segmentation of remotely sensed data
• DeepSurv: Personalized Treatment Recommender System Using A Cox Proportional Hazards Deep Neural Network
• Generative Adversarial Network in Medical Imaging: A Review
• Predicting Cardiovascular Risk Factors from Retinal Fundus Photographs using Deep Learning
• MesoNet: a Compact Facial Video Forgery Detection Network
• Molecular Graph Convolutions: Moving Beyond Fingerprints
• Graph Convolutional Networks for Hyperspectral Image Classification
• Over the Air Deep Learning Based Radio Signal Classification
• Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks
• ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verification
• LSTM Fully Convolutional Networks for Time Series Classification
• MLP-Mixer: An all-MLP Architecture for Vision
• Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations
• DeepSleepNet: a Model for Automatic Sleep Stage Scoring based on Raw Single-Channel EEG
• More Diverse Means Better: Multimodal Deep Learning Meets Remote Sensing Imagery Classification
• Recurrent Neural Networks for Time Series Forecasting: Current Status and Future Directions
• A Survey of Deep Learning-based Object Detection
• Normalizing Flows: An Introduction and Review of Current Methods
• Deep Learning for Single Image Super-Resolution: A Brief Review
• VNect: Real-time 3D Human Pose Estimation with a Single RGB Camera
• Understanding deep learning requires rethinking generalization
• FINN: A Framework for Fast, Scalable Binarized Neural Network Inference
• fastai: A Layered API for Deep Learning
• Momentum Contrast for Unsupervised Visual Representation Learning
• Accurate De Novo Prediction of Protein Contact Map by Ultra-Deep Learning Model
• Blind Image Quality Assessment Using A Deep Bilinear Convolutional Neural Network
• A high-bias, low-variance introduction to Machine Learning for physicists
• Show and Tell: Lessons learned from the 2015 MSCOCO Image Captioning Challenge
• ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices
• Speeding Up Distributed Machine Learning Using Codes
• Road Damage Detection Using Deep Neural Networks with Images Captured Through a Smartphone
• Deep learning-based numerical methods for high-dimensional parabolic partial differential equations and backward stochastic differential equations
• Benchmark Analysis of Representative Deep Neural Network Architectures
• Deep Bilateral Learning for Real-Time Image Enhancement
• CHAOS Challenge -- Combined (CT-MR) Healthy Abdominal Organ Segmentation
• Convolutional Neural Networks for Classification of Alzheimer's Disease: Overview and Reproducible Evaluation
• Convolutional Networks for Fast, Energy-Efficient Neuromorphic Computing
• On instabilities of deep learning in image reconstruction - Does AI come at a cost?
• Evaluation of Output Embeddings for Fine-Grained Image Classification
• Bayesian Deep Convolutional Encoder-Decoder Networks for Surrogate Modeling and Uncertainty Quantification
• DeepConv-DTI: Prediction of drug-target interactions via deep learning with convolution on protein sequences
• An Empirical Survey of Data Augmentation for Time Series Classification with Neural Networks
• BACH: Grand Challenge on Breast Cancer Histology Images
• PACT: Parameterized Clipping Activation for Quantized Neural Networks
• Adversarial Feature Learning
• Deep Learning for Classification of Hyperspectral Data: A Comparative Review
• A Survey and Critique of Multiagent Deep Reinforcement Learning
• Disentangling by Factorising
• Deep-STORM: super-resolution single-molecule microscopy by deep learning
• SynthSeg: Segmentation of brain MRI scans of any contrast and resolution without retraining
• Quantifying the effects of data augmentation and stain color normalization in convolutional neural networks for computational pathology
• Convolutional Recurrent Neural Networks for Polyphonic Sound Event Detection
• FractalNet: Ultra-Deep Neural Networks without Residuals
• TorchIO: A Python library for efficient loading, preprocessing, augmentation and patch-based sampling of medical images in deep learning
• Automatic lung segmentation in routine imaging is primarily a data diversity problem, not a methodology problem
• HDR image reconstruction from a single exposure using deep CNNs
• CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features
• On the Variance of the Adaptive Learning Rate and Beyond
• Towards K-means-friendly Spaces: Simultaneous Deep Learning and Clustering
• Looking to Listen at the Cocktail Party: A Speaker-Independent Audio-Visual Model for Speech Separation
• Semi-Supervised Learning with Ladder Networks
• Impact of Fully Connected Layers on Performance of Convolutional Neural Networks for Image Classification
• Reconstruction of three-dimensional porous media using generative adversarial neural networks
• T-CNN: Tubelets with Convolutional Neural Networks for Object Detection from Videos
• A survey on modern trainable activation functions
• Machine learning in acoustics: theory and applications
• Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges
• Automatic Ship Detection of Remote Sensing Images from Google Earth in Complex Scenes Based on Multi-Scale Rotation Dense Feature Pyramid Networks
• Generalized Seismic Phase Detection with Deep Learning
• Data Synthesis based on Generative Adversarial Networks
• Deep Neuroevolution: Genetic Algorithms Are a Competitive Alternative for Training Deep Neural Networks for Reinforcement Learning
• Fully Dense UNet for 2D Sparse Photoacoustic Tomography Artifact Removal
• Sound Event Localization and Detection of Overlapping Sources Using Convolutional Recurrent Neural Networks
• Applications of Unsupervised Deep Transfer Learning to Intelligent Fault Diagnosis: A Survey and Comparative Study
• Seismic Signal Denoising and Decomposition Using Deep Neural Networks
• Training Deep Nets with Sublinear Memory Cost
• P-wave arrival picking and first-motion polarity determination with deep learning
• A scoping review of transfer learning research on medical image analysis using ImageNet
• Multimodal Fusion Transformer for Remote Sensing Image Classification
• Deep Convolutional Neural Networks for Raman Spectrum Recognition: A Unified Solution
• Evaluate the Malignancy of Pulmonary Nodules Using the 3D Deep Leaky Noisy-or Network
• Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting
• Data Augmentation using Random Image Cropping and Patching for Deep CNNs
• The Microsoft 2017 Conversational Speech Recognition System
• Hybrid LSTM and Encoder-Decoder Architecture for Detection of Image Forgeries
• Deep Clustering for Unsupervised Learning of Visual Features
• Deep Representation Learning with Part Loss for Person Re-Identification
• End-to-End Unsupervised Deformable Image Registration with a Convolutional Neural Network
• Attributed Social Network Embedding
• Modified U-Net (mU-Net) with Incorporation of Object-Dependent High Level Features for Improved Liver and Liver-Tumor Segmentation in CT Images
• Trunk-Branch Ensemble Convolutional Neural Networks for Video-based Face Recognition
• Enabling Spike-based Backpropagation for Training Deep Neural Network Architectures
• Smart Augmentation - Learning an Optimal Data Augmentation Strategy
• ABCNet: Attentive Bilateral Contextual Network for Efficient Semantic Segmentation of Fine-Resolution Remote Sensing Images
• The Open Images Dataset V4: Unified image classification, object detection, and visual relationship detection at scale
• ParticleNet: Jet Tagging via Particle Clouds
• Neural network an1alysis of sleep stages enables efficient diagnosis of narcolepsy
• TSception: Capturing Temporal Dynamics and Spatial Asymmetry from EEG for Emotion Recognition
• Light Gated Recurrent Units for Speech Recognition
• Exploring Simple Siamese Representation Learning
• PlaNet - Photo Geolocation with Convolutional Neural Networks
• Residual Networks of Residual Networks: Multilevel Residual Networks
• Avoiding Overfitting: A Survey on Regularization Methods for Convolutional Neural Networks
• Skeleton-based Action Recognition via Spatial and Temporal Transformer Networks
• Artificial neural networks for neuroscientists: A primer
• Object-Part Attention Model for Fine-grained Image Classification
• Do ImageNet Classifiers Generalize to ImageNet?
• ATLAS $b$-jet identification performance and efficiency measurement with $t\bar{t}$ events in $pp$ collisions at $\sqrt{s}=13$ TeV
• Deep Networks for Direction-of-Arrival Estimation in Low SNR
• Learning Features for Offline Handwritten Signature Verification using Deep Convolutional Neural Networks
• How Powerful are Graph Neural Networks?
• NVAE: A Deep Hierarchical Variational Autoencoder
• A deep convolutional neural network model for rapid prediction of fluvial flood inundation
• A Deep Learning Framework for Optimization of MISO Downlink Beamforming
• Deep convolutional encoder-decoder networks for uncertainty quantification of dynamic multiphase flow in heterogeneous media
• Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization
• Path Aggregation Network for Instance Segmentation
• Early Convolutions Help Transformers See Better
• Evolution of Image Segmentation using Deep Convolutional Neural Network: A Survey
• Deep Neural Networks for Data-Driven Turbulence Models
• Modeling the Dynamics of PDE Systems with Physics-Constrained Deep Auto-Regressive Networks
• Adversarial Reciprocal Points Learning for Open Set Recognition
• Normalizing Flows for Probabilistic Modeling and Inference
• Sharpness-aware Low dose CT denoising using conditional generative adversarial network
• A Comprehensive Analysis of Deep Regression
• Point-Voxel CNN for Efficient 3D Deep Learning
• An application of cascaded 3D fully convolutional networks for medical image segmentation
• Deep Image: Scaling up Image Recognition
• Models Genesis
• Machine learning approximation algorithms for high-dimensional fully nonlinear partial differential equations and second-order backward stochastic differential equations
• Deep learning based cloud detection for medium and high resolution remote sensing images of different sensors
• Systematic evaluation of CNN advances on the ImageNet
• Deep Roots: Improving CNN Efficiency with Hierarchical Filter Groups
• R-Drop: Regularized Dropout for Neural Networks
• Diagnosis of Alzheimer's Disease via Multi-modality 3D Convolutional Neural Network
• Learning Tree-based Deep Model for Recommender Systems
• Machine Learning for Wireless Communications in the Internet of Things: A Comprehensive Survey
• Deep Appearance Models for Face Rendering
• Split Computing and Early Exiting for Deep Learning Applications: Survey and Research Challenges
• Semantic Labeling in Very High Resolution Images via a Self-Cascaded Convolutional Neural Network
• Learning Discrete Representations via Information Maximizing Self-Augmented Training
• Facial Expression Recognition Using Enhanced Deep 3D Convolutional Neural Networks
• A Point-Cloud Deep Learning Framework for Prediction of Fluid Flow Fields on Irregular Geometries
• Deep Gradient Learning for Efficient Camouflaged Object Detection
• Tent: Fully Test-time Adaptation by Entropy Minimization
• Concept Whitening for Interpretable Image Recognition
• Open-vocabulary Object Detection via Vision and Language Knowledge Distillation
• Transfer learning for time series classification
• Training Tips for the Transformer Model
• CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instances
• PhyCRNet: Physics-informed Convolutional-Recurrent Network for Solving Spatiotemporal PDEs
• Unsupervised Single Image Dehazing Using Dark Channel Prior Loss
• Real-time Hand Tracking under Occlusion from an Egocentric RGB-D Sensor
• MFQE 2.0: A New Approach for Multi-frame Quality Enhancement on Compressed Video
• Hyperbolic Graph Convolutional Neural Networks
• TransGAN: Two Pure Transformers Can Make One Strong GAN, and That Can Scale Up
• Self-supervised learning methods and applications in medical imaging analysis: A survey
• RANet: Ranking Attention Network for Fast Video Object Segmentation
• Automatic calcium scoring in low-dose chest CT using deep neural networks with dilated convolutions
• Segmentation of Glioma Tumors in Brain Using Deep Convolutional Neural Network
• X-ModalNet: A Semi-Supervised Deep Cross-Modal Network for Classification of Remote Sensing Data
• Semantic Image Synthesis with Spatially-Adaptive Normalization
• High-Performance Large-Scale Image Recognition Without Normalization
• Conditional Generative Adversarial Networks for Speech Enhancement and Noise-Robust Speaker Verification
• Robust Large Margin Deep Neural Networks
• CalibNet: Geometrically Supervised Extrinsic Calibration using 3D Spatial Transformer Networks
• FPNN: Field Probing Neural Networks for 3D Data
• Var-CNN: A Data-Efficient Website Fingerprinting Attack Based on Deep Learning
• Spatial Temporal Transformer Network for Skeleton-based Action Recognition
• Microstructural Materials Design via Deep Adversarial Learning Methodology
• OrbNet: Deep Learning for Quantum Chemistry Using Symmetry-Adapted Atomic-Orbital Features
• Deep Learning for Human Affect Recognition: Insights and New Developments
• A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts
• Neuromorphic Deep Learning Machines
• Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation
• Rotation equivariant vector field networks
• ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design
• The Principles of Deep Learning Theory
• Learning to Dispatch for Job Shop Scheduling via Deep Reinforcement Learning
• Single Path One-Shot Neural Architecture Search with Uniform Sampling
• Towards Out-Of-Distribution Generalization: A Survey
• Multimodal Residual Learning for Visual QA
• Deep Learning for Generic Object Detection: A Survey
• Comparison of Deep Reinforcement Learning and Model Predictive Control for Adaptive Cruise Control
• Large-scale JPEG steganalysis using hybrid deep-learning framework
• Compute and Energy Consumption Trends in Deep Learning Inference
• Privacy-preserving Spatiotemporal Scenario Generation of Renewable Energies: A Federated Deep Generative Learning Approach
• Averaging Weights Leads to Wider Optima and Better Generalization
• Hyperspectral Classification Based on Lightweight 3-D-CNN With Transfer Learning
• EmergencyNet: Efficient Aerial Image Classification for Drone-Based Emergency Monitoring Using Atrous Convolutional Feature Fusion
• How Does Batch Normalization Help Optimization?
• On the Reconstruction of Face Images from Deep Face Templates
• Deep Residual Learning in Spiking Neural Networks
• Hypernetwork Knowledge Graph Embeddings
• Contrastive Cross-site Learning with Redesigned Net for COVID-19 CT Classification
• Video Compression With Rate-Distortion Autoencoders
• Multi-Modal Self-Supervised Learning for Recommendation
• An Application of Deep Reinforcement Learning to Algorithmic Trading
• Joint Activity Recognition and Indoor Localization with WiFi Fingerprints
• Deep learning analysis of the myocardium in coronary CT angiography for identification of patients with functionally significant coronary artery stenosis
• CardioXNet: A Novel Lightweight Deep Learning Framework for Cardiovascular Disease Classification Using Heart Sound Recordings
• Explainable COVID-19 Detection Using Chest CT Scans and Deep Learning
• Hardware and Software Optimizations for Accelerating Deep Neural Networks: Survey of Current Trends, Challenges, and the Road Ahead
• DeepGCNs: Making GCNs Go as Deep as CNNs
• Context Based Emotion Recognition using EMOTIC Dataset
• InversionNet: A Real-Time and Accurate Full Waveform Inversion with CNNs and continuous CRFs
• A deep learning approach to identify local structures in atomic-resolution transmission electron microscopy images
• High-Fidelity Generative Image Compression
• Central Moment Discrepancy (CMD) for Domain-Invariant Representation Learning
• Country-wide high-resolution vegetation height mapping with Sentinel-2
• Real-Time Apple Detection System Using Embedded Systems With Hardware Accelerators: An Edge AI Application
• Deep DIC: Deep Learning-Based Digital Image Correlation for End-to-End Displacement and Strain Measurement
• Insights into LSTM Fully Convolutional Networks for Time Series Classification
• Coronary Artery Centerline Extraction in Cardiac CT Angiography Using a CNN-Based Orientation Classifier
• Machine Learning for Stochastic Parameterization: Generative Adversarial Networks in the Lorenz '96 Model
• Deep Reinforcement Learning for Solving the Heterogeneous Capacitated Vehicle Routing Problem
• Attentional Pooling for Action Recognition
• Looking Beyond Appearances: Synthetic Training Data for Deep CNNs in Re-identification
• DoFE: Domain-oriented Feature Embedding for Generalizable Fundus Image Segmentation on Unseen Datasets
• Identity Mappings in Deep Residual Networks
• Quantization and Deployment of Deep Neural Networks on Microcontrollers
• Realistic Evaluation of Deep Semi-Supervised Learning Algorithms
• Deep Neural Networks for Multiple Speaker Detection and Localization
• ESRGAN+ : Further Improving Enhanced Super-Resolution Generative Adversarial Network
• Masked Autoencoders Are Scalable Vision Learners
• GhostNets on Heterogeneous Devices via Cheap Operations
• Less is More: Lighter and Faster Deep Neural Architecture for Tomato Leaf Disease Classification
• Data Augmentation for Skin Lesion Analysis
• Deep Image Translation with an Affinity-Based Change Prior for Unsupervised Multimodal Change Detection
• Removal of Batch Effects using Distribution-Matching Residual Networks
• A Deep Learning Interpretable Classifier for Diabetic Retinopathy Disease Grading
• Deep Hough Transform for Semantic Line Detection
• Test-Time Adaptable Neural Networks for Robust Medical Image Segmentation
• Classification of EEG-Based Brain Connectivity Networks in Schizophrenia Using a Multi-Domain Connectome Convolutional Neural Network
• High Quality Monocular Depth Estimation via Transfer Learning
• Multi-branch Convolutional Neural Network for Multiple Sclerosis Lesion Segmentation
• Uncertainty and Interpretability in Convolutional Neural Networks for Semantic Segmentation of Colorectal Polyps
• Data-dependent Initializations of Convolutional Neural Networks
• ShakeDrop Regularization for Deep Residual Learning
• On Empirical Comparisons of Optimizers for Deep Learning
• DABNet: Depth-wise Asymmetric Bottleneck for Real-time Semantic Segmentation
• Finding Strong Gravitational Lenses in the Kilo Degree Survey with Convolutional Neural Networks
• Neuroevolution in Deep Neural Networks: Current Trends and Future Challenges
• A Particle Swarm Optimization-based Flexible Convolutional Auto-Encoder for Image Classification
• Combining time-series and textual data for taxi demand prediction in event areas: a deep learning approach
• Modeling Surface Appearance from a Single Photograph using Self-augmented Convolutional Neural Networks
• Super-resolution-based Change Detection Network with Stacked Attention Module for Images with Different Resolutions
• Deep Decoder: Concise Image Representations from Untrained Non-convolutional Networks
• DFR: Deep Feature Reconstruction for Unsupervised Anomaly Segmentation
• DeepSphere: Efficient spherical Convolutional Neural Network with HEALPix sampling for cosmological applications
• Strategies for Pre-training Graph Neural Networks
• Skin Lesion Classification Using CNNs with Patch-Based Attention and Diagnosis-Guided Loss Weighting
• Deep Graph-Convolutional Image Denoising
• Enhanced CNN for image denoising
• MobileSal: Extremely Efficient RGB-D Salient Object Detection
• Tiny Machine Learning: Progress and Futures
• AxonDeepSeg: automatic axon and myelin segmentation from microscopy data using convolutional neural networks
• L1-Norm Batch Normalization for Efficient Training of Deep Neural Networks
• Hybrid CNN and Dictionary-Based Models for Scene Recognition and Domain Adaptation
• SegMap: 3D Segment Mapping using Data-Driven Descriptors
• Exploiting Epistemic Uncertainty of Anatomy Segmentation for Anomaly Detection in Retinal OCT
• Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere
• Measuring Robustness to Natural Distribution Shifts in Image Classification
• Position Detection and Direction Prediction for Arbitrary-Oriented Ships via Multitask Rotation Region Convolutional Neural Network
• Diagnostic Classification Of Lung Nodules Using 3D Neural Networks
• Ten Years of Generative Adversarial Nets (GANs): A survey of the state-of-the-art
• Generative Adversarial Networks and Conditional Random Fields for Hyperspectral Image Classification
• Quantum machine learning for image classification
• Gravitational-wave parameter estimation with autoregressive neural network flows
• NATS-Bench: Benchmarking NAS Algorithms for Architecture Topology and Size
• Learning to Find Eye Region Landmarks for Remote Gaze Estimation in Unconstrained Settings
• Land Cover Classification from Remote Sensing Images Based on Multi-Scale Fully Convolutional Network
• Deep Residual Correction Network for Partial Domain Adaptation
• Unsupervised Learning via Meta-Learning
• A Contrast-Adaptive Method for Simultaneous Whole-Brain and Lesion Segmentation in Multiple Sclerosis
• Simultaneous Traffic Sign Detection and Boundary Estimation using Convolutional Neural Network
• DeeperLab: Single-Shot Image Parser
• How Does Learning Rate Decay Help Modern Neural Networks?
• Differentiable Learning-to-Normalize via Switchable Normalization
• Deep Learning in the Automotive Industry: Applications and Tools
• Facial Emotion Recognition: State of the Art Performance on FER2013
• Towards More Accurate Automatic Sleep Staging via Deep Transfer Learning
• Heterogeneous Attentions for Solving Pickup and Delivery Problem via Deep Reinforcement Learning
• Graph-based Spatial-temporal Feature Learning for Neuromorphic Vision Sensing
• ViTAE: Vision Transformer Advanced by Exploring Intrinsic Inductive Bias
• Speed/accuracy trade-offs for modern convolutional object detectors
• How to DP-fy ML: A Practical Guide to Machine Learning with Differential Privacy
• Knowledge Guided Disambiguation for Large-Scale Scene Classification with Multi-Resolution CNNs
• A Two-Stage Approach to Few-Shot Learning for Image Recognition
• J$\hat{\text{A}}$A-Net: Joint Facial Action Unit Detection and Face Alignment via Adaptive Attention
• High-dimensional Dense Residual Convolutional Neural Network for Light Field Reconstruction
• Discrimination-aware Network Pruning for Deep Model Compression
• Getting High: High Fidelity Simulation of High Granularity Calorimeters with High Speed
• Semantic Segmentation of Pathological Lung Tissue with Dilated Fully Convolutional Networks
• Adaptive Exploration for Unsupervised Person Re-Identification
• CNN+LSTM Architecture for Speech Emotion Recognition with Data Augmentation
• Measuring the Effects of Data Parallelism on Neural Network Training
• Generating Handwritten Chinese Characters using CycleGAN
• Script Identification in Natural Scene Image and Video Frame using Attention based Convolutional-LSTM Network
• Denoising IMU Gyroscopes with Deep Learning for Open-Loop Attitude Estimation
• TomoGAN: Low-Dose Synchrotron X-Ray Tomography with Generative Adversarial Networks
• Integration of adversarial autoencoders with residual dense convolutional networks for estimation of non-Gaussian hydraulic conductivities
• StegNet: Mega Image Steganography Capacity with Deep Convolutional Network
• Deep Transfer Learning Based Intrusion Detection System for Electric Vehicular Networks
• Robust Spatial Filtering with Graph Convolutional Neural Networks
• Federated Adversarial Domain Adaptation
• Non-local Neural Networks
• Modeling Human Motion with Quaternion-based Neural Networks
• Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation
• BASS Net: Band-Adaptive Spectral-Spatial Feature Learning Neural Network for Hyperspectral Image Classification
• ResT: An Efficient Transformer for Visual Recognition
• Design of metalloproteins and novel protein folds using variational autoencoders
• Dense Dilated Convolutions Merging Network for Land Cover Classification
• Deep Learning in fNIRS: A review
• CornerNet: Detecting Objects as Paired Keypoints
• XCM: An Explainable Convolutional Neural Network for Multivariate Time Series Classification
• Multiclass Classification Procedure for Detecting Attacks on MQTT-IoT Protocol
• Differentially Private Synthetic Medical Data Generation using Convolutional GANs
• Deep Reinforcement Learning for Process Control: A Primer for Beginners
• Deep Reinforcement Learning (DRL): Another Perspective for Unsupervised Wireless Localization
• Cascaded Region-based Densely Connected Network for Event Detection: A Seismic Application
• Swapping Autoencoder for Deep Image Manipulation
• Learning for Video Compression
• SlowFast Networks for Video Recognition
• Adversarial Attacks on Deep Neural Networks for Time Series Classification
• A CNN Approach to Simultaneously Count Plants and Detect Plantation-Rows from UAV Imagery
• MS-ASL: A Large-Scale Data Set and Benchmark for Understanding American Sign Language
• Deformable Kernel Networks for Joint Image Filtering
• A Compact and Interpretable Convolutional Neural Network for Cross-Subject Driver Drowsiness Detection from Single-Channel EEG
• Rolling-Unrolling LSTMs for Action Anticipation from First-Person Video
• Learning Deep Representations of Fine-grained Visual Descriptions
• Nested Sampling with Normalising Flows for Gravitational-Wave Inference
• Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation
• Improvements to context based self-supervised learning
• Pyramidal Convolution: Rethinking Convolutional Neural Networks for Visual Recognition
• Deep Learning for Tumor Classification in Imaging Mass Spectrometry
• Convergence of the Deep BSDE Method for Coupled FBSDEs
• Deep Tone Mapping Operator for High Dynamic Range Images
• Ensemble Kalman Inversion: A Derivative-Free Technique For Machine Learning Tasks
• Enable Deep Learning on Mobile Devices: Methods, Systems, and Applications
• Network Pruning via Transformable Architecture Search
• Learning representations of irregular particle-detector geometry with distance-weighted graph networks
• Hardware Approximate Techniques for Deep Neural Network Accelerators: A Survey
• Fully Automated Organ Segmentation in Male Pelvic CT Images
• A Practical Survey on Faster and Lighter Transformers
• Deep splitting method for parabolic PDEs
• Sharp Minima Can Generalize For Deep Nets
• Progressive Differentiable Architecture Search: Bridging the Depth Gap between Search and Evaluation
• Learning the PE Header, Malware Detection with Minimal Domain Knowledge
• TransCG: A Large-Scale Real-World Dataset for Transparent Object Depth Completion and a Grasping Baseline
• Exploring Spatial Significance via Hybrid Pyramidal Graph Network for Vehicle Re-identification
• Learning Dual Semantic Relations with Graph Attention for Image-Text Matching
• SFace: Sigmoid-Constrained Hypersphere Loss for Robust Face Recognition
• Direct Automatic Coronary Calcium Scoring in Cardiac and Chest CT
• PointCNN: Convolution On $\mathcal{X}$-Transformed Points
• The Modern Mathematics of Deep Learning
• Discovery of Latent 3D Keypoints via End-to-end Geometric Reasoning
• A Fully Convolutional Network for Semantic Labeling of 3D Point Clouds
• GENESIS: Generative Scene Inference and Sampling with Object-Centric Latent Representations
• An End to End Deep Neural Network for Iris Segmentation in Unconstraint Scenarios
• Do Gradient Inversion Attacks Make Federated Learning Unsafe?
• Learning a bidirectional mapping between human whole-body motion and natural language using deep recurrent neural networks
• MgNet: A Unified Framework of Multigrid and Convolutional Neural Network
• Adversarial Networks for Spatial Context-Aware Spectral Image Reconstruction from RGB
• Batch-Instance Normalization for Adaptively Style-Invariant Neural Networks
• BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation
• SwinFace: A Multi-task Transformer for Face Recognition, Expression Recognition, Age Estimation and Attribute Estimation
• Attention-Guided Version of 2D UNet for Automatic Brain Tumor Segmentation
• Multi-Person Continuous Tracking and Identification from mm-Wave micro-Doppler Signatures
• Multi-Source Unsupervised Domain Adaptation via Pseudo Target Domain
• Multiphase flow prediction with deep neural networks
• The jamming transition as a paradigm to understand the loss landscape of deep neural networks
• Optimize TSK Fuzzy Systems for Classification Problems: Mini-Batch Gradient Descent with Uniform Regularization and Batch Normalization
• Estimating Depth from RGB and Sparse Sensing
• OGB-LSC: A Large-Scale Challenge for Machine Learning on Graphs
• DRFN: Deep Recurrent Fusion Network for Single-Image Super-Resolution with Large Factors
• Generative Visual Manipulation on the Natural Image Manifold
• Artistic style transfer for videos and spherical images
• RetinaMask: Learning to predict masks improves state-of-the-art single-shot detection for free
• 3D Convolutional Neural Networks for Cross Audio-Visual Matching Recognition
• Deep Residual Networks with Exponential Linear Unit
• The Role of Cross-Silo Federated Learning in Facilitating Data Sharing in the Agri-Food Sector
• Polyphonic Sound Event Detection and Localization using a Two-Stage Strategy
• Robust Multi-Task Learning and Online Refinement for Spacecraft Pose Estimation across Domain Gap
• OmiEmbed: a unified multi-task deep learning framework for multi-omics data
• Identifying Solar Flare Precursors Using Time Series of SDO/HMI Images and SHARP Parameters
• Deep convolutional networks for quality assessment of protein folds
• GhostNet: More Features from Cheap Operations
• BiSeNet V2: Bilateral Network with Guided Aggregation for Real-time Semantic Segmentation
• Backbones-Review: Feature Extraction Networks for Deep Learning and Deep Reinforcement Learning Approaches
• Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approach
• Machine learning and AI-based approaches for bioactive ligand discovery and GPCR-ligand recognition
• Attenuation correction for brain PET imaging using deep neural network based on dixon and ZTE MR images
• Boosting the Speed of Entity Alignment 10*: Dual Attention Matching Network with Normalized Hard Sample Mining
• Global Stock Market Prediction Based on Stock Chart Images Using Deep Q-Network
• Recent Advances in Object Detection in the Age of Deep Convolutional Neural Networks
• Deep Knockoffs
• What is the Effect of Importance Weighting in Deep Learning?
• Multi-modal Multi-channel Target Speech Separation
• Blind Backdoors in Deep Learning Models
• Lifelong Generative Modeling
• Implicit Dual-domain Convolutional Network for Robust Color Image Compression Artifact Reduction
• Convolutional Neural Networks Applied to Neutrino Events in a Liquid Argon Time Projection Chamber
• Benchmarking the Robustness of Semantic Segmentation Models
• A Deep Learning Reconstruction Framework for Differential Phase-Contrast Computed Tomography with Incomplete Data
• R2U++: A Multiscale Recurrent Residual U-Net with Dense Skip Connections for Medical Image Segmentation
• Streaming convolutional neural networks for end-to-end learning with multi-megapixel images
• Mixing Up Contrastive Learning: Self-Supervised Representation Learning for Time Series
• Deep Learning-based Spacecraft Relative Navigation Methods: A Survey
• Deep CNNs Meet Global Covariance Pooling: Better Representation and Generalization
• Review: Deep Learning in Electron Microscopy
• HoloStain: Holographic virtual staining of individual biological cells
• Root Mean Square Layer Normalization
• FedCP: Separating Feature Information for Personalized Federated Learning via Conditional Policy
• Multi-task Learning with Coarse Priors for Robust Part-aware Person Re-identification
• High Fidelity Speech Synthesis with Adversarial Networks
• OrbNet Denali: A machine learning potential for biological and organic chemistry with semi-empirical cost and DFT accuracy
• ProstAttention-Net: A deep attention model for prostate cancer segmentation by aggressiveness in MRI scans
• Sparse R-CNN: End-to-End Object Detection with Learnable Proposals
• Unsupervised Multi-Class Domain Adaptation: Theory, Algorithms, and Practice
• Decoding and mapping task states of the human brain via deep learning
• Terminal Brain Damage: Exposing the Graceless Degradation in Deep Neural Networks Under Hardware Fault Attacks
• Cascade R-CNN: High Quality Object Detection and Instance Segmentation
• Circle Loss: A Unified Perspective of Pair Similarity Optimization
• AdaBatch: Adaptive Batch Sizes for Training Deep Neural Networks
• Weak lensing cosmology with convolutional neural networks on noisy data
• Pruning Deep Convolutional Neural Networks Architectures with Evolution Strategy
• Backprop KF: Learning Discriminative Deterministic State Estimators
• Balanced Semi-Supervised Generative Adversarial Network for Damage Assessment from Low-Data Imbalanced-Class Regime
• Male pelvic synthetic CT generation from T1-weighted MRI using 2D and 3D convolutional neural networks
• deSpeckNet: Generalizing Deep Learning Based SAR Image Despeckling
• Pelee: A Real-Time Object Detection System on Mobile Devices
• Informing Geometric Deep Learning with Electronic Interactions to Accelerate Quantum Chemistry
• Learning Disentangled Representations in the Imaging Domain
• Deep generative selection models of T and B cell receptor repertoires with soNNia
• Conditional Variational Image Deraining
• Roundtrip: A Deep Generative Neural Density Estimator
• Torchreid: A Library for Deep Learning Person Re-Identification in Pytorch
• The Conditional Entropy Bottleneck
• Machine learning with neural networks
• CycleMLP: A MLP-like Architecture for Dense Prediction
• Hierarchical Paired Channel Fusion Network for Street Scene Change Detection
• Topological Quantum Compiling with Reinforcement Learning
• Rethinking Softmax Cross-Entropy Loss for Adversarial Robustness
• Data augmentation instead of explicit regularization
• StarGAN v2: Diverse Image Synthesis for Multiple Domains
• ContraGAN: Contrastive Learning for Conditional Image Generation
• The Shattered Gradients Problem: If resnets are the answer, then what is the question?
• AFDet: Anchor Free One Stage 3D Object Detection
• SCAN: Self-and-Collaborative Attention Network for Video Person Re-identification
• Automatic sleep stage classification with deep residual networks in a mixed-cohort setting
• Direct Multitype Cardiac Indices Estimation via Joint Representation and Regression Learning
• Dilated Convolutional Neural Networks for Cardiovascular MR Segmentation in Congenital Heart Disease
• PointContrast: Unsupervised Pre-training for 3D Point Cloud Understanding
• Second-Order Pooling for Graph Neural Networks
• Cross-regional oil palm tree counting and detection via multi-level attention domain adaptation network
• A Generative Model for Volume Rendering
• Modeling Tabular data using Conditional GAN
• Capsule Attention for Multimodal EEG-EOG Representation Learning with Application to Driver Vigilance Estimation
• Deep Gated Recurrent and Convolutional Network Hybrid Model for Univariate Time Series Classification
• Aerial Images Processing for Car Detection using Convolutional Neural Networks: Comparison between Faster R-CNN and YoloV3
• Shape and Margin-Aware Lung Nodule Classification in Low-dose CT Images via Soft Activation Mapping
• Recent Progress in the CUHK Dysarthric Speech Recognition System
• Memcomputing: Leveraging memory and physics to compute efficiently
• Prediction of final infarct volume from native CT perfusion and treatment parameters using deep learning
• SoftTriple Loss: Deep Metric Learning Without Triplet Sampling
• Relation-Shape Convolutional Neural Network for Point Cloud Analysis
• Automated Reinforcement Learning (AutoRL): A Survey and Open Problems
• BatchEnsemble: An Alternative Approach to Efficient Ensemble and Lifelong Learning
• A Deep Learning Approach for Blind Drift Calibration of Sensor Networks
• Revisiting Shadow Detection: A New Benchmark Dataset for Complex World
• Evolving Boxes for Fast Vehicle Detection
• Variance Reduced Local SGD with Lower Communication Complexity
• Ellipse R-CNN: Learning to Infer Elliptical Object from Clustering and Occlusion
• The Non-IID Data Quagmire of Decentralized Machine Learning
• Uniformly Accurate Machine Learning Based Hydrodynamic Models for Kinetic Equations
• Interpretable Convolutional Filters with SincNet
• Wireframe-Based UI Design Search Through Image Autoencoder
• Multi-views Fusion CNN for Left Ventricular Volumes Estimation on Cardiac MR Images
• Neural Vector Spaces for Unsupervised Information Retrieval
• An overview on deep learning-based approximation methods for partial differential equations
• Exploring Deep Neural Networks via Layer-Peeled Model: Minority Collapse in Imbalanced Training
• Self-Adaptive Training: beyond Empirical Risk Minimization
• Quasi-hyperbolic momentum and Adam for deep learning
• Integrated Multi-omics Analysis Using Variational Autoencoders: Application to Pan-cancer Classification
• Order-Embeddings of Images and Language
• Complementary Pseudo Labels For Unsupervised Domain Adaptation On Person Re-identification
• WISERNet: Wider Separate-then-reunion Network for Steganalysis of Color Images
• ACNet: Strengthening the Kernel Skeletons for Powerful CNN via Asymmetric Convolution Blocks
• Meta-Learning Update Rules for Unsupervised Representation Learning
• Ensemble-Based Deep Reinforcement Learning for Chatbots
• Noise Reduction in Gravitational-wave Data via Deep Learning
• Solving high-dimensional eigenvalue problems using deep neural networks: A diffusion Monte Carlo like approach
• Incorporating human and learned domain knowledge into training deep neural networks: A differentiable dose volume histogram and adversarial inspired framework for generating Pareto optimal dose distributions in radiation therapy
• Exploiting deep residual networks for human action recognition from skeletal data
• A machine learning approach for efficient uncertainty quantification using multiscale methods
• A Decomposition-Based Hybrid Ensemble CNN Framework for Driver Fatigue Recognition
• Generating Visually Aligned Sound from Videos
• SPACE: Unsupervised Object-Oriented Scene Representation via Spatial Attention and Decomposition
• Semi-Supervised Segmentation of Radiation-Induced Pulmonary Fibrosis from Lung CT Scans with Multi-Scale Guided Dense Attention
• Beyond Self-attention: External Attention using Two Linear Layers for Visual Tasks
• A Deep Neural Network for Pixel-Level Electromagnetic Particle Identification in the MicroBooNE Liquid Argon Time Projection Chamber
• ViscNet: Neural network for predicting the fragility index and the temperature-dependency of viscosity
• An Investigation of Why Overparameterization Exacerbates Spurious Correlations
• Discovering Parametric Activation Functions
• Towards Deeper Graph Neural Networks with Differentiable Group Normalization
• Exploring Randomly Wired Neural Networks for Image Recognition
• Evolving Deep Convolutional Neural Networks for Image Classification
• ProCAN: Progressive Growing Channel Attentive Non-Local Network for Lung Nodule Classification
• A Comparison of Neural Network Architectures for Data-Driven Reduced-Order Modeling
• Training BatchNorm and Only BatchNorm: On the Expressive Power of Random Features in CNNs
• Seizure Detection using Least EEG Channels by Deep Convolutional Neural Network
• AdamP: Slowing Down the Slowdown for Momentum Optimizers on Scale-invariant Weights
• Deep Polynomial Neural Networks
• Heterogeneous Multilayer Generalized Operational Perceptron
• Automatic Annotation of Hip Anatomy in Fluoroscopy for Robust and Efficient 2D/3D Registration
• Angle-Closure Detection in Anterior Segment OCT based on Multi-Level Deep Network
• Few-Shot Learning via Embedding Adaptation with Set-to-Set Functions
• Automatic COVID-19 disease diagnosis using 1D convolutional neural network and augmentation with human respiratory sound based on parameters: cough, breath, and voice
• Rain Streak Removal for Single Image via Kernel Guided CNN
• Predicting orientation-dependent plastic susceptibility from static structure in amorphous solids via deep learning
• SCGAN: Saliency Map-guided Colorization with Generative Adversarial Network
• Revisiting Training Strategies and Generalization Performance in Deep Metric Learning
• Tensor Regression Networks
• Classification of chaotic time series with deep learning
• Scattering Networks for Hybrid Representation Learning
• T-Net: Nested encoder-decoder architecture for the main vessel segmentation in coronary angiography
• Lip-reading with Densely Connected Temporal Convolutional Networks
• A Hybrid SFANC-FxNLMS Algorithm for Active Noise Control based on Deep Learning
• Autoencoders on FPGAs for real-time, unsupervised new physics detection at 40 MHz at the Large Hadron Collider
• Probabilistic Deep Learning for Real-Time Large Deformation Simulations
• Detection of Inferior Myocardial Infarction using Shallow Convolutional Neural Networks
• IENet: Interacting Embranchment One Stage Anchor Free Detector for Orientation Aerial Object Detection
• Secure Evaluation of Quantized Neural Networks
• Three Dimensional Fluorescence Microscopy Image Synthesis and Segmentation
• Analyzing Human-Human Interactions: A Survey
• Optical Fringe Patterns Filtering Based on Multi-Stage Convolution Neural Network
• A Fully Convolutional Deep Auditory Model for Musical Chord Recognition
• Learning without feedback: Fixed random learning signals allow for feedforward training of deep neural networks
• Deep neural network improves the estimation of polygenic risk scores for breast cancer
• Super-resolution reconstruction of turbulent flow at various Reynolds numbers based on generative adversarial networks
• DisCo Fever: Robust Networks Through Distance Correlation
• Neural Networks and Quantum Field Theory
• GraphNorm: A Principled Approach to Accelerating Graph Neural Network Training
• Spiking Deep Residual Network
• COOT: Cooperative Hierarchical Transformer for Video-Text Representation Learning
• Dynamic Gesture Recognition by Using CNNs and Star RGB: a Temporal Information Condensation
• Recovering missing CFD data for high-order discretizations using deep neural networks and dynamics learning
• Adversarial Perturbations Against Real-Time Video Classification Systems
• When Do Neural Networks Outperform Kernel Methods?
• Bayesian convolutional neural network based MRI brain extraction on nonhuman primates
• PANNs: Large-Scale Pretrained Audio Neural Networks for Audio Pattern Recognition
• Deep DIH : Statistically Inferred Reconstruction of Digital In-Line Holography by Deep Learning
• Decoupled Neural Interfaces using Synthetic Gradients
• Semi-supervised multichannel speech enhancement with variational autoencoders and non-negative matrix factorization
• Enhanced Machine Learning Techniques for Early HARQ Feedback Prediction in 5G
• Learning 3D Shape Completion under Weak Supervision
• Performance of a Deep Neural Network at Detecting North Atlantic Right Whale Upcalls
• Building medical image classifiers with very limited data using segmentation networks
• Deep Unsupervised Learning for Joint Antenna Selection and Hybrid Beamforming
• Attention-Based Deep Learning Framework for Human Activity Recognition with User Adaptation
• Interaction networks for the identification of boosted $H\to b\overline{b}$ decays
• Probabilistic Neural Architecture Search
• Few-Shot Learning with Geometric Constraints
• Reference-guided Pseudo-Label Generation for Medical Semantic Segmentation
• Pricing and hedging American-style options with deep learning
• PA-ResSeg: A Phase Attention Residual Network for Liver Tumor Segmentation from Multi-phase CT Images
• Unsupervised Speech Enhancement Based on Multichannel NMF-Informed Beamforming for Noise-Robust Automatic Speech Recognition
• Wasserstein GANs for MR Imaging: from Paired to Unpaired Training
• Sequential Neural Likelihood: Fast Likelihood-free Inference with Autoregressive Flows
• Intelligent Residential Energy Management System using Deep Reinforcement Learning
• Generalized Domain Conditioned Adaptation Network
• DeepTrack: Lightweight Deep Learning for Vehicle Path Prediction in Highways
• A newcomer's guide to deep learning for inverse design in nano-photonics
• Neural Wikipedian: Generating Textual Summaries from Knowledge Base Triples
• Deep learning for presumed probability density function models
• Revisiting Self-Supervised Visual Representation Learning
• A Deep Generative Model for Graph Layout
• Modeling the Resource Requirements of Convolutional Neural Networks on Mobile Devices
• TinaFace: Strong but Simple Baseline for Face Detection
• Domain Adaptation for Ear Recognition Using Deep Convolutional Neural Networks
• End-to-end Autonomous Driving with Semantic Depth Cloud Mapping and Multi-agent
• Meta-Learning with Warped Gradient Descent
• Open Domain Event Extraction Using Neural Latent Variable Models
• Neural Sampling Machine with Stochastic Synapse allows Brain-like Learning and Inference
• Gradient Harmonized Single-stage Detector
• DeepMTS: Deep Multi-task Learning for Survival Prediction in Patients with Advanced Nasopharyngeal Carcinoma using Pretreatment PET/CT
• Urban Land Cover Classification with Missing Data Modalities Using Deep Convolutional Neural Networks
• Cross-view image synthesis using geometry-guided conditional GANs
• Hypernetwork functional image representation
• ECOVNet: An Ensemble of Deep Convolutional Neural Networks Based on EfficientNet to Detect COVID-19 From Chest X-rays
• Deep Triplet Hashing Network for Case-based Medical Image Retrieval
• Integrating uncertainty in deep neural networks for MRI based stroke analysis
• Revisiting Light Field Rendering with Deep Anti-Aliasing Neural Network
• Co-training for Demographic Classification Using Deep Learning from Label Proportions
• Deep learning dark matter map reconstructions from DES SV weak lensing data
• Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation
• Deep Learning with Low Precision by Half-wave Gaussian Quantization
• Audio-Visual Speech Separation and Dereverberation with a Two-Stage Multimodal Network
• Multivariate Probabilistic Time Series Forecasting via Conditioned Normalizing Flows
• RepMLP: Re-parameterizing Convolutions into Fully-connected Layers for Image Recognition
• DeeperForensics-1.0: A Large-Scale Dataset for Real-World Face Forgery Detection
• A Neural Network based Shock Detection and Localization Approach for Discontinuous Galerkin Methods
• Infrared and 3D skeleton feature fusion for RGB-D action recognition
• Unsupervised Learning of Depth, Optical Flow and Pose with Occlusion from 3D Geometry
• How Important is Weight Symmetry in Backpropagation?
• SWP-LeafNET: A novel multistage approach for plant leaf identification based on deep CNN
• DC3: A learning method for optimization with hard constraints
• Robust Differentiable SVD
• Cancer image classification based on DenseNet model
• Salient Object Detection with Lossless Feature Reflection and Weighted Structural Loss
• Analyzing features learned for Offline Signature Verification using Deep CNNs
• Expression Analysis Based on Face Regions in Read-world Conditions
• Hitchhiker's Guide to Super-Resolution: Introduction and Recent Advances
• Unsupervised Domain Adversarial Self-Calibration for Electromyographic-based Gesture Recognition
• Rethinking the Hyperparameters for Fine-tuning
• Toward Convolutional Blind Denoising of Real Photographs
• A Systematic IoU-Related Method: Beyond Simplified Regression for Better Localization
• Decay Replay Mining to Predict Next Process Events
• Bayesian Meta-Learning for the Few-Shot Setting via Deep Kernels
• ConTNet: Why not use convolution and transformer at the same time?
• Key Points Estimation and Point Instance Segmentation Approach for Lane Detection
• A Systematic Survey of Regularization and Normalization in GANs
• SELD-TCN: Sound Event Localization & Detection via Temporal Convolutional Networks
• Estimation of the volume of the left ventricle from MRI images using deep neural networks
• Neural Attention for Image Captioning: Review of Outstanding Methods
• Discovering Neural Wirings
• Neural Persistence: A Complexity Measure for Deep Neural Networks Using Algebraic Topology
• TimeMatch: Unsupervised Cross-Region Adaptation by Temporal Shift Estimation
• Video Representation Learning with Visual Tempo Consistency
• Panoptic Feature Pyramid Networks
• TensorLayer: A Versatile Library for Efficient Deep Learning Development
• PoNA: Pose-guided Non-local Attention for Human Pose Transfer
• Spatial Transformer Networks
• SOFT: Softmax-free Transformer with Linear Complexity
• Convolutional Sketch Inversion
• Towards automated brain aneurysm detection in TOF-MRA: open data, weak labels, and anatomical knowledge
• Convolutional Neural Networks with Gated Recurrent Connections
• STM: SpatioTemporal and Motion Encoding for Action Recognition
• Do We Need Zero Training Loss After Achieving Zero Training Error?
• Residual Dense Network for Image Restoration
• SiFall: Practical Online Fall Detection with RF Sensing
• Flight Time Prediction for Fuel Loading Decisions with a Deep Learning Approach
• Multi-Representational Learning for Offline Signature Verification using Multi-Loss Snapshot Ensemble of CNNs
• Deep AutoEncoder-based Lossy Geometry Compression for Point Clouds
• CMT: Convolutional Neural Networks Meet Vision Transformers
• Dual Adversarial Auto-Encoders for Clustering
• Deep Learning Approach for Building Detection in Satellite Multispectral Imagery
• You Only Learn Once: Universal Anatomical Landmark Detection
• EDITH :ECG biometrics aided by Deep learning for reliable Individual auTHentication
• AvatarMe++: Facial Shape and BRDF Inference with Photorealistic Rendering-Aware GANs
• Cluster Contrast for Unsupervised Person Re-Identification
• Acoustic Anomaly Detection for Machine Sounds based on Image Transfer Learning
• Dual Adaptive Representation Alignment for Cross-domain Few-shot Learning
• Denoising and Regularization via Exploiting the Structural Bias of Convolutional Generators
• DPODv2: Dense Correspondence-Based 6 DoF Pose Estimation
• Fast simulation of muons produced at the SHiP experiment using Generative Adversarial Networks
• RCCNet: An Efficient Convolutional Neural Network for Histological Routine Colon Cancer Nuclei Classification
• A Survey on Deep Domain Adaptation for LiDAR Perception
• ELF: An Extensive, Lightweight and Flexible Research Platform for Real-time Strategy Games
• StructureNet: Hierarchical Graph Networks for 3D Shape Generation
• Bi-GCN: Binary Graph Convolutional Network
• One-Two-One Networks for Compression Artifacts Reduction in Remote Sensing
• Pervasive Attention: 2D Convolutional Neural Networks for Sequence-to-Sequence Prediction
• Effective Training Strategies for Deep-learning-based Precipitation Nowcasting and Estimation
• Asymmetric Residual Neural Network for Accurate Human Activity Recognition
• Multi-scale Convolutional Neural Networks for Inverse Problems
• Morphological classification of galaxies with deep learning: comparing 3-way and 4-way CNNs
• Search for pair production of heavy vector-like quarks decaying into hadronic final states in $pp$ collisions at $\sqrt{s}=13$ TeV with the ATLAS detector
• Reducing Noise in GAN Training with Variance Reduced Extragradient
• AutoTune: Automatically Tuning Convolutional Neural Networks for Improved Transfer Learning
• Lane Detection Model Based on Spatio-Temporal Network With Double Convolutional Gated Recurrent Units
• Lessons Learned from Designing an AI-Enabled Diagnosis Tool for Pathologists
• Deep Graph Matching Consensus
• Deep Ensembles vs. Committees for Uncertainty Estimation in Neural-Network Force Fields: Comparison and Application to Active Learning
• SRECG: ECG Signal Super-resolution Framework for Portable/Wearable Devices in Cardiac Arrhythmias Classification
• SNIPER: Efficient Multi-Scale Training
• Real-time System Identification Using Deep Learning for Linear Processes with Application to Unmanned Aerial Vehicles
• Receptive Field Regularization Techniques for Audio Classification and Tagging with Deep Convolutional Neural Networks
• Self-attending RNN for Speech Enhancement to Improve Cross-corpus Generalization
• Invariance Matters: Exemplar Memory for Domain Adaptive Person Re-identification
• Generalized Wasserstein Dice Score, Distributionally Robust Deep Learning, and Ranger for brain tumor segmentation: BraTS 2020 challenge
• Lightweight Modules for Efficient Deep Learning based Image Restoration
• Predicting Temporal Sets with Deep Neural Networks
• Aligning Pretraining for Detection via Object-Level Contrastive Learning
• Learning Deep Structure-Preserving Image-Text Embeddings
• Batch Normalization is a Cause of Adversarial Vulnerability
• Segmentation of histological images and fibrosis identification with a convolutional neural network
• Neural Predictive Coding using Convolutional Neural Networks towards Unsupervised Learning of Speaker Characteristics
• Lightweight Pixel Difference Networks for Efficient Visual Representation Learning
• ReduNet: A White-box Deep Network from the Principle of Maximizing Rate Reduction
• PixelBNN: Augmenting the PixelCNN with batch normalization and the presentation of a fast architecture for retinal vessel segmentation
• You Only Hear Once: A YOLO-like Algorithm for Audio Segmentation and Sound Event Detection
• Effective and Efficient Dropout for Deep Convolutional Neural Networks
• i-Mix: A Domain-Agnostic Strategy for Contrastive Representation Learning
• Evolving Normalization-Activation Layers
• OSLNet: Deep Small-Sample Classification with an Orthogonal Softmax Layer
• Multi-Modal MRI Reconstruction Assisted with Spatial Alignment Network
• PruneTrain: Fast Neural Network Training by Dynamic Sparse Model Reconfiguration
• Multiscale Deep Equilibrium Models
• SiTGRU: Single-Tunnelled Gated Recurrent Unit for Abnormality Detection
• DeFMO: Deblurring and Shape Recovery of Fast Moving Objects
• Strong error analysis for stochastic gradient descent optimization algorithms
• Translating and Segmenting Multimodal Medical Volumes with Cycle- and Shape-Consistency Generative Adversarial Network
• Zero-Shot Action Recognition in Videos: A Survey
• Quasi Anomalous Knowledge: Searching for new physics with embedded knowledge
• Square Kilometre Array Science Data Challenge 1: analysis and results
• Automatic Prediction of Building Age from Photographs
• Robotic Endoscope Control via Autonomous Instrument Tracking
• Learning from synthetic photorealistic raindrop for single image raindrop removal
• Is Attention Better Than Matrix Decomposition?
• A Spatiotemporal Deep Neural Network for Fine-Grained Multi-Horizon Wind Prediction
• TCGAN: Convolutional Generative Adversarial Network for Time Series Classification and Clustering
• Driver Behavior Recognition via Interwoven Deep Convolutional Neural Nets with Multi-stream Inputs
• Normalization Techniques in Training DNNs: Methodology, Analysis and Application
• DQC: a Python program package for Differentiable Quantum Chemistry
• Restructuring Batch Normalization to Accelerate CNN Training
• Training Neural Networks Using Features Replay
• Deep residual detection of radio frequency interference for FAST
• Toward Extremely Lightweight Distracted Driver Recognition With Distillation-Based Neural Architecture Search and Knowledge Transfer
• Neural Network Reconstruction of Late-Time Cosmology and Null Tests
• Deep learning for plasma tomography using the bolometer system at JET
• Generative Modeling of Turbulence
• Adaptive deep density approximation for Fokker-Planck equations
• Tensor Programs II: Neural Tangent Kernel for Any Architecture
• Gait recognition via deep learning of the center-of-pressure trajectory
• Convolutional Neural Networks for Multispectral Image Cloud Masking
• Temporal Segment Networks for Action Recognition in Videos
• A volumetric deep Convolutional Neural Network for simulation of mock dark matter halo catalogues
• Pruning and Quantization for Deep Neural Network Acceleration: A Survey
• Automated detection of vulnerable plaque in intravascular ultrasound images
• DFTerNet: Towards 2-bit Dynamic Fusion Networks for Accurate Human Activity Recognition
• NeST: A Neural Network Synthesis Tool Based on a Grow-and-Prune Paradigm
• Multispectral Vineyard Segmentation: A Deep Learning approach
• Generative adversarial network-based glottal waveform model for statistical parametric speech synthesis
• The Early Phase of Neural Network Training
• Learning nonlocal constitutive models with neural networks
• Early Exit or Not: Resource-Efficient Blind Quality Enhancement for Compressed Images
• Learning Generalisable Omni-Scale Representations for Person Re-Identification
• "No, to the Right" -- Online Language Corrections for Robotic Manipulation via Shared Autonomy
• Complex-valued neural networks for machine learning on non-stationary physical data
• CONNECT: A neural network based framework for emulating cosmological observables and cosmological parameter inference
• Data-Efficient Reinforcement Learning with Self-Predictive Representations
• Learning Improvement Heuristics for Solving Routing Problems
• Development of Skip Connection in Deep Neural Networks for Computer Vision and Medical Image Analysis: A Survey
• On the Minimal Supervision for Training Any Binary Classifier from Only Unlabeled Data
• Efficient Neural Architecture Transformation Searchin Channel-Level for Object Detection
• StereoSpike: Depth Learning with a Spiking Neural Network
• QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answering
• Batch-Shaping for Learning Conditional Channel Gated Networks
• Lightweight Neural Architecture Search for Temporal Convolutional Networks at the Edge
• Inter- and intra-uncertainty based feature aggregation model for semi-supervised histopathology image segmentation
• Scaling Spike-driven Transformer with Efficient Spike Firing Approximation Training
• Primordial non-Gaussianity from the Completed SDSS-IV extended Baryon Oscillation Spectroscopic Survey I: Catalogue Preparation and Systematic Mitigation
• Search for electroweak production of charginos and neutralinos in proton-proton collisions at $\sqrt{s}=$ 13 TeV
• Ensemble of Averages: Improving Model Selection and Boosting Performance in Domain Generalization
• Deep-Learning-Based Audio-Visual Speech Enhancement in Presence of Lombard Effect
• Uncertainty-Aware Deep Ensembles for Reliable and Explainable Predictions of Clinical Time Series
• V4D:4D Convolutional Neural Networks for Video-level Representation Learning
• s-LWSR: Super Lightweight Super-Resolution Network
• Adversarial Examples Improve Image Recognition
• Neural Vocoder is All You Need for Speech Super-resolution
• Video Representation Learning by Dense Predictive Coding
• The Gaussian equivalence of generative models for learning with shallow neural networks
• Distribution Matching in Variational Inference
• Attention Guided Low-light Image Enhancement with a Large Scale Low-light Simulation Dataset
• SAR Target Image Generation Method Using Azimuth-Controllable Generative Adversarial Network
• Survey of Dropout Methods for Deep Neural Networks
• Point-Cloud Deep Learning of Porous Media for Permeability Prediction
• Network Randomization: A Simple Technique for Generalization in Deep Reinforcement Learning
• Dual Rectified Linear Units (DReLUs): A Replacement for Tanh Activation Functions in Quasi-Recurrent Neural Networks
• Self-Supervised Pre-Training for Transformer-Based Person Re-Identification
• Boosted $W/Z$ Tagging with Jet Charge and Deep Learning
• IB-GAN: Disentangled Representation Learning with Information Bottleneck Generative Adversarial Networks
• Efficient Saliency Maps for Explainable AI
• Transformer Encoder with Multiscale Deep Learning for Pain Classification Using Physiological Signals
• Learning Memory-guided Normality for Anomaly Detection
• Neural networks in pulsed dipolar spectroscopy: a practical guide
• Learning physical properties of anomalous random walks using graph neural networks
• Competitive Inner-Imaging Squeeze and Excitation for Residual Network
• RepVGG: Making VGG-style ConvNets Great Again
• GCoNet+: A Stronger Group Collaborative Co-Salient Object Detector
• Using convolutional neural networks to predict galaxy metallicity from three-color images
• PoreNet: CNN-based Pore Descriptor for High-resolution Fingerprint Recognition
• Semantic Segmentation Using Deep Learning to Extract Total Extraocular Muscles and Optic Nerve from Orbital Computed Tomography Images
• Weisfeiler and Lehman Go Topological: Message Passing Simplicial Networks
• Optimization of data-driven filterbank for automatic speaker verification
• Universal Statistics of Fisher Information in Deep Neural Networks: Mean Field Approach
• Advanced sleep spindle identification with neural networks
• Machine learning astrophysics from 21 cm lightcones: impact of network architectures and signal contamination
• NeuroLKH: Combining Deep Learning Model with Lin-Kernighan-Helsgaun Heuristic for Solving the Traveling Salesman Problem
• Are we done with object recognition? The iCub robot's perspective
• TernaryNet: Faster Deep Model Inference without GPUs for Medical 3D Segmentation using Sparse and Binary Convolutions
• 3D shape sensing and deep learning-based segmentation of strawberries
• Indoor environment data time-series reconstruction using autoencoder neural networks
• Detection of Gravitational Waves Using Bayesian Neural Networks
• WaveGrad: Estimating Gradients for Waveform Generation
• Lesion Segmentation in Ultrasound Using Semi-pixel-wise Cycle Generative Adversarial Nets
• Learning to Simulate High Energy Particle Collisions from Unlabeled Data
• K for the Price of 1: Parameter-efficient Multi-task and Transfer Learning
• IMAE for Noise-Robust Learning: Mean Absolute Error Does Not Treat Examples Equally and Gradient Magnitude's Variance Matters
• Back to Simplicity: How to Train Accurate BNNs from Scratch?
• KD3A: Unsupervised Multi-Source Decentralized Domain Adaptation via Knowledge Distillation
• Longitudinal Dynamic versus Kinematic Models for Car-Following Control Using Deep Reinforcement Learning
• Compensating for visibility artefacts in photoacoustic imaging with a deep learning approach providing prediction uncertainties
• DAIS: Automatic Channel Pruning via Differentiable Annealing Indicator Search
• A deep learning framework for the detection and quantification of drusen and reticular pseudodrusen on optical coherence tomography
• A Geometric Analysis of Neural Collapse with Unconstrained Features
• Diverse Human Motion Prediction Guided by Multi-Level Spatial-Temporal Anchors
• MiniSeg: An Extremely Minimum Network for Efficient COVID-19 Segmentation
• An Exponential Learning Rate Schedule for Deep Learning
• Deep Ranking Model by Large Adaptive Margin Learning for Person Re-identification
• Parkinson's Disease Recognition Using SPECT Image and Interpretable AI: A Tutorial
• Four Things Everyone Should Know to Improve Batch Normalization
• A Comprehensive Review of Modern Object Segmentation Approaches
• An Empirical Study on Writer Identification & Verification from Intra-variable Individual Handwriting
• Crowding Reveals Fundamental Differences in Local vs. Global Processing in Humans and Machines
• Progressive Pose Attention Transfer for Person Image Generation
• SRM : A Style-based Recalibration Module for Convolutional Neural Networks
• IRNet: A General Purpose Deep Residual Regression Framework for Materials Discovery
• Fully Automatic Electrocardiogram Classification System based on Generative Adversarial Network with Auxiliary Classifier
• DER: Dynamically Expandable Representation for Class Incremental Learning
• Generative Capacity of Probabilistic Protein Sequence Models
• ELF OpenGo: An Analysis and Open Reimplementation of AlphaZero
• Uncovering Temporal Context for Video Question and Answering
• Adversarial Spheres
• HCR-Net: A deep learning based script independent handwritten character recognition network
• Panoptic-DeepLab: A Simple, Strong, and Fast Baseline for Bottom-Up Panoptic Segmentation
• Whitening for Self-Supervised Representation Learning
• 3D Mesh Segmentation via Multi-branch 1D Convolutional Neural Networks
• The LHC Olympics 2020: A Community Challenge for Anomaly Detection in High Energy Physics
• Robust Training of Vector Quantized Bottleneck Models
• Tensor Programs I: Wide Feedforward or Recurrent Neural Networks of Any Architecture are Gaussian Processes
• Message-Passing Neural Networks Learn Little's Law
• Distinguishing Computer-generated Graphics from Natural Images Based on Sensor Pattern Noise and Deep Learning
• Domain Generalization with MixStyle
• Learned Camera Gain and Exposure Control for Improved Visual Feature Detection and Matching
• DeltaConv: Anisotropic Operators for Geometric Deep Learning on Point Clouds
• Deep Learning-Based Computer Vision for Real Time Intravenous Drip Infusion Monitoring
• UNetGAN: A Robust Speech Enhancement Approach in Time Domain for Extremely Low Signal-to-noise Ratio Condition
• Learning based Facial Image Compression with Semantic Fidelity Metric
• Mapping oil palm density at country scale: An active learning approach
• Red Alarm for Pre-trained Models: Universal Vulnerability to Neuron-Level Backdoor Attacks
• Concussion classification via deep learning using whole-brain white matter fiber strains
• Neural ranking models for document retrieval
• Speech Emotion Recognition via Contrastive Loss under Siamese Networks
• Learning to Paint With Model-based Deep Reinforcement Learning
• Convolution with even-sized kernels and symmetric padding
• Rethinking Classification and Localization for Object Detection
• Adaptive Image Sampling using Deep Learning and its Application on X-Ray Fluorescence Image Reconstruction
• Decoding ECoG signal into 3D hand translation using deep learning
• Learning to Recognize 3D Human Action from A New Skeleton-based Representation Using Deep Convolutional Neural Networks
• Neural Metric Learning for Fast End-to-End Relation Extraction
• Transfer learning for radio galaxy classification
• Dynamic Neural Networks: A Survey
• Improving Electron Micrograph Signal-to-Noise with an Atrous Convolutional Encoder-Decoder
• ASSANet: An Anisotropic Separable Set Abstraction for Efficient Point Cloud Representation Learning
• Multi-task Learning For Detecting and Segmenting Manipulated Facial Images and Videos
• PeaceGAN: A GAN-based Multi-Task Learning Method for SAR Target Image Generation with a Pose Estimator and an Auxiliary Classifier
• Fusion-Catalyzed Pruning for Optimizing Deep Learning on Intelligent Edge Devices
• Measurements of inclusive and differential fiducial cross-sections of $t\bar{t}\gamma$ production in leptonic final states at $\sqrt{s}$ = 13 TeV in ATLAS
• Neural Networks Versus Conventional Filters for Inertial-Sensor-based Attitude Estimation
• Dirichlet Energy Constrained Learning for Deep Graph Neural Networks
• Disentangled Representations for Short-Term and Long-Term Person Re-Identification
• Hierarchical binary CNNs for landmark localization with limited resources
• Neural Ordinary Differential Equation Control of Dynamics on Graphs
• On the Protection of Private Information in Machine Learning Systems: Two Recent Approaches
• Learning Regional Attraction for Line Segment Detection
• Competitive Multi-scale Convolution
• Binary Single-dimensional Convolutional Neural Network for Seizure Prediction
• Predictive-Corrective Networks for Action Detection
• Automatic quantification of the LV function and mass: a deep learning approach for cardiovascular MRI
• Deep Learning for Simultaneous Inference of Hydraulic and Transport Properties
• Unified Probabilistic Deep Continual Learning through Generative Replay and Open Set Recognition
• DVAE++: Discrete Variational Autoencoders with Overlapping Transformations
• Fully Convolutional Networks for Chip-wise Defect Detection Employing Photoluminescence Images
• Joint Transmission Map Estimation and Dehazing using Deep Networks
• Analysis of Deep Clustering as Preprocessing for Automatic Speech Recognition of Sparsely Overlapping Speech
• Improving Efficiency in Convolutional Neural Network with Multilinear Filters
• Ensemble learning in CNN augmented with fully connected subnetworks
• Towards Better Understanding Attribution Methods
• Flatten-T Swish: a thresholded ReLU-Swish-like activation function for deep learning
• DnS: Distill-and-Select for Efficient and Accurate Video Indexing and Retrieval
• Dynamical Isometry and a Mean Field Theory of CNNs: How to Train 10,000-Layer Vanilla Convolutional Neural Networks
• Deep learning approach for identification of HII regions during reionization in 21-cm observations
• A Survey of Machine Learning Methods and Challenges for Windows Malware Classification
• Predicting Basin Stability of Power Grids using Graph Neural Networks
• RetroComposer: Composing Templates for Template-Based Retrosynthesis Prediction
• State estimation with limited sensors -- A deep learning based approach
• Checkmate: Breaking the Memory Wall with Optimal Tensor Rematerialization
• Convolutional Autoencoder-Based Phase Shift Feedback Compression for Intelligent Reflecting Surface-Assisted Wireless Systems
• Speaker Diarization using Deep Recurrent Convolutional Neural Networks for Speaker Embeddings
• Privacy Adversarial Network: Representation Learning for Mobile Data Privacy
• SA-UNet: Spatial Attention U-Net for Retinal Vessel Segmentation
• Convolutional neural networks enable high-fidelity prediction of path-dependent diffusion barrier spectra in multi-principal element alloys
• Quarks and gluons in the Lund plane
• Transductive Episodic-Wise Adaptive Metric for Few-Shot Learning
• Portraying Double Higgs at the Large Hadron Collider
• Low-Memory Neural Network Training: A Technical Report
• Learning to Adapt Invariance in Memory for Person Re-identification
• Deep learning jet modifications in heavy-ion collisions
• Deep learning-based photoacoustic imaging of vascular network through thick porous media
• SqueezeSegV2: Improved Model Structure and Unsupervised Domain Adaptation for Road-Object Segmentation from a LiDAR Point Cloud
• An Empirical Evaluation on Robustness and Uncertainty of Regularization Methods
• MSED: a multi-modal sleep event detection model for clinical sleep analysis
• On-device Training: A First Overview on Existing Systems
• Contrastive Self-supervised Neural Architecture Search
• ISTA-NAS: Efficient and Consistent Neural Architecture Search by Sparse Coding
• Inferring Latent Domains for Unsupervised Deep Domain Adaptation
• Concat Convolutional Neural Network for Pulsar Candidate Selection
• Learning Deep Morphological Networks with Neural Architecture Search
• Comparative evaluation of CNN architectures for Image Caption Generation
• Cross-task learning for audio tagging, sound event detection and spatial localization: DCASE 2019 baseline systems
• DD-PPO: Learning Near-Perfect PointGoal Navigators from 2.5 Billion Frames
• Cut-Thumbnail: A Novel Data Augmentation for Convolutional Neural Network
• Many-Class Few-Shot Learning on Multi-Granularity Class Hierarchy
• AutoFIS: Automatic Feature Interaction Selection in Factorization Models for Click-Through Rate Prediction
• Progressive Identification of True Labels for Partial-Label Learning
• LieTransformer: Equivariant self-attention for Lie Groups
• Confidence-Calibrated Adversarial Training: Generalizing to Unseen Attacks
• Kronecker Attention Networks
• Automatic Segmentation of Thoracic Aorta Segments in Low-Dose Chest CT
• Deep speech inpainting of time-frequency masks
• Quaternion Generative Adversarial Networks
• Asymmetric Valleys: Beyond Sharp and Flat Local Minima
• Data Augmentation Revisited: Rethinking the Distribution Gap between Clean and Augmented Data
• Deep Learning based Switching Filter for Impulsive Noise Removal in Color Images
• Universal Adversarial Audio Perturbations
• Neural Network Decoders for Large-Distance 2D Toric Codes
• H-CNN: Spatial Hashing Based CNN for 3D Shape Analysis
• PHD-GIFs: Personalized Highlight Detection for Automatic GIF Creation
• An Empirical Study on Leveraging Scene Graphs for Visual Question Answering
• Searching for Low-Bit Weights in Quantized Neural Networks
• A Deep Learning Approach for Pose Estimation from Volumetric OCT Data
• RAPID: Retrofitting IEEE 802.11ay Access Points for Indoor Human Detection and Sensing
• Iterative Network for Image Super-Resolution
• Extracting gamma-ray information from images with convolutional neural network methods on simulated Cherenkov Telescope Array data
• A Learning Framework for n-bit Quantized Neural Networks toward FPGAs
• Non-Rigid Point Set Registration Networks
• Event reconstruction for KM3NeT/ORCA using convolutional neural networks
• Fuzzy Pooling
• Space4HGNN: A Novel, Modularized and Reproducible Platform to Evaluate Heterogeneous Graph Neural Network
• Guided Anisotropic Diffusion and Iterative Learning for Weakly Supervised Change Detection
• Learning Deep NBNN Representations for Robust Place Categorization
• Understanding Self-supervised Learning with Dual Deep Networks
• A Comprehensive and Modularized Statistical Framework for Gradient Norm Equality in Deep Neural Networks
• TinyTL: Reduce Activations, Not Trainable Parameters for Efficient On-Device Learning
• Deeply Self-Supervised Contour Embedded Neural Network Applied to Liver Segmentation
• Learning Spatiotemporal Features via Video and Text Pair Discrimination
• The NN-Stacking: Feature weighted linear stacking through neural networks
• End-to-End Adversarial Text-to-Speech
• Generative Adversarial Networks for Image and Video Synthesis: Algorithms and Applications
• Electromagnetic Showers Beyond Shower Shapes
• ES-ImageNet: A Million Event-Stream Classification Dataset for Spiking Neural Networks
• Prototype Learning Guided Hybrid Network for Breast Tumor Segmentation in DCE-MRI
• Variational Context: Exploiting Visual and Textual Context for Grounding Referring Expressions
• Long-Term Feature Banks for Detailed Video Understanding
• When Deep Learning Meets Multi-Task Learning in SAR ATR: Simultaneous Target Recognition and Segmentation
• Pixel-Level Clustering Network for Unsupervised Image Segmentation
• Class-incremental Learning with Pre-allocated Fixed Classifiers
• Pretraining Representations for Data-Efficient Reinforcement Learning
• Adversarial Distributional Training for Robust Deep Learning
• Towards Better Accuracy-efficiency Trade-offs: Divide and Co-training
• InversionNet3D: Efficient and Scalable Learning for 3D Full Waveform Inversion
• Considerations When Learning Additive Explanations for Black-Box Models
• North Ecliptic Pole merging galaxy catalogue
• Learning to Optimize Domain Specific Normalization for Domain Generalization
• DensePoint: Learning Densely Contextual Representation for Efficient Point Cloud Processing
• MaX-DeepLab: End-to-End Panoptic Segmentation with Mask Transformers
• torchgpipe: On-the-fly Pipeline Parallelism for Training Giant Models
• Self-Supervised Learning for Domain Adaptation on Point-Clouds
• Adaptive neighborhood Metric learning
• The Perfect Match: 3D Point Cloud Matching with Smoothed Densities
• Faster Neural Network Training with Data Echoing
• The Break-Even Point on Optimization Trajectories of Deep Neural Networks
• Attentive Semantic Exploring for Manipulated Face Detection
• Machine learning for complete intersection Calabi-Yau manifolds: a methodological study
• Meta-Transfer Learning for Few-Shot Learning
• Improved Selective Refinement Network for Face Detection
• Baryon acoustic oscillations reconstruction using convolutional neural networks
• Inferring a Continuous Distribution of Atom Coordinates from Cryo-EM Images using VAEs
• InGAN: Capturing and Remapping the "DNA" of a Natural Image
• To Explain or Not to Explain: A Study on the Necessity of Explanations for Autonomous Vehicles
• RAVEN: A Dataset for Relational and Analogical Visual rEasoNing
• A Novel Weight-Shared Multi-Stage CNN for Scale Robustness
• MEMC-Net: Motion Estimation and Motion Compensation Driven Neural Network for Video Interpolation and Enhancement
• MetaFormer Is Actually What You Need for Vision
• MRI Super-Resolution with GAN and 3D Multi-Level DenseNet: Smaller, Faster, and Better
• sMRI-PatchNet: A novel explainable patch-based deep learning network for Alzheimer's disease diagnosis and discriminative atrophy localisation with Structural MRI
• OptEmbed: Learning Optimal Embedding Table for Click-through Rate Prediction
• Granger-causal Attentive Mixtures of Experts: Learning Important Features with Neural Networks
• Fine-grained Solar Flare Forecasting Based on the Hybrid Convolutional Neural Networks
• Application of machine learning in the determination of impact parameter in the ${}^{132}$Sn+${}^{124}$Sn system
• Exploring Architectural Ingredients of Adversarially Robust Deep Neural Networks
• Mitigating Overfitting in Supervised Classification from Two Unlabeled Datasets: A Consistent Risk Correction Approach
• TAda! Temporally-Adaptive Convolutions for Video Understanding
• AIBench: An Industry Standard Internet Service AI Benchmark Suite
• Collaborative Spatio-temporal Feature Learning for Video Action Recognition
• Artificial Intelligence in Materials Science and Engineering: Current Landscape, Key Challenges, and Future Trajectorie
• Gaze-based dual resolution deep imitation learning for high-precision dexterous robot manipulation
• Dim but not entirely dark: Extracting the Galactic Center Excess' source-count distribution with neural nets
• Light curve classification with recurrent neural networks for GOTO: dealing with imbalanced data
• Semantic segmentation of mFISH images using convolutional networks
• Regularizing Class-wise Predictions via Self-knowledge Distillation
• Robust Tumor Localization with Pyramid Grad-CAM
• Extracting the Subhalo Mass Function from Strong Lens Images with Image Segmentation
• Cross-Camera Feature Prediction for Intra-Camera Supervised Person Re-identification across Distant Scenes
• Video Action Understanding
• Towards Stabilizing Batch Statistics in Backward Propagation of Batch Normalization
• SSAP: Single-Shot Instance Segmentation With Affinity Pyramid
• ElasticTrainer: Speeding Up On-Device Training with Runtime Elastic Tensor Selection
• JDSR-GAN: Constructing An Efficient Joint Learning Network for Masked Face Super-Resolution
• A Neural Influence Diffusion Model for Social Recommendation
• The Difficulty of Training Sparse Neural Networks
• Incremental Few-Shot Learning with Attention Attractor Networks
• Self-Supervised Visual Learning by Variable Playback Speeds Prediction of a Video
• Densely connected neural networks for nonlinear regression
• Large-Scale Representation Learning on Graphs via Bootstrapping
• Deep Semi-Supervised Anomaly Detection
• Synthesizing Speech from Intracranial Depth Electrodes using an Encoder-Decoder Framework
• FitVid: Overfitting in Pixel-Level Video Prediction
• Co-salient Object Detection Based on Deep Saliency Networks and Seed Propagation over an Integrated Graph
• Impedance-optical Dual-modal Cell Culture Imaging with Learning-based Information Fusion
• On the Benefit of Adversarial Training for Monocular Depth Estimation
• Towards constraining warm dark matter with stellar streams through neural simulation-based inference
• Deep Reinforcement Learning for Closed-Loop Blood Glucose Control
• Every Pixel Counts ++: Joint Learning of Geometry and Motion with 3D Holistic Understanding
• Attention Meets Perturbations: Robust and Interpretable Attention with Adversarial Training
• Pillar-based Object Detection for Autonomous Driving
• Comparison Analysis of Traditional Machine Learning and Deep Learning Techniques for Data and Image Classification
• Deep Fictitious Play for Finding Markovian Nash Equilibrium in Multi-Agent Games
• Focal Frequency Loss for Image Reconstruction and Synthesis
• Source-free Domain Adaptation via Distributional Alignment by Matching Batch Normalization Statistics
• Human Vocal Sentiment Analysis
• Data-Driven Sparse Structure Selection for Deep Neural Networks
• Noise-aware Physics-informed Machine Learning for Robust PDE Discovery
• DivGraphPointer: A Graph Pointer Network for Extracting Diverse Keyphrases
• On the Use of Neural Networks for Energy Reconstruction in High-granularity Calorimeters
• Deep Contextual Bandit and Reinforcement Learning for IRS-Assisted MU-MIMO Systems
• Feature Overcorrelation in Deep Graph Neural Networks: A New Perspective
• Self-learning Monte Carlo method with Behler-Parrinello neural networks
• Alleviating the transit timing variation bias in transit surveys. I. RIVERS: Method and detection of a pair of resonant super-Earths around Kepler-1705
• Efficient Riemannian Optimization on the Stiefel Manifold via the Cayley Transform
• Deep Learning based Channel Estimation for Massive MIMO with Hybrid Transceivers
• Source Free Domain Adaptation with Image Translation
• DeepMTL Pro: Deep Learning Based MultipleTransmitter Localization and Power Estimation
• Single-exposure absorption imaging of ultracold atoms using deep learning
• Exploring Cross-Domain Pretrained Model for Hyperspectral Image Classification
• Better Compression with Deep Pre-Editing
• FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation
• Icentia11K: An Unsupervised Representation Learning Dataset for Arrhythmia Subtype Discovery
• Asymmetric Contextual Modulation for Infrared Small Target Detection
• Weight-Sharing Neural Architecture Search: A Battle to Shrink the Optimization Gap
• BigDataBench: A Scalable and Unified Big Data and AI Benchmark Suite
• Exponential convergence rates for Batch Normalization: The power of length-direction decoupling in non-convex optimization
• Unbiased Teacher for Semi-Supervised Object Detection
• Large-Scale Generative Data-Free Distillation
• Efficient feature learning and multi-size image steganalysis based on CNN
• Scaling Wide Residual Networks for Panoptic Segmentation
• Deep Learning Aided Packet Routing in Aeronautical Ad-Hoc Networks Relying on Real Flight Data: From Single-Objective to Near-Pareto Multi-Objective Optimization
• Mean-field theory of graph neural networks in graph partitioning
• Speech and Speaker Recognition from Raw Waveform with SincNet
• Comparing Neural- and N-Gram-Based Language Models for Word Segmentation
• Large-scale Landmark Retrieval/Recognition under a Noisy and Diverse Dataset
• RMVPE: A Robust Model for Vocal Pitch Estimation in Polyphonic Music
• HySpecNet-11k: A Large-Scale Hyperspectral Dataset for Benchmarking Learning-Based Hyperspectral Image Compression Methods
• Data-driven Cloud Clustering via a Rotationally Invariant Autoencoder
• Spatially Regularized Parametric Map Reconstruction for Fast Magnetic Resonance Fingerprinting
• Binary Neural Networks for Memory-Efficient and Effective Visual Place Recognition in Changing Environments
• Learning to Set Waypoints for Audio-Visual Navigation
• Deep Convolutional Neural Network for Identifying Seam-Carving Forgery
• What Do Neural Networks Learn When Trained With Random Labels?
• EPNet: Enhancing Point Features with Image Semantics for 3D Object Detection
• RatLesNetv2: A Fully Convolutional Network for Rodent Brain Lesion Segmentation
• Distinguishing mirror from glass: A 'big data' approach to material perception
• Channel Compression: Rethinking Information Redundancy among Channels in CNN Architecture
• Searches for Compact Binary Coalescence Events using Neural Networks in LIGO/Virgo Second Observation Period
• Accurate Retinal Vessel Segmentation via Octave Convolution Neural Network
• CASTLE: Regularization via Auxiliary Causal Graph Discovery
• Parrot: Data-Driven Behavioral Priors for Reinforcement Learning
• Episodic Training for Domain Generalization
• On Filter Generalization for Music Bandwidth Extension Using Deep Neural Networks
• Adversarial Neuron Pruning Purifies Backdoored Deep Models
• Efficient Dense Modules of Asymmetric Convolution for Real-Time Semantic Segmentation
• SPRING: A Sparsity-Aware Reduced-Precision Monolithic 3D CNN Accelerator Architecture for Training and Inference
• Neural Spline Flows
• Beyond Heart Murmur Detection: Automatic Murmur Grading from Phonocardiogram
• HINet: Half Instance Normalization Network for Image Restoration
• FabricNet: A Fiber Recognition Architecture Using Ensemble ConvNets
• Deep encoder-decoder hierarchical convolutional neural networks for conjugate heat transfer surrogate modeling
• Shared Data and Algorithms for Deep Learning in Fundamental Physics
• Automated Segmentation of Pulmonary Lobes using Coordination-Guided Deep Neural Networks
• Few-Shot Learning with Global Class Representations
• Data-driven Crop Growth Simulation on Time-varying Generated Images using Multi-conditional Generative Adversarial Networks
• Contrastive Multiview Coding with Electro-optics for SAR Semantic Segmentation
• Empirical Studies on the Properties of Linear Regions in Deep Neural Networks
• Multi-Scored Sleep Databases: How to Exploit the Multiple-Labels in Automated Sleep Scoring
• Region-based Quality Estimation Network for Large-scale Person Re-identification
• Mathematical Models of Overparameterized Neural Networks
• Tracking perovskite crystallization via deep learning-based feature detection on 2D X-ray scattering data
• Rethinking "Batch" in BatchNorm
• Self-supervised Multi-view Person Association and Its Applications
• Relational Learning between Multiple Pulmonary Nodules via Deep Set Attention Transformers
• Exploring Data Augmentation for Multi-Modality 3D Object Detection
• Structured LISTA for Multidimensional Harmonic Retrieval
• Principled Training of Neural Networks with Direct Feedback Alignment
• Transcribing Content from Structural Images with Spotlight Mechanism
• Fast and accurate dose predictions for novel radiotherapy treatments in heterogeneous phantoms using conditional 3D-UNet generative adversarial networks
• Semi-supervised Anomaly Detection using AutoEncoders
• Hybrid Deep Network for Anomaly Detection
• DML-GANR: Deep Metric Learning With Generative Adversarial Network Regularization for High Spatial Resolution Remote Sensing Image Retrieval
• FlexConv: Continuous Kernel Convolutions with Differentiable Kernel Sizes
• Do Not Let Privacy Overbill Utility: Gradient Embedding Perturbation for Private Learning
• Patch Refinement -- Localized 3D Object Detection
• Image Classification with Hierarchical Multigraph Networks
• AssembleNet: Searching for Multi-Stream Neural Connectivity in Video Architectures
• A deep learning driven pseudospectral PCE based FFT homogenization algorithm for complex microstructures
• Disentangled Self-Attentive Neural Networks for Click-Through Rate Prediction
• Domain-Specific Batch Normalization for Unsupervised Domain Adaptation
• New Benchmarks for Learning on Non-Homophilous Graphs
• Decentralized and Model-Free Federated Learning: Consensus-Based Distillation in Function Space
• Multi-Attention-Based Soft Partition Network for Vehicle Re-Identification
• Graph Neural Networks with Learnable Structural and Positional Representations
• Robust Conditional Generative Adversarial Networks
• Reducing the Model Variance of a Rectal Cancer Segmentation Network
• Improved Residual Networks for Image and Video Recognition
• Recent Advances in Deep Learning for Object Detection
• Deep Volumetric Ambient Occlusion
• A Large RGB-D Dataset for Semi-supervised Monocular Depth Estimation
• Demonstration of background rejection using deep convolutional neural networks in the NEXT experiment
• Learning Implicitly Recurrent CNNs Through Parameter Sharing
• Objectness Scoring and Detection Proposals in Forward-Looking Sonar Images with Convolutional Neural Networks
• Decentralized Learning of Generative Adversarial Networks from Non-iid Data
• Boosting Neural Machine Translation
• MARS: Multi-macro Architecture SRAM CIM-Based Accelerator with Co-designed Compressed Neural Networks
• S-Net: A Scalable Convolutional Neural Network for JPEG Compression Artifact Reduction
• Investigating U-Nets with various Intermediate Blocks for Spectrogram-based Singing Voice Separation
• Deep Learning for Identifying Iran's Cultural Heritage Buildings in Need of Conservation Using Image Classification and Grad-CAM
• Rethinking of Pedestrian Attribute Recognition: A Reliable Evaluation under Zero-Shot Pedestrian Identity Setting
• Automatic segmentation method of pelvic floor levator hiatus in ultrasound using a self-normalising neural network
• ForceNet: A Graph Neural Network for Large-Scale Quantum Calculations
• Refinement of polygonal grids using Convolutional Neural Networks with applications to polygonal Discontinuous Galerkin and Virtual Element methods
• High-resolution Deep Convolutional Generative Adversarial Networks
• Jigsaw Puzzle Solving Using Local Feature Co-Occurrences in Deep Neural Networks
• Como funciona o Deep Learning
• Weather GAN: Multi-Domain Weather Translation Using Generative Adversarial Networks
• Background Adaptive Faster R-CNN for Semi-Supervised Convolutional Object Detection of Threats in X-Ray Images
• ProGraML: Graph-based Deep Learning for Program Optimization and Analysis
• Dalek -- a deep-learning emulator for TARDIS
• Addressing database variability in learning from medical data: an ensemble-based approach using convolutional neural networks and a case of study applied to automatic sleep scoring
• Pre-Training Graph Neural Networks for Generic Structural Feature Extraction
• Dynamic Manipulation of Flexible Objects with Torque Sequence Using a Deep Neural Network
• WebFace260M: A Benchmark Unveiling the Power of Million-Scale Deep Face Recognition
• Unsupervised Learning of Full-Waveform Inversion: Connecting CNN and Partial Differential Equation in a Loop
• Regularization Methods for Generative Adversarial Networks: An Overview of Recent Studies
• Concept Learning through Deep Reinforcement Learning with Memory-Augmented Neural Networks
• Crafting GBD-Net for Object Detection
• Robust and Energy-efficient PPG-based Heart-Rate Monitoring
• Source Data-absent Unsupervised Domain Adaptation through Hypothesis Transfer and Labeling Transfer
• Recovering Loss to Followup Information Using Denoising Autoencoders
• DeepSym: Deep Symbol Generation and Rule Learning from Unsupervised Continuous Robot Interaction for Planning
• Regular Polytope Networks
• Dirty Road Can Attack: Security of Deep Learning based Automated Lane Centering under Physical-World Attack
• Attention-guided Unified Network for Panoptic Segmentation
• Asteroid Flyby Cycler Trajectory Design Using Deep Neural Networks
• Learning to segment images with classification labels
• Adaptive Block Compressive Sensing: towards a real-time and low-complexity implementation
• Point Spread Function Modelling for Wide Field Small Aperture Telescopes with a Denoising Autoencoder
• CurlingNet: Compositional Learning between Images and Text for Fashion IQ Data
• Auxiliary-task Based Deep Reinforcement Learning for Participant Selection Problem in Mobile Crowdsourcing
• Temporal Pyramid Network for Action Recognition
• Optimal Physical Preprocessing for Example-Based Super-Resolution
• Deep Group-shuffling Random Walk for Person Re-identification
• Learned Threshold Pruning
• Longitudinal diffusion MRI analysis using Segis-Net: a single-step deep-learning framework for simultaneous segmentation and registration
• GNN-Geo: A Graph Neural Network-based Fine-grained IP geolocation Framework
• TAM: Temporal Adaptive Module for Video Recognition
• Comparing Normalization Methods for Limited Batch Size Segmentation Neural Networks
• Predictive Information Accelerates Learning in RL
• Information Plane Analysis of Deep Neural Networks via Matrix-Based Renyi's Entropy and Tensor Kernels
• X-volution: On the unification of convolution and self-attention
• Programming and Training Rate-Independent Chemical Reaction Networks
• Examining the Robustness of Spiking Neural Networks on Non-ideal Memristive Crossbars
• Transport Analysis of Infinitely Deep Neural Network
• MCTNet: A Multi-Scale CNN-Transformer Network for Change Detection in Optical Remote Sensing Images
• Efficient Certified Defenses Against Patch Attacks on Image Classifiers
• Improving Graph Neural Network Representations of Logical Formulae with Subgraph Pooling
• End-to-End Supermask Pruning: Learning to Prune Image Captioning Models
• Test-time Batch Statistics Calibration for Covariate Shift
• Distillation-based fabric anomaly detection
• Depth from Monocular Images using a Semi-Parallel Deep Neural Network (SPDNN) Hybrid Architecture
• An efficient solution for semantic segmentation: ShuffleNet V2 with atrous separable convolutions
• DUT-LFSaliency: Versatile Dataset and Light Field-to-RGB Saliency Detection
• Turbulence model reduction by deep learning
• Can AI be enabled to dynamical downscaling? A Latent Diffusion Model to mimic km-scale COSMO5.0\_CLM9 simulations
• Diverse Branch Block: Building a Convolution as an Inception-like Unit
• CIFAR10 to Compare Visual Recognition Performance between Deep Neural Networks and Humans
• AdderNet and its Minimalist Hardware Design for Energy-Efficient Artificial Intelligence
• Sharing Matters for Generalization in Deep Metric Learning
• PixelGame: Infrared small target segmentation as a Nash equilibrium
• Fine-Grained Visual Classification via Progressive Multi-Granularity Training of Jigsaw Patches
• Combining data assimilation and machine learning to estimate parameters of a convective-scale model
• Object Recognition, Dynamic Contact Simulation, Detection, and Control of the Flexible Musculoskeletal Hand Using a Recurrent Neural Network with Parametric Bias
• A hybrid quantum-classical conditional generative adversarial network algorithm for human-centered paradigm in cloud
• Systematic Generalization: What Is Required and Can It Be Learned?
• Inferring Astrophysics and Dark Matter Properties from 21cm Tomography using Deep Learning
• Voice-assisted Image Labelling for Endoscopic Ultrasound Classification using Neural Networks
• Beyond Classification: Latent User Interests Profiling from Visual Contents Analysis
• Fully-Convolutional Siamese Networks for Object Tracking
• Machine Learning on EPEX Order Books: Insights and Forecasts
• Convolutional-network models to predict wall-bounded turbulence from wall quantities
• Generalizable multi-task, multi-domain deep segmentation of sparse pediatric imaging datasets via multi-scale contrastive regularization and multi-joint anatomical priors
• Similarity-preserving Image-image Domain Adaptation for Person Re-identification
• Autonomous Power Allocation based on Distributed Deep Learning for Device-to-Device Communication Underlaying Cellular Network
• Image inpainting using frequency domain priors
• Deep Learning for Scene Classification: A Survey
• Numerical Calabi-Yau metrics from holomorphic networks
• Memory In Memory: A Predictive Neural Network for Learning Higher-Order Non-Stationarity from Spatiotemporal Dynamics
• Deep regularization and direct training of the inner layers of Neural Networks with Kernel Flows
• Attention-based Ensemble for Deep Metric Learning
• Multi-step Online Unsupervised Domain Adaptation
• Navigating by Touch: Haptic Monte Carlo Localization via Geometric Sensing and Terrain Classification
• BlendedMVS: A Large-scale Dataset for Generalized Multi-view Stereo Networks
• Attacking Binarized Neural Networks
• Cooking State Recognition from Images Using Inception Architecture
• Symmetric Uncertainty-Aware Feature Transmission for Depth Super-Resolution
• Brain MRI Tumor Segmentation with Adversarial Networks
• Subsampling Generative Adversarial Networks: Density Ratio Estimation in Feature Space with Softplus Loss
• Collaborative Video Object Segmentation by Foreground-Background Integration
• 0.8% Nyquist computational ghost imaging via non-experimental deep learning
• Time Matters in Regularizing Deep Networks: Weight Decay and Data Augmentation Affect Early Learning Dynamics, Matter Little Near Convergence
• Model Slicing for Supporting Complex Analytics with Elastic Inference Cost and Resource Constraints
• Transformer-Based Source-Free Domain Adaptation
• Automatic detection of microsleep episodes with deep learning
• BeamLearning: an end-to-end Deep Learning approach for the angular localization of sound sources using raw multichannel acoustic pressure data
• CODEBench: A Neural Architecture and Hardware Accelerator Co-Design Framework
• Rotor Localization and Phase Mapping of Cardiac Excitation Waves using Deep Neural Networks
• Automated Classification of Seizures against Nonseizures: A Deep Learning Approach
• BioNetExplorer: Architecture-Space Exploration of Bio-Signal Processing Deep Neural Networks for Wearables
• AutoEmb: Automated Embedding Dimensionality Search in Streaming Recommendations
• A Closer Look at Structured Pruning for Neural Network Compression
• Complex data labeling with deep learning methods: Lessons from fisheries acoustics
• DNN-Based Speech Presence Probability Estimation for Multi-Frame Single-Microphone Speech Enhancement
• Convolutional Neural Networks for cytoarchitectonic brain mapping at large scale
• Decimated Framelet System on Graphs and Fast G-Framelet Transforms
• ArtFlow: Unbiased Image Style Transfer via Reversible Neural Flows
• Characterizing signal propagation to close the performance gap in unnormalized ResNets
• LabelSens: Enabling Real-time Sensor Data Labelling at the point of Collection on Edge Computing
• Automated Assessment of Transthoracic Echocardiogram Image Quality Using Deep Neural Networks
• Rotate-and-Render: Unsupervised Photorealistic Face Rotation from Single-View Images
• Likelihood-free Inference with Mixture Density Network
• DPDnet: A Robust People Detector using Deep Learning with an Overhead Depth Camera
• Federated learning for secure development of AI models for Parkinson's disease detection using speech from different languages
• DeepStability: A Study of Unstable Numerical Methods and Their Solutions in Deep Learning
• ConvS2S-VC: Fully convolutional sequence-to-sequence voice conversion
• Band Attention Convolutional Networks For Hyperspectral Image Classification
• Global Self-Attention Networks for Image Recognition
• BYOL works even without batch statistics
• Deep Active Learning in Remote Sensing for data efficient Change Detection
• Resource-Efficient Neural Networks for Embedded Systems
• Geometric Approaches to Increase the Expressivity of Deep Neural Networks for MR Reconstruction
• Single Day Outdoor Photometric Stereo
• Automated Quality Control of Vacuum Insulated Glazing by Convolutional Neural Network Image Classification
• TG-GAN: Continuous-time Temporal Graph Generation with Deep Generative Models
• From Here to There: Video Inbetweening Using Direct 3D Convolutions
• Deep learning fluid flow reconstruction around arbitrary two-dimensional objects from sparse sensors using conformal mappings
• The Edge-on Galaxies in the Pan-STARRS survey (EGIPS)
• DeepOrigin: End-to-End Deep Learning for Detection of New Malware Families
• Sigsoftmax: Reanalysis of the Softmax Bottleneck
• Siamese Networks for Weakly Supervised Human Activity Recognition
• Facial Affect Estimation in the Wild Using Deep Residual and Convolutional Networks
• Expressive TTS Training with Frame and Style Reconstruction Loss
• Random Features for Kernel Approximation: A Survey on Algorithms, Theory, and Beyond
• The Evolution of Out-of-Distribution Robustness Throughout Fine-Tuning
• DeepFlash: Turning a Flash Selfie into a Studio Portrait
• Dual Student: Breaking the Limits of the Teacher in Semi-supervised Learning
• Quantifying the Preferential Direction of the Model Gradient in Adversarial Training With Projected Gradient Descent
• Optical information transfer through random unknown diffusers using electronic encoding and diffractive decoding
• Multimodal Anomaly Detection based on Deep Auto-Encoder for Object Slip Perception of Mobile Manipulation Robots
• Probabilistic Radiomics: Ambiguous Diagnosis with Controllable Shape Analysis
• Location-aware Adaptive Normalization: A Deep Learning Approach For Wildfire Danger Forecasting
• Neural Collapse Under MSE Loss: Proximity to and Dynamics on the Central Path
• Understanding Self-Training for Gradual Domain Adaptation
• Reinforcement Learning for Photonic Component Design
• Compressing deep quaternion neural networks with targeted regularization
• Towards Optimal Power Control via Ensembling Deep Neural Networks
• 1st Place Solution for Waymo Open Dataset Challenge -- 3D Detection and Domain Adaptation
• Robust and Efficient Fault Diagnosis of mm-Wave Active Phased Arrays using Baseband Signal
• A Large-Scale Study on Unsupervised Spatiotemporal Representation Learning
• Parrotron: An End-to-End Speech-to-Speech Conversion Model and its Applications to Hearing-Impaired Speech and Speech Separation
• Generalised gravitational burst generation with Generative Adversarial Networks
• Unsupervised Multivariate Time-Series Transformers for Seizure Identification on EEG
• ActSonic: Recognizing Everyday Activities from Inaudible Acoustic Wave Around the Body
• Dropout Q-Functions for Doubly Efficient Reinforcement Learning
• Weakly Supervised Change Detection Using Guided Anisotropic Difusion
• Galaxy shape measurement with convolutional neural networks
• Large-Scale Distributed Second-Order Optimization Using Kronecker-Factored Approximate Curvature for Deep Convolutional Neural Networks
• Hierarchical Deep Learning Architecture For 10K Objects Classification
• Hardware-Robust In-RRAM-Computing for Object Detection
• Guided Unsupervised Learning by Subaperture Decomposition for Ocean SAR Image Retrieval
• Understanding symmetries in deep networks
• End-to-End Learning of Geometric Deformations of Feature Maps for Virtual Try-On
• RAFT-Stereo: Multilevel Recurrent Field Transforms for Stereo Matching
• 1-Dimensional polynomial neural networks for audio signal related problems
• Multi-structure bone segmentation in pediatric MR images with combined regularization from shape priors and adversarial network
• Learning a Deep ConvNet for Multi-label Classification with Partial Labels
• Channel Normalization in Convolutional Neural Network avoids Vanishing Gradients
• Reduced-order modeling of unsteady fluid flow using neural network ensembles
• Heard More Than Heard: An Audio Steganography Method Based on GAN
• Disentangled High Quality Salient Object Detection
• Robotic Table Tennis: A Case Study into a High Speed Learning System
• Regional Homogeneity: Towards Learning Transferable Universal Adversarial Perturbations Against Defenses
• Extending GCC-PHAT using Shift Equivariant Neural Networks
• ResNet or DenseNet? Introducing Dense Shortcuts to ResNet
• Quantile QT-Opt for Risk-Aware Vision-Based Robotic Grasping
• Machine Learning Microscopic Form of Nematic Order in twisted double-bilayer graphene
• Learning to be a Statistician: Learned Estimator for Number of Distinct Values
• A Deep Learning Approach to Mapping Irrigation: IrrMapper-U-Net
• Learning and Recognizing Human Action from Skeleton Movement with Deep Residual Neural Networks
• Memory-efficient Embedding for Recommendations
• A Graph Theoretic Framework of Recomputation Algorithms for Memory-Efficient Backpropagation
• Deep reinforcement learning for smart calibration of radio telescopes
• On the Validity of Modeling SGD with Stochastic Differential Equations (SDEs)
• Cross-sectional Stock Price Prediction using Deep Learning for Actual Investment Management
• Visual Parser: Representing Part-whole Hierarchies with Transformers
• Edge Representation Learning with Hypergraphs
• Coherent Point Drift Networks: Unsupervised Learning of Non-Rigid Point Set Registration
• Learning from Positive and Unlabeled Data with Arbitrary Positive Shift
• FoodTracker: A Real-time Food Detection Mobile Application by Deep Convolutional Neural Networks
• A Little Energy Goes a Long Way: Build an Energy-Efficient, Accurate Spiking Neural Network from Convolutional Neural Network
• Short Quantum Circuits in Reinforcement Learning Policies for the Vehicle Routing Problem
• Differentially Private Federated Learning for Resource-Constrained Internet of Things
• Spectra of the Conjugate Kernel and Neural Tangent Kernel for linear-width neural networks
• Measuring and regularizing networks in function space
• Acoustic Scene Classification by Implicitly Identifying Distinct Sound Events
• Lookahead: A Far-Sighted Alternative of Magnitude-based Pruning
• Lipschitzness Is All You Need To Tame Off-policy Generative Adversarial Imitation Learning
• (ASNA) An Attention-based Siamese-Difference Neural Network with Surrogate Ranking Loss function for Perceptual Image Quality Assessment
• Solving Raven's Progressive Matrices with Neural Networks
• Transfer Learning of Artist Group Factors to Musical Genre Classification
• Invariant recognition drives neural representations of action sequences
• Deep learning piston aberration control of fiber laser phased array by spiral phase modulation
• An Improved Normed-Deformable Convolution for Crowd Counting
• On the distance between two neural networks and the stability of learning
• Revisiting Image-Language Networks for Open-ended Phrase Detection
• A General Method For Automatic Discovery of Powerful Interactions In Click-Through Rate Prediction
• ALGAN: Anomaly Detection by Generating Pseudo Anomalous Data via Latent Variables
• A Gradient Boosting Approach for Training Convolutional and Deep Neural Networks
• Variational Inference with NoFAS: Normalizing Flow with Adaptive Surrogate for Computationally Expensive Models
• Improving Graph Neural Networks with Simple Architecture Design
• Scalable Surface Reconstruction with Delaunay-Graph Neural Networks
• Training large-scale ANNs on simulated resistive crossbar arrays
• FrankenSplit: Efficient Neural Feature Compression with Shallow Variational Bottleneck Injection for Mobile Edge Computing
• Appliance Detection Using Very Low-Frequency Smart Meter Time Series
• An empirical comparison of deep-neural-network architectures for next activity prediction using context-enriched process event logs
• Cross-X Learning for Fine-Grained Visual Categorization
• Graph Generative Adversarial Networks for Sparse Data Generation in High Energy Physics
• MultiScene: A Large-scale Dataset and Benchmark for Multi-scene Recognition in Single Aerial Images
• Data augmentation and feature selection for automatic model recommendation in computational physics
• Determination of the Semion Code Threshold using Neural Decoders
• A Loss Function for Generative Neural Networks Based on Watson's Perceptual Model
• Global Planar Convolutions for improved context aggregation in Brain Tumor Segmentation
• Cross-Iteration Batch Normalization
• The Tree Ensemble Layer: Differentiability meets Conditional Computation
• PowerNorm: Rethinking Batch Normalization in Transformers
• Intriguing properties of adversarial training at scale
• Acute ischemic stroke lesion segmentation in non-contrast CT images using 3D convolutional neural networks
• MixNorm: Test-Time Adaptation Through Online Normalization Estimation
• Flat2Layout: Flat Representation for Estimating Layout of General Room Types
• Backprop with Approximate Activations for Memory-efficient Network Training
• Towards Cross-Granularity Few-Shot Learning: Coarse-to-Fine Pseudo-Labeling with Visual-Semantic Meta-Embedding
• One Model to Serve All: Star Topology Adaptive Recommender for Multi-Domain CTR Prediction
• Bayesian Inference for Large Scale Image Classification
• Iteratively Training Look-Up Tables for Network Quantization
• Hierarchical Discrete Distribution Decomposition for Match Density Estimation
• Sampling-Free Variational Inference of Bayesian Neural Networks by Variance Backpropagation
• Assessing the Generalization Gap of Learning-Based Speech Enhancement Systems in Noisy and Reverberant Environments
• Fast and Robust Femur Segmentation from Computed Tomography Images for Patient-Specific Hip Fracture Risk Screening
• Spherical Kernel for Efficient Graph Convolution on 3D Point Clouds
• Signal-Aware Direction-of-Arrival Estimation Using Attention Mechanisms
• Backpropagation-Friendly Eigendecomposition
• Deep Metric Learning with Spherical Embedding
• Pedestrian Attribute Recognition in Video Surveillance Scenarios Based on View-attribute Attention Localization
• A scalable saliency-based Feature selection method with instance level information
• Temporal Attentive Alignment for Large-Scale Video Domain Adaptation
• FreezeNet: Full Performance by Reduced Storage Costs
• Pruning Self-attentions into Convolutional Layers in Single Path
• A Review of Learning with Deep Generative Models from Perspective of Graphical Modeling
• Single-epoch supernova classification with deep convolutional neural networks
• Adversarial training in communication constrained federated learning
• Astroconformer: The Prospects of Analyzing Stellar Light Curves with Transformer-Based Deep Learning Models
• Multi-Task Attentive Residual Networks for Argument Mining
• A case for new neural network smoothness constraints
• Semi-Supervised Learning by Label Gradient Alignment
• Characterizing Evaporation Ducts Within the Marine Atmospheric Boundary Layer Using Artificial Neural Networks
• A Generative Adversarial Network for AI-Aided Chair Design
• Image Denoising using Attention-Residual Convolutional Neural Networks
• Frustratingly Easy Person Re-Identification: Generalizing Person Re-ID in Practice
• Have convolutions already made recurrence obsolete for unconstrained handwritten text recognition ?
• Query-guided End-to-End Person Search
• A Multi-cascaded Deep Model for Bilingual SMS Classification
• Multi-Scale Deep Learning for Estimating Horizontal Velocity Fields on the Solar Surface
• On Multitask Loss Function for Audio Event Detection and Localization
• Learned Optimizers for Analytic Continuation
• An Active Galactic Nucleus Recognition Model based on Deep Neural Network
• Imitation Learning with Additional Constraints on Motion Style using Parametric Bias
• Survival Function Matching for Calibrated Time-to-Event Predictions
• Learning to recognize touch gestures: recurrent vs. convolutional features and dynamic sampling
• Reynolds-Averaged Turbulence Modeling Using Type I and Type II Machine Learning Frameworks with Deep Learning
• Parallel Architecture and Hyperparameter Search via Successive Halving and Classification
• Global inducing point variational posteriors for Bayesian neural networks and deep Gaussian processes
• PFDet: 2nd Place Solution to Open Images Challenge 2018 Object Detection Track
• Learning Neural-Symbolic Descriptive Planning Models via Cube-Space Priors: The Voyage Home (to STRIPS)
• The new Herschel/PACS Point Source Catalogue
• The Six Fronts of the Generative Adversarial Networks
• Confidence-Aware Learning for Camouflaged Object Detection
• Transfer Learning Gaussian Anomaly Detection by Fine-tuning Representations
• Graph Warp Module: an Auxiliary Module for Boosting the Power of Graph Neural Networks in Molecular Graph Analysis
• A holistic approach to polyphonic music transcription with neural networks
• Path optimization for $U(1)$ gauge theory with complexified parameters
• Coupled Oscillatory Recurrent Neural Network (coRNN): An accurate and (gradient) stable architecture for learning long time dependencies
• An Evaluation of Action Recognition Models on EPIC-Kitchens
• Iris and periocular recognition in arabian race horses using deep convolutional neural networks
• BI-GCN: Boundary-Aware Input-Dependent Graph Convolution Network for Biomedical Image Segmentation
• Comicolorization: Semi-Automatic Manga Colorization
• Neural Sign Language Translation based on Human Keypoint Estimation
• Pop Music Highlighter: Marking the Emotion Keypoints
• End-to-End Deep Structured Models for Drawing Crosswalks
• Learning Neural Network Subspaces
• Super-resolving Herschel imaging: a proof of concept using Deep Neural Networks
• Spectrally Adapted Physics-Informed Neural Networks for Solving Unbounded Domain Problems
• Anomaly Detection in Multivariate Non-stationary Time Series for Automatic DBMS Diagnosis
• Image Generation From Small Datasets via Batch Statistics Adaptation
• Anchor Box Optimization for Object Detection
• MixPath: A Unified Approach for One-shot Neural Architecture Search
• Learning a Deep Embedding Model for Zero-Shot Learning
• Efficient Folded Attention for 3D Medical Image Reconstruction and Segmentation
• Manas: Mining Software Repositories to Assist AutoML
• Residual Network and Embedding Usage: New Tricks of Node Classification with Graph Convolutional Networks
• Recurrent Connections Aid Occluded Object Recognition by Discounting Occluders
• Audio Cover Song Identification using Convolutional Neural Network
• A Flexible Selection Scheme for Minimum-Effort Transfer Learning
• Training Algorithm Matters for the Performance of Neural Network Potential: A Case Study of Adam and the Kalman Filter Optimizers
• Guided Collaborative Training for Pixel-wise Semi-Supervised Learning
• SRGAN: Training Dataset Matters
• Dual-view Molecule Pre-training
• Arbitrary-Shaped Text Detection withAdaptive Text Region Representation
• OwlEyes-Online: A Fully Automated Platform for Detecting and Localizing UI Display Issues
• W2v-BERT: Combining Contrastive Learning and Masked Language Modeling for Self-Supervised Speech Pre-Training
• DAPnet: A Double Self-attention Convolutional Network for Point Cloud Semantic Labeling
• CATA++: A Collaborative Dual Attentive Autoencoder Method for Recommending Scientific Articles
• SuSketch: Surrogate Models of Gameplay as a Design Assistant
• Evidence Networks: simple losses for fast, amortized, neural Bayesian model comparison
• PRSeg: A Lightweight Patch Rotate MLP Decoder for Semantic Segmentation
• Real or Not Real, that is the Question
• A Hybrid Approach to Music Playlist Continuation Based on Playlist-Song Membership
• Normalized Flat Minima: Exploring Scale Invariant Definition of Flat Minima for Neural Networks using PAC-Bayesian Analysis
• Distributed Learning of Deep Neural Networks using Independent Subnet Training
• High-resolution Piano Transcription with Pedals by Regressing Onset and Offset Times
• SparseTrain:Leveraging Dynamic Sparsity in Training DNNs on General-Purpose SIMD Processors
• Unsupervised Visual Odometry and Action Integration for PointGoal Navigation in Indoor Environment
• Rethinking Channel Dimensions for Efficient Model Design
• Learning to Generalize Unseen Domains via Memory-based Multi-Source Meta-Learning for Person Re-Identification
• BatchQuant: Quantized-for-all Architecture Search with Robust Quantizer
• CANU-ReID: A Conditional Adversarial Network for Unsupervised person Re-IDentification
• Hate-Alert@DravidianLangTech-EACL2021: Ensembling strategies for Transformer-based Offensive language Detection
• The Effect of Silence Feature in Dimensional Speech Emotion Recognition
• Which Algorithmic Choices Matter at Which Batch Sizes? Insights From a Noisy Quadratic Model
• Objects are Different: Flexible Monocular 3D Object Detection
• Learning to Generate with Memory
• Multimodal Urban Sound Tagging with Spatiotemporal Context
• Eigenvalue distribution of nonlinear models of random matrices
• Partial transfusion: on the expressive influence of trainable batch norm parameters for transfer learning
• SimNet: Enabling Robust Unknown Object Manipulation from Pure Synthetic Data via Stereo
• Understanding Negative Samples in Instance Discriminative Self-supervised Representation Learning
• Perceptual Generative Autoencoders
• Low-latency Monaural Speech Enhancement with Deep Filter-bank Equalizer
• PixelVAE++: Improved PixelVAE with Discrete Prior
• TELESTO: A Graph Neural Network Model for Anomaly Classification in Cloud Services
• Dynamic Refinement Network for Oriented and Densely Packed Object Detection
• DRD-Net: Detail-recovery Image Deraining via Context Aggregation Networks
• Enabling Large Batch Size Training for DNN Models Beyond the Memory Limit While Maintaining Performance
• Deep Residual Network for Sound Source Localization in the Time Domain
• Improving Pedestrian Attribute Recognition With Weakly-Supervised Multi-Scale Attribute-Specific Localization
• Action Shuffling for Weakly Supervised Temporal Localization
• Centripetal SGD for Pruning Very Deep Convolutional Networks with Complicated Structure
• What can linearized neural networks actually say about generalization?
• Graph Stacked Hourglass Networks for 3D Human Pose Estimation
• Attention Convolutional Binary Neural Tree for Fine-Grained Visual Categorization
• EEG-based Texture Roughness Classification in Active Tactile Exploration with Invariant Representation Learning Networks
• You Only Look Yourself: Unsupervised and Untrained Single Image Dehazing Neural Network
• Deep Network Uncertainty Maps for Indoor Navigation
• MirBot: A collaborative object recognition system for smartphones using convolutional neural networks
• Optimal Solving of Constrained Path-Planning Problems with Graph Convolutional Networks and Optimized Tree Search
• Hyperparameter-Free Out-of-Distribution Detection Using Softmax of Scaled Cosine Similarity
• Improved Adversarial Robustness by Reducing Open Space Risk via Tent Activations
• Look at What I'm Doing: Self-Supervised Spatial Grounding of Narrations in Instructional Videos
• Deep Learning for Classifying and Characterizing Atmospheric Ducting within the Maritime Setting
• Deep learning for Gaussian process tomography model selection using the ASDEX Upgrade SXR system
• 3D Sketch-aware Semantic Scene Completion via Semi-supervised Structure Prior
• Radiologist-level stroke classification on non-contrast CT scans with Deep U-Net
• Transformation-based Adversarial Video Prediction on Large-Scale Data
• An unsupervised deep learning approach in solving partial integro-differential equations
• Rethinking Assumptions in Deep Anomaly Detection
• A White Paper on Neural Network Quantization
• On the Ineffectiveness of Variance Reduced Optimization for Deep Learning
• DARNet: Deep Active Ray Network for Building Segmentation
• Switchable Whitening for Deep Representation Learning
• Physics-Informed Holomorphic Neural Networks (PIHNNs): Solving Linear Elasticity Problems
• Online Adaptation through Meta-Learning for Stereo Depth Estimation
• Factor Graph Attention
• Multi-Modal Hybrid Deep Neural Network for Speech Enhancement
• An initial attempt of combining visual selective attention with deep reinforcement learning
• Ranking Candidate Signals with Machine Learning in Low-Latency Search for Gravitational-Waves from Compact Binary Mergers
• Neural Likelihoods via Cumulative Distribution Functions
• Generalizing MLPs With Dropouts, Batch Normalization, and Skip Connections
• DARTS-ASR: Differentiable Architecture Search for Multilingual Speech Recognition and Adaptation
• Towards Robust ResNet: A Small Step but A Giant Leap
• Machine Learning Algorithms for Classification of Microcirculation Images from Septic and Non-Septic Patients
• Subaru Hyper Suprime-Cam revisits the large-scale environmental dependence on galaxy morphology over 360 deg${}^2$ at z=0.3-0.6
• One Loss for All: Deep Hashing with a Single Cosine Similarity based Learning Objective
• Predicting the wall-shear stress and wall pressure through convolutional neural networks
• Search for Better Students to Learn Distilled Knowledge
• Multiresolution Graph Transformers and Wavelet Positional Encoding for Learning Hierarchical Structures
• A Coarse-to-Fine Adaptive Network for Appearance-Based Gaze Estimation
• Feature Selection Based on Sparse Neural Network Layer with Normalizing Constraints
• BlockSwap: Fisher-guided Block Substitution for Network Compression on a Budget
• A CNN Approach for 5G mmWave Positioning Using Beamformed CSI Measurements
• Towards Understanding the Transferability of Deep Representations
• Probing Convolutional Neural Networks for Event Reconstruction in γ-Ray Astronomy with Cherenkov Telescopes
• Acoustic Structure Inverse Design and Optimization Using Deep Learning
• Loss Patterns of Neural Networks
• End-2-End COVID-19 Detection from Breath & Cough Audio
• SSFG: Stochastically Scaling Features and Gradients for Regularizing Graph Convolutional Networks
• Parameterized Hypercomplex Graph Neural Networks for Graph Classification
• Frank-Wolfe Network: An Interpretable Deep Structure for Non-Sparse Coding
• Tubule segmentation of fluorescence microscopy images based on convolutional neural networks with inhomogeneity correction
• The Phonetic Footprint of Parkinson's Disease
• Equivariant Subgraph Aggregation Networks
• Geographic ratemaking with spatial embeddings
• Infrared Image Super-Resolution via Heterogeneous Convolutional WGAN
• Multiple Domain Experts Collaborative Learning: Multi-Source Domain Generalization For Person Re-Identification
• LocalDrop: A Hybrid Regularization for Deep Neural Networks
• Medical Image Generation using Generative Adversarial Networks
• Deep Learning of Transferable MIMO Channel Modes for 6G V2X Communications
• Residual Tensor Train: A Quantum-inspired Approach for Learning Multiple Multilinear Correlations
• Appearance-Preserving 3D Convolution for Video-based Person Re-identification
• Topological Planning with Transformers for Vision-and-Language Navigation
• Learning Graph Normalization for Graph Neural Networks
• Feature Pyramid Grids
• ThreshNet: An Efficient DenseNet Using Threshold Mechanism to Reduce Connections
• Iterative, Deep Synthetic Aperture Sonar Image Segmentation
• Fixed-MAML for Few Shot Classification in Multilingual Speech Emotion Recognition
• Recurrence along Depth: Deep Convolutional Neural Networks with Recurrent Layer Aggregation
• Optimization of Quantum-dot Qubit Fabrication via Machine Learning
• MM-ALT: A Multimodal Automatic Lyric Transcription System
• Comparing Hysteresis Comparator and RMS Threshold Methods for Automatic Single Cough Segmentations
• Visual Transformers for Primates Classification and Covid Detection
• Artificial Intelligence Assisted Inversion (AIAI) of Synthetic Type Ia Supernova Spectra
• Keep It Simple: CNN Model Complexity Studies for Interference Classification Tasks
• Capsule networks with non-iterative cluster routing
• Pose Estimation and 3D Reconstruction of Vehicles from Stereo-Images Using a Subcategory-Aware Shape Prior
• Dissecting Hessian: Understanding Common Structure of Hessian in Neural Networks
• A Theoretical Analysis of the Number of Shots in Few-Shot Learning
• CardiSort: a convolutional neural network for cross vendor automated sorting of cardiac MR images
• Searching for Efficient Multi-Stage Vision Transformers
• On the locality of local neural operator in learning fluid dynamics
• Convolutional Channel-wise Competitive Learning for the Forward-Forward Algorithm
• CNN-based event classification for alpha-decay events in nuclear emulsion
• Spatio-Temporal Fusion Networks for Action Recognition
• P-CRITICAL: A Reservoir Autoregulation Plasticity Rule for Neuromorphic Hardware
• MART: Memory-Augmented Recurrent Transformer for Coherent Video Paragraph Captioning
• Predicting Shot Making in Basketball Learnt from Adversarial Multiagent Trajectories
• NILMFormer: Non-Intrusive Load Monitoring that Accounts for Non-Stationarity
• Convergence of Deep Fictitious Play for Stochastic Differential Games
• Deep Learning for Face Anti-Spoofing: A Survey
• Iterative Normalization: Beyond Standardization towards Efficient Whitening
• Decorrelated Adversarial Learning for Age-Invariant Face Recognition
• Spectrum Correction: Acoustic Scene Classification with Mismatched Recording Devices
• 3D Shape Synthesis for Conceptual Design and Optimization Using Variational Autoencoders
• Hierarchical Contrastive Motion Learning for Video Action Recognition
• Heavily Augmented Sound Event Detection utilizing Weak Predictions
• Highly Efficient Salient Object Detection with 100K Parameters
• A Simple Probabilistic Method for Deep Classification under Input-Dependent Label Noise
• Spectral Normalisation for Deep Reinforcement Learning: an Optimisation Perspective
• A Comprehensive Overhaul of Feature Distillation
• EllSeg-Gen, towards Domain Generalization for head-mounted eyetracking
• Bounded Residual Gradient Networks (BReG-Net) for Facial Affect Computing
• Naive-Student: Leveraging Semi-Supervised Learning in Video Sequences for Urban Scene Segmentation
• Rethinking Importance Weighting for Deep Learning under Distribution Shift
• LightTrack: Finding Lightweight Neural Networks for Object Tracking via One-Shot Architecture Search
• Convolutional Auto-encoding of Sentence Topics for Image Paragraph Generation
• COVID-19 Diagnosis from Cough Acoustics using ConvNets and Data Augmentation
• On the impact of selected modern deep-learning techniques to the performance and celerity of classification models in an experimental high-energy physics use case
• Deep Neural Networks for Detecting Statistical Model Misspecifications. The Case of Measurement Invariance
• Boundary-preserving Mask R-CNN
• ChildPredictor: A Child Face Prediction Framework with Disentangled Learning
• FxP-QNet: A Post-Training Quantizer for the Design of Mixed Low-Precision DNNs with Dynamic Fixed-Point Representation
• Deep Transfer Learning for Classification of Variable Sources
• Evaluating Generalization Ability of Convolutional Neural Networks and Capsule Networks for Image Classification via Top-2 Classification
• Densely connected normalizing flows
• Examining the Role and Limits of Batchnorm Optimization to Mitigate Diverse Hardware-noise in In-memory Computing
• Electromyography Signal Classification Using Deep Learning
• The redshift evolution of the S0 fraction for $z<1$ in COSMOS
• Tackling Catastrophic Forgetting and Background Shift in Continual Semantic Segmentation
• MOBIUS: Model-Oblivious Binarized Neural Networks
• Deep Learning for Reduced Order Modelling and Efficient Temporal Evolution of Fluid Simulations
• DenseAttentionSeg: Segment Hands from Interacted Objects Using Depth Input
• Generate, Segment and Refine: Towards Generic Manipulation Segmentation
• Symmetry-invariant optimization in deep networks
• A possible late-time transition of $M_B$ inferred via neural networks
• SE(3)-Equivariant and Noise-Invariant 3D Rigid Motion Tracking in Brain MRI
• Automotive Object Detection via Learning Sparse Events by Spiking Neurons
• The Training Process of Many Deep Networks Explores the Same Low-Dimensional Manifold
• Text-only domain adaptation for end-to-end ASR using integrated text-to-mel-spectrogram generator
• Uniformly convex neural networks and non-stationary iterated network Tikhonov (iNETT) method
• Softmax-free Linear Transformers
• PAMS: Quantized Super-Resolution via Parameterized Max Scale
• Integrating Lattice-Free MMI into End-to-End Speech Recognition
• Learning Instance Occlusion for Panoptic Segmentation
• MDN-VO: Estimating Visual Odometry with Confidence
• Generative Convolution Layer for Image Generation
• Deep Co-Space: Sample Mining Across Feature Transformation for Semi-Supervised Learning
• GP: Context-free Grammar Pre-training for Text-to-SQL Parsers
• Learning-to-Ask: Knowledge Acquisition via 20 Questions
• CoVA: Context-aware Visual Attention for Webpage Information Extraction
• Learning Optimal Conformal Classifiers
• Unsupervised learning for concept detection in medical images: a comparative analysis
• Abstractive Text Classification Using Sequence-to-convolution Neural Networks
• An Information Theory-inspired Strategy for Automatic Network Pruning
• Deep learning of deformation-dependent conductance in thin films: nanobubbles in graphene
• Long Short-Term Transformer for Online Action Detection
• An Oracle for Guiding Large-Scale Model/Hybrid Parallel Training of Convolutional Neural Networks
• Training-Time-Friendly Network for Real-Time Object Detection
• Should You Go Deeper? Optimizing Convolutional Neural Network Architectures without Training by Receptive Field Analysis
• In Conclusion Not Repetition: Comprehensive Abstractive Summarization With Diversified Attention Based On Determinantal Point Processes
• Does Knowledge Distillation Really Work?
• Scaling-Translation-Equivariant Networks with Decomposed Convolutional Filters
• Semantic Correlation Promoted Shape-Variant Context for Segmentation
• Normalized Attention Without Probability Cage
• Flow-based Spatio-Temporal Structured Prediction of Motion Dynamics
• The Low-Rank Simplicity Bias in Deep Networks
• RadarNet: Exploiting Radar for Robust Perception of Dynamic Objects
• Relational Data Synthesis using Generative Adversarial Networks: A Design Space Exploration
• Multi-Task Learning by Deep Collaboration and Application in Facial Landmark Detection
• FlowSeq: Non-Autoregressive Conditional Sequence Generation with Generative Flow
• Over Parameterized Two-level Neural Networks Can Learn Near Optimal Feature Representations
• Rank-One Network: An Effective Framework for Image Restoration
• Neural Network Pruning with Residual-Connections and Limited-Data
• Vector representations of text data in deep learning
• Deep Optimization model for Screen Content Image Quality Assessment using Neural Networks
• Magnetic Resonance Fingerprinting Reconstruction Using Recurrent Neural Networks
• Interpretation of Brain Morphology in Association to Alzheimer's Disease Dementia Classification Using Graph Convolutional Networks on Triangulated Meshes
• Continuous Speech Separation with Conformer
• Improving Deep Neural Network with Multiple Parametric Exponential Linear Units
• Automatic Emotion Recognition (AER) System based on Two-Level Ensemble of Lightweight Deep CNN Models
• CEB Improves Model Robustness
• Reinforcement Learning Under Moral Uncertainty
• Extended Batch Normalization
• Memory-Based Graph Networks
• SBSGAN: Suppression of Inter-Domain Background Shift for Person Re-Identification
• Blind SAR Image Despeckling Using Self-Supervised Dense Dilated Convolutional Neural Network
• Bringing Cartoons to Life: Towards Improved Cartoon Face Detection and Recognition Systems
• A Critique of Self-Expressive Deep Subspace Clustering
• Exploring Self-Supervised Regularization for Supervised and Semi-Supervised Learning
• OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledge
• Mirror Descent View for Neural Network Quantization
• VSA: Reconfigurable Vectorwise Spiking Neural Network Accelerator
• Training Larger Networks for Deep Reinforcement Learning
• The CORSMAL benchmark for the prediction of the properties of containers
• A Deep Generative Model for Reordering Adjacency Matrices
• Temporal Sequence Distillation: Towards Few-Frame Action Recognition in Videos
• Second-order step-size tuning of SGD for non-convex optimization
• Sex Trafficking Detection with Ordinal Regression Neural Networks
• Coupling the reduced-order model and the generative model for an importance sampling estimator
• Robust Processing-In-Memory Neural Networks via Noise-Aware Normalization
• Being Bayesian about Categorical Probability
• Adaptive Denoising via GainTuning
• Convolutional Recurrent Neural Network Based Progressive Learning for Monaural Speech Enhancement
• Convolutional Neural Network-based Intrusion Detection System for AVTP Streams in Automotive Ethernet-based Networks
• Deep Fictitious Play for Stochastic Differential Games
• Explicitly Conditioned Melody Generation: A Case Study with Interdependent RNNs
• Graph Neural Networks for Topological Feature Extraction in ECG Classification
• TAME: Attention Mechanism Based Feature Fusion for Generating Explanation Maps of Convolutional Neural Networks
• Certification of Gaussian Boson Sampling via graph theory
• An Adaptive X-vector Model for Text-independent Speaker Verification
• An encoder-decoder-based method for COVID-19 lung infection segmentation
• Unconstrained Scene Text and Video Text Recognition for Arabic Script
• ACNe: Attentive Context Normalization for Robust Permutation-Equivariant Learning
• Key Protected Classification for Collaborative Learning
• Blind Predicting Similar Quality Map for Image Quality Assessment
• Deep Face Recognition Model Compression via Knowledge Transfer and Distillation
• Deep Template Matching for Pedestrian Attribute Recognition with the Auxiliary Supervision of Attribute-wise Keypoints
• Hard-Attention for Scalable Image Classification
• Reconciling Modern Deep Learning with Traditional Optimization Analyses: The Intrinsic Learning Rate
• Deep learning based numerical approximation algorithms for stochastic partial differential equations
• Signal Combination for Language Identification
• Unsupervised Deep Learning-based clustering for Human Activity Recognition
• CO2: Consistent Contrast for Unsupervised Visual Representation Learning
• Deep learning algorithms for solving high dimensional nonlinear backward stochastic differential equations
• GradInit: Learning to Initialize Neural Networks for Stable and Efficient Training
• Weak-lensing Mass Reconstruction of Galaxy Clusters with Convolutional Neural Network
• Toward Automatic Threat Recognition for Airport X-ray Baggage Screening with Deep Convolutional Object Detection
• Structured Convolution Matrices for Energy-efficient Deep learning
• Adaptively Connected Neural Networks
• Unsupervised Anomaly Detection for X-Ray Images
• DeepWarp: Photorealistic Image Resynthesis for Gaze Manipulation
• A Comprehensive Review of Deep Learning-based Single Image Super-resolution
• Generating Electronic Health Records with Multiple Data Types and Constraints
• Dense Uncertainty Estimation
• TransLoc3D : Point Cloud based Large-scale Place Recognition using Adaptive Receptive Fields
• Event reconstruction of Compton telescopes using a multi-task neural network
• Efficient Deep Neural Networks
• Towards robust vision by multi-task learning on monkey visual cortex
• BayesFT: Bayesian Optimization for Fault Tolerant Neural Network Architecture
• Deep learning reconstruction of three-dimensional galaxy distributions with intensity mapping observations
• Keep and Learn: Continual Learning by Constraining the Latent Space for Knowledge Preservation in Neural Networks
• Spin-Weighted Spherical CNNs
• LGGNet: Learning from Local-Global-Graph Representations for Brain-Computer Interface
• Responsible AI: Gender bias assessment in emotion recognition
• DMC-Net: Generating Discriminative Motion Cues for Fast Compressed Video Action Recognition
• Joint Deep Cross-Domain Transfer Learning for Emotion Recognition
• Learning Individual Speaking Styles for Accurate Lip to Speech Synthesis
• Automatic speech recognition for the Nepali language using CNN, bidirectional LSTM and ResNet
• Learning Tree Structures from Leaves For Particle Decay Reconstruction
• Compression based bound for non-compressed network: unified generalization error analysis of large compressible deep neural network
• DeepLight: Robust & Unobtrusive Real-time Screen-Camera Communication for Real-World Displays
• Batch Group Normalization
• GraphTSNE: A Visualization Technique for Graph-Structured Data
• Convolutional Networks with Dense Connectivity
• An Empirical Study on Hyperparameters and their Interdependence for RL Generalization
• ChartPointFlow for Topology-Aware 3D Point Cloud Generation
• Facial Expression Video Generation Based-On Spatio-temporal Convolutional GAN: FEV-GAN
• FASTER Recurrent Networks for Efficient Video Classification
• SatImNet: Structured and Harmonised Training Data for Enhanced Satellite Imagery Classification
• Parallel Training of Deep Networks with Local Updates
• Large-Scale Classification of Structured Objects using a CRF with Deep Class Embedding
• Learning Manipulation States and Actions for Efficient Non-prehensile Rearrangement Planning
• Material Property Prediction using Graphs based on Generically Complete Isometry Invariants
• End-to-end depth from motion with stabilized monocular videos
• A Contrastive Learning Approach for Training Variational Autoencoder Priors
• The Impact of Background Removal on Performance of Neural Networks for Fashion Image Classification and Segmentation
• Per-Tensor Fixed-Point Quantization of the Back-Propagation Algorithm
• Selective Distillation of Weakly Annotated GTD for Vision-based Slab Identification System
• A Time Attention based Fraud Transaction Detection Framework
• The Deep Arbitrary Polynomial Chaos Neural Network or how Deep Artificial Neural Networks could benefit from Data-Driven Homogeneous Chaos Theory
• Hierarchical Pooling Structure for Weakly Labeled Sound Event Detection
• AI Illustrator: Translating Raw Descriptions into Images by Prompt-based Cross-Modal Generation
• ST3D: Self-training for Unsupervised Domain Adaptation on 3D Object Detection
• Tractable Regularization of Probabilistic Circuits
• CSTNet: Contrastive Speech Translation Network for Self-Supervised Speech Representation Learning
• Batch Normalization Orthogonalizes Representations in Deep Random Networks
• CatNet: music source separation system with mix-audio augmentation
• Scene Transformer: A unified architecture for predicting multiple agent trajectories
• GRAPPA-GANs for Parallel MRI Reconstruction
• Graph Neural Network Guided Local Search for the Traveling Salesperson Problem
• SIRe-Networks: Convolutional Neural Networks Architectural Extension for Information Preservation via Skip/Residual Connections and Interlaced Auto-Encoders
• Multi-Mapping Image-to-Image Translation with Central Biasing Normalization
• Cold Brew: Distilling Graph Node Representations with Incomplete or Missing Neighborhoods
• Learning from Temporal Gradient for Semi-supervised Action Recognition
• Pipelined Backpropagation at Scale: Training Large Models without Batches
• Automated skin lesion segmentation using multi-scale feature extraction scheme and dual-attention mechanism
• MonoRUn: Monocular 3D Object Detection by Reconstruction and Uncertainty Propagation
• Extracting Variable-Depth Logical Document Hierarchy from Long Documents: Method, Evaluation, and Application
• An Investigation of Few-Shot Learning in Spoken Term Classification
• Signal Transformer: Complex-valued Attention and Meta-Learning for Signal Recognition
• Video Super-resolution with Temporal Group Attention
• The Case for Strong Scaling in Deep Learning: Training Large 3D CNNs with Hybrid Parallelism
• Learning to Blindly Assess Image Quality in the Laboratory and Wild
• Distilling Self-Knowledge From Contrastive Links to Classify Graph Nodes Without Passing Messages
• A Generalized Zero-Shot Quantization of Deep Convolutional Neural Networks via Learned Weights Statistics
• Demystifying Batch Normalization in ReLU Networks: Equivalent Convex Optimization Models and Implicit Regularization
• Automatic Defect Detection in Sewer Network Using Deep Learning Based Object Detector
• Predicting brain-age from raw T 1 -weighted Magnetic Resonance Imaging data using 3D Convolutional Neural Networks
• CT organ segmentation using GPU data augmentation, unsupervised labels and IOU loss
• Riemannian Normalizing Flow on Variational Wasserstein Autoencoder for Text Modeling
• Improving Transferability of Representations via Augmentation-Aware Self-Supervision
• Growing Efficient Deep Networks by Structured Continuous Sparsification
• An astronomical image content-based recommendation system using combined deep learning models in a fully unsupervised mode
• Invertible Generative Modeling using Linear Rational Splines
• NTIRE 2020 Challenge on Perceptual Extreme Super-Resolution: Methods and Results
• Mutual exclusivity as a challenge for deep neural networks
• Task-specific Self-body Controller Acquisition by Musculoskeletal Humanoids: Application to Pedal Control in Autonomous Driving
• Partial Order Pruning: for Best Speed/Accuracy Trade-off in Neural Architecture Search
• Deep learning for time series classification
• STEP: Segmenting and Tracking Every Pixel
• Finding and Visualizing Weaknesses of Deep Reinforcement Learning Agents
• Amplitude Spectrum Transformation for Open Compound Domain Adaptive Semantic Segmentation
• Depthwise Multiception Convolution for Reducing Network Parameters without Sacrificing Accuracy
• PrivPAS: A real time Privacy-Preserving AI System and applied ethics
• A Comprehensive Comparison of Multi-Dimensional Image Denoising Methods
• Split Batch Normalization: Improving Semi-Supervised Learning under Domain Shift
• Interpretable agent communication from scratch (with a generic visual processor emerging on the side)
• How Framelets Enhance Graph Neural Networks
• The Local Elasticity of Neural Networks
• Accelerating Deep Unsupervised Domain Adaptation with Transfer Channel Pruning
• Effective Abstract Reasoning with Dual-Contrast Network
• Unleashing the Potential of Pre-Trained Diffusion Models for Generalizable Person Re-Identification
• Multi-Camera Sensor Fusion for Visual Odometry using Deep Uncertainty Estimation
• FBDNN: Filter Banks and Deep Neural Networks for Portable and Fast Brain-Computer Interfaces
• Adversarially Adaptive Normalization for Single Domain Generalization
• Deep Tactile Experience: Estimating Tactile Sensor Output from Depth Sensor Data
• End-to-end Kernel Learning via Generative Random Fourier Features
• Unification of Symmetries Inside Neural Networks: Transformer, Feedforward and Neural ODE
• Byte-based Language Identification with Deep Convolutional Networks
• Needles in Haystacks: On Classifying Tiny Objects in Large Images
• Collaborative Video Object Segmentation by Multi-Scale Foreground-Background Integration
• FSNet: Compression of Deep Convolutional Neural Networks by Filter Summary
• Graph-Based Object Classification for Neuromorphic Vision Sensing
• Benchmarking the Robustness of Instance Segmentation Models
• Regularizing by the Variance of the Activations' Sample-Variances
• ExSinGAN: Learning an Explainable Generative Model from a Single Image
• Knowledge as Priors: Cross-Modal Knowledge Generalization for Datasets without Superior Knowledge
• Making EfficientNet More Efficient: Exploring Batch-Independent Normalization, Group Convolutions and Reduced Resolution Training
• Learning to Discriminate Information for Online Action Detection: Analysis and Application
• Interpretable and Accurate Fine-grained Recognition via Region Grouping
• Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair Selection
• Prune and Replace NAS
• Learning Deep Gradient Descent Optimization for Image Deconvolution
• Hyper-Parameter Sweep on AlphaZero General
• Foreground Removal of CO Intensity Mapping Using Deep Learning
• Residual-Concatenate Neural Network with Deep Regularization Layers for Binary Classification
• Intra- and Inter-Action Understanding via Temporal Action Parsing
• I Am Going MAD: Maximum Discrepancy Competition for Comparing Classifiers Adaptively
• Rethinking Normalization and Elimination Singularity in Neural Networks
• Efficient Deep Spiking Multi-Layer Perceptrons with Multiplication-Free Inference
• Differentiable Earth Mover's Distance for Data Compression at the High-Luminosity LHC
• Proxy Anchor Loss for Deep Metric Learning
• Recognizing Handwritten Mathematical Expressions as LaTex Sequences Using a Multiscale Robust Neural Network
• Universal Stagewise Learning for Non-Convex Problems with Convergence on Averaged Solutions
• Hierarchical VAEs Know What They Don't Know
• Audio-based automatic mating success prediction of giant pandas
• Orthogonal Deep Neural Networks
• Elastic Significant Bit Quantization and Acceleration for Deep Neural Networks
• Hierarchical Classification of Pulmonary Lesions: A Large-Scale Radio-Pathomics Study
• Contrastive Representation Learning for Whole Brain Cytoarchitectonic Mapping in Histological Human Brain Sections
• Exponential Moving Average Normalization for Self-supervised and Semi-supervised Learning
• Improving Transferability of Domain Adaptation Networks Through Domain Alignment Layers
• Adversarial Loss for Semantic Segmentation of Aerial Imagery
• Regularizing activations in neural networks via distribution matching with the Wasserstein metric
• Training GANs with Stronger Augmentations via Contrastive Discriminator
• Semantic Labeling of Large-Area Geographic Regions Using Multi-View and Multi-Date Satellite Images and Noisy OSM Training Labels
• The Impact of Global Structural Information in Graph Neural Networks Applications
• Boosting Binary Masks for Multi-Domain Learning through Affine Transformations
• Fighting Gradients with Gradients: Dynamic Defenses against Adversarial Attacks
• Inductive Bias of Gradient Descent based Adversarial Training on Separable Data
• MediumVC: Any-to-any voice conversion using synthetic specific-speaker speeches as intermedium features
• End-to-End Spectro-Temporal Graph Attention Networks for Speaker Verification Anti-Spoofing and Speech Deepfake Detection
• The Normalization Method for Alleviating Pathological Sharpness in Wide Neural Networks
• Dependency-aware Attention Control for Unconstrained Face Recognition with Image Sets
• An Efficient Approach to Informative Feature Extraction from Multimodal Data
• SSN: Learning Sparse Switchable Normalization via SparsestMax
• Broadcasted Residual Learning for Efficient Keyword Spotting
• Face Completion with Semantic Knowledge and Collaborative Adversarial Learning
• Adversarial Motion Modelling helps Semi-supervised Hand Pose Estimation
• Automating Vehicles by Deep Reinforcement Learning using Task Separation with Hill Climbing
• Causal-BALD: Deep Bayesian Active Learning of Outcomes to Infer Treatment-Effects from Observational Data
• Classification with Rejection Based on Cost-sensitive Classification
• A Softmax-free Loss Function Based on Predefined Optimal-distribution of Latent Features for Deep Learning Classifier
• AlignSeg: Feature-Aligned Segmentation Networks
• Spatio-Temporal Joint Graph Convolutional Networks for Traffic Forecasting
• Fine-Grained Image Captioning with Global-Local Discriminative Objective
• Network Quantization with Element-wise Gradient Scaling
• Benanza: Automatic $\mu$Benchmark Generation to Compute "Lower-bound" Latency and Inform Optimizations of Deep Learning Models on GPUs
• A law of robustness for two-layers neural networks
• Modeling Uncertainty by Learning a Hierarchy of Deep Neural Connections
• Improving Dual-Microphone Speech Enhancement by Learning Cross-Channel Features with Multi-Head Attention
• Anatomy and Physiology of Artificial Intelligence in PET Imaging
• Towards High Performance Human Keypoint Detection
• Drop-Bottleneck: Learning Discrete Compressed Representation for Noise-Robust Exploration
• PlayVirtual: Augmenting Cycle-Consistent Virtual Trajectories for Reinforcement Learning
• Deep Learning with CNNs: A Compact Holistic Tutorial with Focus on Supervised Regression (Preprint)
• Fix Your Features: Stationary and Maximally Discriminative Embeddings using Regular Polytope (Fixed Classifier) Networks
• MathNet: Haar-Like Wavelet Multiresolution-Analysis for Graph Representation and Learning
• Bit Error Robustness for Energy-Efficient DNN Accelerators
• ePointDA: An End-to-End Simulation-to-Real Domain Adaptation Framework for LiDAR Point Cloud Segmentation
• Deep 3D Convolutional Neural Network for Automated Lung Cancer Diagnosis
• Neural Processes Mixed-Effect Models for Deep Normative Modeling of Clinical Neuroimaging Data
• Computational Performance of Deep Reinforcement Learning to find Nash Equilibria
• From Synthetic to Real: Unsupervised Domain Adaptation for Animal Pose Estimation
• Spherical View Synthesis for Self-Supervised 360 Depth Estimation
• A Novel Framework for Neural Architecture Search in the Hill Climbing Domain
• Direct Prediction of Steady-State Flow Fields in Meshed Domain with Graph Networks
• Learning from Adversarial Features for Few-Shot Classification
• Derivative Manipulation for General Example Weighting
• In the Eye of the Beholder: Gaze and Actions in First Person Video
• Revisiting "Qualitatively Characterizing Neural Network Optimization Problems"
• OMPQ: Orthogonal Mixed Precision Quantization
• Distillation Guided Residual Learning for Binary Convolutional Neural Networks
• Proxy-Normalizing Activations to Match Batch Normalization while Removing Batch Dependence
• Gated Channel Transformation for Visual Recognition
• The EPIC-KITCHENS Dataset: Collection, Challenges and Baselines
• Batch Normalization Preconditioning for Neural Network Training
• Unsupervised Object-Level Representation Learning from Scene Images
• Research on Mosaic Image Data Enhancement for Overlapping Ship Targets
• Training Feedback Spiking Neural Networks by Implicit Differentiation on the Equilibrium State
• Data Stream Stabilization for Optical Coherence Tomography Volumetric Scanning
• Controllable Person Image Synthesis with Spatially-Adaptive Warped Normalization
• PARN: Position-Aware Relation Networks for Few-Shot Learning
• Deep Mining External Imperfect Data for Chest X-ray Disease Screening
• Evaluation of Deep Species Distribution Models using Environment and Co-occurrences
• Forming Ensembles at Runtime: A Machine Learning Approach
• RelaySum for Decentralized Deep Learning on Heterogeneous Data
• Boosting Co-teaching with Compression Regularization for Label Noise
• Deep Residual 3D U-Net for Joint Segmentation and Texture Classification of Nodules in Lung
• Automated brainstem parcellation using multi-atlas segmentation and deep neural network
• The Nonlinearity Coefficient - Predicting Generalization in Deep Neural Networks
• A Simple Baseline for Semi-supervised Semantic Segmentation with Strong Data Augmentation
• Deep Claim: Payer Response Prediction from Claims Data with Deep Learning
• Uncertainty-Aware Lookahead Factor Models for Quantitative Investing
• Weakly Supervised Deep Recurrent Neural Networks for Basic Dance Step Generation
• Convolutional Normalization: Improving Deep Convolutional Network Robustness and Training
• Meta Feature Modulator for Long-tailed Recognition
• HMOR: Hierarchical Multi-Person Ordinal Relations for Monocular Multi-Person 3D Pose Estimation
• Stable and expressive recurrent vision models
• Local-Selective Feature Distillation for Single Image Super-Resolution
• Are Graph Neural Networks Miscalibrated?
• NAM: Normalization-based Attention Module
• AdaDM: Enabling Normalization for Image Super-Resolution
• When Do Curricula Work?
• An Features Extraction and Recognition Method for Underwater Acoustic Target Based on ATCNN
• Learning to Sample the Most Useful Training Patches from Images
• A Robust Initialization of Residual Blocks for Effective ResNet Training without Batch Normalization
• Is Robustness the Cost of Accuracy? -- A Comprehensive Study on the Robustness of 18 Deep Image Classification Models
• Variational Autoencoders for Deforming 3D Mesh Models
• Relational Graph Representation Learning for Open-Domain Question Answering
• Exploring Gradient Flow Based Saliency for DNN Model Compression
• SENSE: a Shared Encoder Network for Scene-flow Estimation
• KISS: Keeping It Simple for Scene Text Recognition
• RSA: Randomized Simulation as Augmentation for Robust Human Action Recognition
• Sensitivity - Local Index to Control Chaoticity or Gradient Globally -
• Multi-Channel Graph Convolutional Networks
• Forecasting Human-Object Interaction: Joint Prediction of Motor Attention and Actions in First Person Video
• From Kinematics To Dynamics: Estimating Center of Pressure and Base of Support from Video Frames of Human Motion
• Powerpropagation: A sparsity inducing weight reparameterisation
• Orthogonal Convolutional Neural Networks
• Fully-Convolutional Intensive Feature Flow Neural Network for Text Recognition
• CSNNs: Unsupervised, Backpropagation-free Convolutional Neural Networks for Representation Learning
• NaturalInversion: Data-Free Image Synthesis Improving Real-World Consistency
• A Neural Network Approach for Orienting Heavy-Ion Collision Events
• A Deep Learning based Framework to Detect and Recognize Humans using Contactless Palmprints in the Wild
• Physically Explainable Deep Learning for Convective Initiation Nowcasting Using GOES-16 Satellite Observations
• Context Aware Machine Learning
• Search for the edge-on galaxies using an artificial neural network
• Regularizing Neural Networks via Adversarial Model Perturbation
• CSTNet: A Dual-Branch Convolutional Network for Imaging of Reactive Flows using Chemical Species Tomography
• Leveraging Visual Supervision for Array-based Active Speaker Detection and Localization
• A Deep-Learning Technique to Locate Cryptographic Operations in Side-Channel Traces
• Interaction-aware Factorization Machines for Recommender Systems
• MunchSonic: Tracking Fine-grained Dietary Actions through Active Acoustic Sensing on Eyeglasses
• 3D-DEEP: 3-Dimensional Deep-learning based on elevation patterns forroad scene interpretation
• Atrial Fibrillation Detection Using Deep Features and Convolutional Networks
• Quizbowl: The Case for Incremental Question Answering
• Relational Long Short-Term Memory for Video Action Recognition
• Cerberus: Attribute-based person re-identification using semantic IDs
• Estimating Photometric Redshifts for Galaxies from the DESI Legacy Imaging Surveys with Bayesian Neural Networks Trained by DESI EDR
• Spectro-Temporal RF Identification using Deep Learning
• Deep Cross Residual Learning for Multitask Visual Recognition
• Dynamic Task Control Method of a Flexible Manipulator Using a Deep Recurrent Neural Network
• Sparseout: Controlling Sparsity in Deep Networks
• Learning Expectation of Label Distribution for Facial Age and Attractiveness Estimation
• Evaluation of POSIT Arithmetic with Accelerators
• Semi-Supervised Deep Ensembles for Blind Image Quality Assessment
• Deep Fake Detection: Survey of Facial Manipulation Detection Solutions
• Machine learning classification: case of Higgs boson CP state in H to tau tau decay at LHC
• Non-local U-Net for Biomedical Image Segmentation
• Deep learning complete intersection Calabi-Yau manifolds
• Scalable and Accurate Self-supervised Multimodal Representation Learning without Aligned Video and Text Data
• Propagating Asymptotic-Estimated Gradients for Low Bitwidth Quantized Neural Networks
• Generative Models For Deep Learning with Very Scarce Data
• Object classification on video data of meteors and meteor-like phenomena: algorithm and data
• Real-time 3D object proposal generation and classification under limited processing resources
• Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles
• ARC: A Vision-based Automatic Retail Checkout System
• Neural Anisotropy Directions
• Co-VeGAN: Complex-Valued Generative Adversarial Network for Compressive Sensing MR Image Reconstruction
• Towards Learning Affine-Invariant Representations via Data-Efficient CNNs
• Compound Batch Normalization for Long-tailed Image Classification
• Making CNNs for Video Parsing Accessible
• Delving Deeper into the Decoder for Video Captioning
• SocialInteractionGAN: Multi-person Interaction Sequence Generation
• Particle Cloud Generation with Message Passing Generative Adversarial Networks
• Learning Discrete State Abstractions With Deep Variational Inference
• The 'Paris-end' of town? Urban typology through machine learning
• AOGNets: Compositional Grammatical Architectures for Deep Learning
• A Machine Learning Approach to Correcting Atmospheric Seeing in Solar Flare Observations
• MVFNet: Multi-View Fusion Network for Efficient Video Recognition
• SOAR: Second-Order Adversarial Regularization
• Neutrino Characterisation using Convolutional Neural Networks in CHIPS water Cherenkov detectors
• Deep Low-Density Separation for Semi-Supervised Classification
• A deep learning approach to multi-track location and orientation in gaseous drift chambers
• BiO-Net: Learning Recurrent Bi-directional Connections for Encoder-Decoder Architecture
• Interpretable Compositional Convolutional Neural Networks
• Weakly Supervised Person Re-ID: Differentiable Graphical Learning and A New Benchmark
• Cross-Domain First Person Audio-Visual Action Recognition through Relative Norm Alignment
• Privacy Leakage of SIFT Features via Deep Generative Model based Image Reconstruction
• Initialization of ReLUs for Dynamical Isometry
• Constraint-Based Regularization of Neural Networks
• EdgeCompress: Coupling Multidimensional Model Compression and Dynamic Inference for EdgeAI
• Meta-Learning with Adaptive Hyperparameters
• Improved End-to-End Dysarthric Speech Recognition via Meta-learning Based Model Re-initialization
• Road User Detection in Videos
• Measuring economic activity from space: a case study using flying airplanes and COVID-19
• Using Chinese Glyphs for Named Entity Recognition
• Revisiting Loss Modelling for Unstructured Pruning
• Verification of Neural Networks: Enhancing Scalability through Pruning
• Anomalous Sound Detection as a Simple Binary Classification Problem with Careful Selection of Proxy Outlier Examples
• Self-Supervised Learning by Estimating Twin Class Distributions
• MVPNet: Multi-View Point Regression Networks for 3D Object Reconstruction from A Single Image
• Schizophrenia-mimicking layers outperform conventional neural network layers
• Visuomotor Understanding for Representation Learning of Driving Scenes
• End-to-end Learning Improves Static Object Geo-localization in Monocular Video
• Fast Certified Robust Training with Short Warmup
• Attentional Feature Fusion
• Towards Deep and Efficient: A Deep Siamese Self-Attention Fully Efficient Convolutional Network for Change Detection in VHR Images
• Spherical Motion Dynamics: Learning Dynamics of Neural Network with Normalization, Weight Decay, and SGD
• Multi-modal anticipation of stochastic trajectories in a dynamic environment with Conditional Variational Autoencoders
• Real-Time Anchor-Free Single-Stage 3D Detection with IoU-Awareness
• Classifying the classifier: dissecting the weight space of neural networks
• EMC2A-Net: An Efficient Multibranch Cross-channel Attention Network for SAR Target Classification
• Unpaired Image Super-Resolution using Pseudo-Supervision
• Adaptive Loss Scaling for Mixed Precision Training
• What and How Well You Performed? A Multitask Learning Approach to Action Quality Assessment
• Unbiased deep solvers for linear parametric PDEs
• A dataset and exploration of models for understanding video data through fill-in-the-blank question-answering
• Stochastic Adversarial Koopman Model for Dynamical Systems
• Unity Style Transfer for Person Re-Identification
• Noise-Aware Ensemble Learning for Efficient Radar Modulation Recognition
• Learning Student Networks via Feature Embedding
• Set Flow: A Permutation Invariant Normalizing Flow
• Pix2Shape: Towards Unsupervised Learning of 3D Scenes from Images using a View-based Representation
• Patch vs. Global Image-Based Unsupervised Anomaly Detection in MR Brain Scans of Early Parkinsonian Patients
• A Recursive Network with Dynamic Attention for Monaural Speech Enhancement
• Integrated monitoring of ice in selected Swiss lakes. Final project report
• DensSiam: End-to-End Densely-Siamese Network with Self-Attention Model for Object Tracking
• A Bayesian Approach to Recurrence in Neural Networks
• Spatiotemporal CNN for Video Object Segmentation
• Extracting the gamma-ray source-count distribution below the Fermi-LAT detection limit with deep learning
• Self-Adaptive Training: Bridging Supervised and Self-Supervised Learning
• Music Artist Classification with Convolutional Recurrent Neural Networks
• Feature Selection for Multivariate Time Series via Network Pruning
• CNN-based Automatic Detection of Bone Conditions via Diagnostic CT Images for Osteoporosis Screening
• A Loss Curvature Perspective on Training Instability in Deep Learning
• AdaSample: Adaptive Sampling of Hard Positives for Descriptor Learning
• Latent Variables on Spheres for Autoencoders in High Dimensions
• xEEGNet: Towards Explainable AI in EEG Dementia Classification
• Forged Image Detection using SOTA Image Classification Deep Learning Methods for Image Forensics with Error Level Analysis
• TetraSphere: A Neural Descriptor for O(3)-Invariant Point Cloud Analysis
• The Three Hundred Project: Mapping The Matter Distribution in Galaxy Clusters Via Deep Learning from Multiview Simulated Observations
• Directional Statistics-based Deep Metric Learning for Image Classification and Retrieval
• Efficient Semantic Scene Completion Network with Spatial Group Convolution
• Hire-MLP: Vision MLP via Hierarchical Rearrangement
• Reconstruction Bottlenecks in Object-Centric Generative Models
• Embedded Large-Scale Handwritten Chinese Character Recognition
• DebCSE: Rethinking Unsupervised Contrastive Sentence Embedding Learning in the Debiasing Perspective
• Learning to Match Distributions for Domain Adaptation
• TSIT: A Simple and Versatile Framework for Image-to-Image Translation
• Optimising for Interpretability: Convolutional Dynamic Alignment Networks
• HopGAT: Hop-aware Supervision Graph Attention Networks for Sparsely Labeled Graphs
• MBNet: MOS Prediction for Synthesized Speech with Mean-Bias Network
• MyDigitalFootprint: an extensive context dataset for pervasive computing applications at the edge
• CycleGAN-VC3: Examining and Improving CycleGAN-VCs for Mel-spectrogram Conversion
• Real-time Detection of 2D Tool Landmarks with Synthetic Training Data
• Learning Interpretable Concept Groups in CNNs
• Deep neural network for solving differential equations motivated by Legendre-Galerkin approximation
• Learning Selective Mutual Attention and Contrast for RGB-D Saliency Detection
• A Quantitative Analysis of the Effect of Batch Normalization on Gradient Descent
• Image Super-Resolution via RL-CSC: When Residual Learning Meets Convolutional Sparse Coding
• Self-supervised Learning of Rotation-invariant 3D Point Set Features using Transformer and its Self-distillation
• Sound Event Detection of Weakly Labelled Data with CNN-Transformer and Automatic Threshold Optimization
• Generating artificial digital image correlation data using physics-guided adversarial networks
• Batch-normalized Recurrent Highway Networks
• Scene Change Detection Using Multiscale Cascade Residual Convolutional Neural Networks
• A Committee of Convolutional Neural Networks for Image Classication in the Concurrent Presence of Feature and Label Noise
• Improving Sequential Latent Variable Models with Autoregressive Flows
• Predicting Research Trends in Artificial Intelligence with Gradient Boosting Decision Trees and Time-aware Graph Neural Networks
• Towards scalable pattern-based optimization for dense linear algebra
• MaCow: Masked Convolutional Generative Flow
• SPIN: A High Speed, High Resolution Vision Dataset for Tracking and Action Recognition in Ping Pong
• Ranked List Loss for Deep Metric Learning
• One Self-Configurable Model to Solve Many Abstract Visual Reasoning Problems
• Increasing Depth Leads to U-Shaped Test Risk in Over-parameterized Convolutional Networks
• Deep Ensembles on a Fixed Memory Budget: One Wide Network or Several Thinner Ones?
• Blind Inpainting of Large-scale Masks of Thin Structures with Adversarial and Reinforcement Learning
• ADF & TransApp: A Transformer-Based Framework for Appliance Detection Using Smart Meter Consumption Series
• Training Energy-Efficient Deep Spiking Neural Networks with Time-to-First-Spike Coding
• Learning the Lantern: Neural network applications to broadband photonic lantern modelling
• You Look Twice: GaterNet for Dynamic Filter Selection in CNNs
• Convolutional Neural Networks with Dynamic Regularization
• Dependency Aware Filter Pruning
• Multigrid Neural Architectures
• Meta Learning for Few-Shot One-class Classification
• Learning towards Minimum Hyperspherical Energy
• Deep Learning-Based Position Detection for Hydraulic Cylinders Using Scattering Parameters
• Instance Cross Entropy for Deep Metric Learning
• LPRNet: Lightweight Deep Network by Low-rank Pointwise Residual Convolution
• Towards Defending Multiple ${\ell }_p$-norm Bounded Adversarial Perturbations via Gated Batch Normalization
• Deciphering quantum fingerprints in electric conductance
• Learning Dynamics from Kinematics: Estimating 2D Foot Pressure Maps from Video Frames
• Leveraging Deep Learning for Time Series Extrinsic Regression in predicting photometric metallicity of Fundamental-mode RR Lyrae Stars
• Machine learning methods for Schlieren imaging of a plasma channel in tenuous atomic vapor
• Language Anisotropic Cross-Lingual Model Editing
• A comprehensive approach to incorporating intermolecular dispersion into the openCOSMO-RS model. Part 2: Atomic polarizabilities
• i-Razor: A Differentiable Neural Input Razor for Feature Selection and Dimension Search in DNN-Based Recommender Systems
• Hardware-software co-exploration with racetrack memory based in-memory computing for CNN inference in embedded systems
• Kernelized Wasserstein Natural Gradient
• Learning by Turning: Neural Architecture Aware Optimisation
• MRI to PET Cross-Modality Translation using Globally and Locally Aware GAN (GLA-GAN) for Multi-Modal Diagnosis of Alzheimer's Disease
• Improving Parametric Neural Networks for High-Energy Physics (and Beyond)
• Detecting cognitive impairments by agreeing on interpretations of linguistic features
• An Efficient Dual-Line Decoder Network with Multi-Scale Convolutional Attention for Multi-organ Segmentation
• 3D-to-2D Distillation for Indoor Scene Parsing
• Multi-channel Deep 3D Face Recognition
• FedHealth 2: Weighted Federated Transfer Learning via Batch Normalization for Personalized Healthcare
• LP-3DCNN: Unveiling Local Phase in 3D Convolutional Neural Networks
• Popcorn: Paillier Meets Compression For Efficient Oblivious Neural Network Inference
• A Feature Fusion-Net Using Deep Spatial Context Encoder and Nonstationary Joint Statistical Model for High Resolution SAR Image Classification
• A 1Mb mixed-precision quantized encoder for image classification and patch-based compression
• Self-Supervised Pillar Motion Learning for Autonomous Driving
• DeepRemaster: Temporal Source-Reference Attention Networks for Comprehensive Video Enhancement
• S-SGD: Symmetrical Stochastic Gradient Descent with Weight Noise Injection for Reaching Flat Minima
• Weisfeiler and Lehman Go Cellular: CW Networks
• Tool Shape Optimization through Backpropagation of Neural Network
• Re-using Adversarial Mask Discriminators for Test-time Training under Distribution Shifts
• Semantic similarity metrics for learned image registration
• Romanian Speech Recognition Experiments from the ROBIN Project
• Do All MobileNets Quantize Poorly? Gaining Insights into the Effect of Quantization on Depthwise Separable Convolutional Networks Through the Eyes of Multi-scale Distributional Dynamics
• Generative Deep Learning Techniques for Password Generation
• The Z-loss: a shift and scale invariant classification loss belonging to the Spherical Family
• Block Shuffle: A Method for High-resolution Fast Style Transfer with Limited Memory
• Exploiting Channel Similarity for Accelerating Deep Convolutional Neural Networks
• Improving Consistency and Correctness of Sequence Inpainting using Semantically Guided Generative Adversarial Network
• Neural Dataset Generality
• Cooperative Training of Fast Thinking Initializer and Slow Thinking Solver for Conditional Learning
• RigNet: Repetitive Image Guided Network for Depth Completion
• Detection of Object Throwing Behavior in Surveillance Videos
• Digital Passport: A Novel Technological Strategy for Intellectual Property Protection of Convolutional Neural Networks
• Hierarchical Feature Aggregation Networks for Video Action Recognition
• A Two-Step Framework for Arbitrage-Free Prediction of the Implied Volatility Surface
• Sparsely Aggregated Convolutional Networks
• Compressed Learning of Deep Neural Networks for OpenCL-Capable Embedded Systems
• RGB-D-Fusion: Image Conditioned Depth Diffusion of Humanoid Subjects
• Improving Ultrasound Tongue Image Reconstruction from Lip Images Using Self-supervised Learning and Attention Mechanism
• WaveGrad 2: Iterative Refinement for Text-to-Speech Synthesis
• Spectrum concentration in deep residual learning: a free probability approach
• TuiGAN: Learning Versatile Image-to-Image Translation with Two Unpaired Images
• Fast Quantum Property Prediction via Deeper 2D and 3D Graph Networks
• Adaptive Task Sampling for Meta-Learning
• An ADMM-Newton-CNN Numerical Approach to a TV Model for Identifying Discontinuous Diffusion Coefficients in Elliptic Equations: Convex Case with Gradient Observations
• Overcoming Difficulty in Obtaining Dark-skinned Subjects for Remote-PPG by Synthetic Augmentation
• Controlling Model Complexity in Probabilistic Model-Based Dynamic Optimization of Neural Network Structures
• Multi-Task Image-Based Dietary Assessment for Food Recognition and Portion Size Estimation
• A Lightweight Structure Aimed to Utilize Spatial Correlation for Sparse-View CT Reconstruction
• Generative Zero-shot Network Quantization
• Diagnostic Spatio-temporal Transformer with Faithful Encoding
• Embedding Transfer with Label Relaxation for Improved Metric Learning
• Monocular Depth Estimation with Augmented Ordinal Depth Relationships
• Non-Negative Bregman Divergence Minimization for Deep Direct Density Ratio Estimation
• 3D Quasi-Recurrent Neural Network for Hyperspectral Image Denoising
• An Investigation of the Effectiveness of Phase for Audio Classification
• KinePose: A temporally optimized inverse kinematics technique for 6DOF human pose estimation with biomechanical constraints
• Bayesian Statistics Guided Label Refurbishment Mechanism: Mitigating Label Noise in Medical Image Classification
• DRILL: Dynamic Representations for Imbalanced Lifelong Learning
• Attentive Normalization for Conditional Image Generation
• Stable Tool-Use with Flexible Musculoskeletal Hands by Learning the Predictive Model of Sensor State Transition
• Find the Conversation Killers: a Predictive Study of Thread-ending Posts
• Open DNN Box by Power Side-Channel Attack
• Exploring Uncertainty Measures for Image-Caption Embedding-and-Retrieval Task
• Learning from Videos with Deep Convolutional LSTM Networks
• Activity Driven Weakly Supervised Object Detection
• DeepLight: Learning Illumination for Unconstrained Mobile Mixed Reality
• Modulating Image Restoration with Continual Levels via Adaptive Feature Modification Layers
• A resnet-based universal method for speckle reduction in optical coherence tomography images
• Concatenated Feature Pyramid Network for Instance Segmentation
• Spatiotemporal Pyramid Network for Video Action Recognition
• From Visual to Acoustic Question Answering
• Detecting Colorized Images via Convolutional Neural Networks: Toward High Accuracy and Good Generalization
• Revisiting Sample Selection Approach to Positive-Unlabeled Learning: Turning Unlabeled Data into Positive rather than Negative
• Online Learning to Rank with List-level Feedback for Image Filtering
• Deep-HR: Fast Heart Rate Estimation from Face Video Under Realistic Conditions
• Deep Motion Blur Removal Using Noisy/Blurry Image Pairs
• Ground Truth Simulation for Deep Learning Classification of Mid-Resolution Venus Images Via Unmixing of High-Resolution Hyperspectral Fenix Data
• Tabulated MLP for Fast Point Feature Embedding
• TAB-VCR: Tags and Attributes based Visual Commonsense Reasoning Baselines
• DeepFolio: Convolutional Neural Networks for Portfolios with Limit Order Book Data
• Deep Learning Based Early Diagnostics of Parkinsons Disease
• Deep Kernel Survival Analysis and Subject-Specific Survival Time Prediction Intervals
• A New Look at Ghost Normalization
• Stereo Vision Based Single-Shot 6D Object Pose Estimation for Bin-Picking by a Robot Manipulator
• When Residual Learning Meets Dense Aggregation: Rethinking the Aggregation of Deep Neural Networks
• Transferable, Controllable, and Inconspicuous Adversarial Attacks on Person Re-identification With Deep Mis-Ranking
• Neural Architecture Search for Lightweight Non-Local Networks
• Towards Multi-Scale Style Control for Expressive Speech Synthesis
• MOST: A Multi-Oriented Scene Text Detector with Localization Refinement
• HVPR: Hybrid Voxel-Point Representation for Single-stage 3D Object Detection
• Bilevel Online Adaptation for Out-of-Domain Human Mesh Reconstruction
• 3D Human Pose, Shape and Texture from Low-Resolution Images and Videos
• Multi-Task Self-Supervised Pre-Training for Music Classification
• A Supervised Learning Approach for Robust Health Monitoring using Face Videos
• Generative Adversarial Network for Image Synthesis
• Disentangled Planning and Control in Vision Based Robotics via Reward Machines
• Centralized Information Interaction for Salient Object Detection
• SB-MTL: Score-based Meta Transfer-Learning for Cross-Domain Few-Shot Learning
• Separation and Concentration in Deep Networks
• Jet tagging in the Lund plane with graph networks
• Dual Encoder Fusion U-Net (DEFU-Net) for Cross-manufacturer Chest X-ray Segmentation
• Decentralised Person Re-Identification with Selective Knowledge Aggregation
• The Impact of Reinitialization on Generalization in Convolutional Neural Networks
• Feature Stylization and Domain-aware Contrastive Learning for Domain Generalization
• m-RevNet: Deep Reversible Neural Networks with Momentum
• Manipulating Identical Filter Redundancy for Efficient Pruning on Deep and Complicated CNN
• Data-driven deep density estimation
• Improving Sound Event Classification by Increasing Shift Invariance in Convolutional Neural Networks
• Bag of Tricks for Neural Architecture Search
• Maximum Entropy Weighted Independent Set Pooling for Graph Neural Networks
• Context-aware PolyUNet for Liver and Lesion Segmentation from Abdominal CT Images
• The Nonlinearity Coefficient - A Practical Guide to Neural Architecture Design
• Partially Oblivious Neural Network Inference
• Picking Up Quantization Steps for Compressed Image Classification
• An Intelligent Approach to Detecting Novel Fault Classes for Centrifugal Pumps Based on Deep CNNs and Unsupervised Methods
• Effective Multi-Stage Training Model For Edge Computing Devices In Intrusion Detection
• Variational Prefix Tuning for Diverse and Accurate Code Summarization Using Pre-trained Language Models
• Hyperbolic Deep Learning for Foundation Models: A Survey
• Reducing Label Dependency in Human Activity Recognition with Wearables: From Supervised Learning to Novel Weakly Self-Supervised Approaches
• RadarCNN: Learning-based Indoor Object Classification from IQ Imaging Radar Data
• End-to-End Deep Learning in Phase Noisy Coherent Optical Link
• Active Learning-Based Optimization of Hydroelectric Turbine Startup to Minimize Fatigue Damage
• Murine AI excels at cats and cheese: Structural differences between human and mouse neurons and their implementation in generative AIs
• An Enhanced Harmonic Densely Connected Hybrid Transformer Network Architecture for Chronic Wound Segmentation Utilising Multi-Colour Space Tensor Merging
• Deep Feature Gaussian Processes for Single-Scene Aerosol Optical Depth Reconstruction
• Deep-learning design of graphene metasurfaces for quantum control and Dirac electron holography
• Testing Outlier Detection Algorithms for Identifying Early-Stage Solute Clusters in Atom Probe Tomography
• Self-Supervised Representation Learning for Nerve Fiber Distribution Patterns in 3D-PLI
• Rotational Augmented Noise2Inverse for Low-dose Computed Tomography Reconstruction
• A Simple and Robust Framework for Cross-Modality Medical Image Segmentation applied to Vision Transformers
• Towards a Machine-Learned Poisson Solver for Low-Temperature Plasma Simulations in Complex Geometries
• Explicit Abnormality Extraction for Unsupervised Motion Artifact Reduction in Magnetic Resonance Imaging
• Denoising Particle Beam Micrographs with Plug-and-Play Methods
• Hidden-Fold Networks: Random Recurrent Residuals Using Sparse Supermasks
• Pyramid Adversarial Training Improves ViT Performance
• Connectivity Matters: Neural Network Pruning Through the Lens of Effective Sparsity
• Locally Enhanced Self-Attention: Combining Self-Attention and Convolution as Local and Context Terms
• Dynamical Isometry: The Missing Ingredient for Neural Network Pruning
• On Feature Decorrelation in Self-Supervised Learning
• Intentional Deep Overfit Learning (IDOL): A Novel Deep Learning Strategy for Adaptive Radiation Therapy
• A State-of-the-art Survey of Artificial Neural Networks for Whole-slide Image Analysis:from Popular Convolutional Neural Networks to Potential Visual Transformers
• Low-Fidelity End-to-End Video Encoder Pre-training for Temporal Action Localization
• Efficient learning of goal-oriented push-grasping synergy in clutter
• Scaling Up Exact Neural Network Compression by ReLU Stability
• A Runtime-Based Computational Performance Predictor for Deep Neural Network Training
• Distributed Training and Optimization Of Neural Networks
• SmartShuttle: Model Based Design and Evaluation of Automated On-Demand Shuttles for Solving the First-Mile and Last-Mile Problem in a Smart City
• Cross-Layer Distillation with Semantic Calibration
• Predicting Localized Primordial Star Formation with Deep Convolutional Neural Networks
• EqCo: Equivalent Rules for Self-supervised Contrastive Learning
• VirtualFlow: Decoupling Deep Learning Models from the Underlying Hardware
• Multi-Task Learning for Interpretable Weakly Labelled Sound Event Detection
• The Representation Theory of Neural Networks
• Concept Learners for Few-Shot Learning
• Neural Mesh Flow: 3D Manifold Mesh Generation via Diffeomorphic Flows
• Taming GANs with Lookahead-Minmax
• FNA++: Fast Network Adaptation via Parameter Remapping and Architecture Search
• Deep learning method to remove chemical, kinetic and electric artifacts on ISEs
• Semantically Multi-modal Image Synthesis
• Orthogonal Over-Parameterized Training
• RANSAC-Flow: generic two-stage image alignment
• Towards democratizing music production with AI-Design of Variational Autoencoder-based Rhythm Generator as a DAW plugin
• Source Printer Identification from Document Images Acquired using Smartphone
• BS-NAS: Broadening-and-Shrinking One-Shot NAS with Searchable Numbers of Channels
• LCP: A Low-Communication Parallelization Method for Fast Neural Network Inference in Image Recognition
• Unsupervised Audiovisual Synthesis via Exemplar Autoencoders
• Dense Residual Network: Enhancing Global Dense Feature Flow for Character Recognition
• On Random Kernels of Residual Architectures
• Optimizing Data Usage via Differentiable Rewards
• Information-Theoretic Local Minima Characterization and Regularization
• Single-Stage 6D Object Pose Estimation
• JSI-GAN: GAN-Based Joint Super-Resolution and Inverse Tone-Mapping with Pixel-Wise Task-Specific Filters for UHD HDR Video
• FlatteNet: A Simple Versatile Framework for Dense Pixelwise Prediction
• SpatialSense: An Adversarially Crowdsourced Benchmark for Spatial Relation Recognition
• Mixed-Supervised Dual-Network for Medical Image Segmentation
• Natural-Logarithm-Rectified Activation Function in Convolutional Neural Networks
• Interleaved Multitask Learning for Audio Source Separation with Independent Databases
• Deep Triplet Neural Networks with Cluster-CCA for Audio-Visual Cross-modal Retrieval
• Composition-Aware Image Aesthetics Assessment
• Dimensional Reweighting Graph Convolutional Networks
• Accelerating temporal action proposal generation via high performance computing
• Inner-Imaging Networks: Put Lenses into Convolutional Structure
• EventNet: Asynchronous Recursive Event Processing
• Deep Metric Learning by Online Soft Mining and Class-Aware Attention
• FineGAN: Unsupervised Hierarchical Disentanglement for Fine-Grained Object Generation and Discovery
• Multi-Expert Gender Classification on Age Group by Integrating Deep Neural Networks
• MRFusion: A Deep Learning architecture to fuse PAN and MS imagery for land cover mapping
• Differential Diagnosis for Pancreatic Cysts in CT Scans Using Densely-Connected Convolutional Networks
• Improving Confidence Estimates for Unfamiliar Examples
• Predicting Adversarial Examples with High Confidence
• PrivPy: Enabling Scalable and General Privacy-Preserving Machine Learning
• McKernel: A Library for Approximate Kernel Expansions in Log-linear Time
• NEON: Living Needs Prediction System in Meituan
• Learning End-to-End Lossy Image Compression: A Benchmark
• Neural Academic Paper Generation
• Pinyin Regularization in Error Correction for Chinese Speech Recognition with Large Language Models
• CTC-aligned Audio-Text Embedding for Streaming Open-vocabulary Keyword Spotting
• Generalizable Model-agnostic Semantic Segmentation via Target-specific Normalization
• Online Learning of Danger Avoidance for Complex Structures of Musculoskeletal Humanoids and Its Applications
• Histogram-Equalized Quantization for logic-gated Residual Neural Networks
• Evaluating Convolutional Neural Networks for COVID-19 classification in chest X-ray images
• Iris Style Transfer: Enhancing Iris Recognition with Style Features and Privacy Preservation through Neural Style Transfer
• BackPACK: Packing more into backprop
• PD-GAN: Probabilistic Diverse GAN for Image Inpainting
• Novel Suboptimal approaches for Hyperparameter Tuning of Deep Neural Network [under the shelf of Optical Communication]
• Exploiting Inter-Sample Information for Long-tailed Out-of-Distribution Detection
• Improving ensemble extreme precipitation forecasts using generative artificial intelligence
• Relation Network for Person Re-identification
• MaLa-ASR: Multimedia-Assisted LLM-Based ASR
• SPDGAN: A Generative Adversarial Network based on SPD Manifold Learning for Automatic Image Colorization
• Analytical Verification of Performance of Deep Neural Network Based Time-Synchronized Distribution System State Estimation
• Effect of latent space distribution on the segmentation of images with multiple annotations
• Beyond Fixed Grid: Learning Geometric Image Representation with a Deformable Grid
• A machine learning photon detection algorithm for coherent X-ray ultrafast fluctuation analysis
• Faster Optimization-Based Meta-Learning Adaptation Phase
• Feedback Gradient Descent: Efficient and Stable Optimization with Orthogonality for DNNs
• Towards Amortized Ranking-Critical Training for Collaborative Filtering
• Unsupervised MRI Super-Resolution Using Deep External Learning and Guided Residual Dense Network with Multimodal Image Priors
• Improved Transformer for High-Resolution GANs
• DCT-Conv: Coding filters in convolutional networks with Discrete Cosine Transform
• Stage-based Hyper-parameter Optimization for Deep Learning
• Regularizing Neural Networks via Minimizing Hyperspherical Energy
• DeepLABNet: End-to-end Learning of Deep Radial Basis Networks with Fully Learnable Basis Functions
• Learnable Adaptive Cosine Estimator (LACE) for Image Classification
• Hierarchical Graph Networks for 3D Human Pose Estimation
• Annotation-Free Cardiac Vessel Segmentation via Knowledge Transfer from Retinal Images
• Propose-and-Attend Single Shot Detector
• Image Captioning with Sparse Recurrent Neural Network
• Automated Cardiac Resting Phase Detection Targeted on the Right Coronary Artery
• ID-aware Quality for Set-based Person Re-identification
• 3D Pose Transfer with Correspondence Learning and Mesh Refinement
• MEx: Multi-modal Exercises Dataset for Human Activity Recognition
• Table-Based Neural Units: Fully Quantizing Networks for Multiply-Free Inference
• Highly Accurate CNN Inference Using Approximate Activation Functions over Homomorphic Encryption
• LIP: Local Importance-based Pooling
• NAAQA: A Neural Architecture for Acoustic Question Answering
• DcaseNet: An integrated pretrained deep neural network for detecting and classifying acoustic scenes and events
• Unsupervised Text Summarization via Mixed Model Back-Translation
• U-Net Training with Instance-Layer Normalization
• Selection Bias Explorations and Debias Methods for Natural Language Sentence Matching Datasets
• [Extended version] Rethinking Deep Neural Network Ownership Verification: Embedding Passports to Defeat Ambiguity Attacks
• Adversarial Robustness of Stabilized NeuralODEs Might be from Obfuscated Gradients
• An Effective Hit-or-Miss Layer Favoring Feature Interpretation as Learned Prototypes Deformations
• Hierarchical Representation Network for Steganalysis of QIM Steganography in Low-Bit-Rate Speech Signals
• Encoding Robustness to Image Style via Adversarial Feature Perturbations
• IntersectGAN: Learning Domain Intersection for Generating Images with Multiple Attributes
• Train-by-Reconnect: Decoupling Locations of Weights from their Values
• Automatic Analysis System of Calcaneus Radiograph: Rotation-Invariant Landmark Detection for Calcaneal Angle Measurement, Fracture Identification and Fracture Region Segmentation
• Neural Topic Modeling with Cycle-Consistent Adversarial Training
• Global Convergence and Generalization Bound of Gradient-Based Meta-Learning with Deep Neural Nets
• Learning Fully Dense Neural Networks for Image Semantic Segmentation
• A Seq-to-Seq Transformer Premised Temporal Convolutional Network for Chinese Word Segmentation
• Learning Channel Inter-dependencies at Multiple Scales on Dense Networks for Face Recognition
• Multi-stream 3D FCN with Multi-scale Deep Supervision for Multi-modality Isointense Infant Brain MR Image Segmentation
• Deep-3DAligner: Unsupervised 3D Point Set Registration Network With Optimizable Latent Vector
• Learning Discriminative Feature with CRF for Unsupervised Video Object Segmentation
• SimPose: Effectively Learning DensePose and Surface Normals of People from Simulated Data
• Unsupervised Disentanglement GAN for Domain Adaptive Person Re-Identification
• FarSee-Net: Real-Time Semantic Segmentation by Efficient Multi-scale Context Aggregation and Feature Space Super-resolution
• URIE: Universal Image Enhancement for Visual Recognition in the Wild
• DeepDive: An Integrative Algorithm/Architecture Co-Design for Deep Separable Convolutional Neural Networks
• Deep Fusion Network for Image Completion
• Compressed DenseNet for Lightweight Character Recognition
• Xiaomingbot: A Multilingual Robot News Reporter
• Multi-Partition Embedding Interaction with Block Term Format for Knowledge Graph Completion
• Exploiting Contextual Information with Deep Neural Networks
• Are You Convinced? Choosing the More Convincing Evidence with a Siamese Network
• Facial Expression Editing with Continuous Emotion Labels
• Single Image Deraining with Continuous Rain Density Estimation
• Multiple Attentional Pyramid Networks for Chinese Herbal Recognition
• Federated Generative Adversarial Learning
• Leveraging Photometric Consistency over Time for Sparsely Supervised Hand-Object Reconstruction
• Continual Learning with Extended Kronecker-factored Approximate Curvature
• LAFEAT: Piercing Through Adversarial Defenses with Latent Features
• The General Pair-based Weighting Loss for Deep Metric Learning
• Comprehensive process-molten pool relations modeling using CNN for wire-feed laser additive manufacturing
• Including Physics in Deep Learning -- An example from 4D seismic pressure saturation inversion
• CNN Model & Tuning for Global Road Damage Detection
• Estimating Atmospheric Parameters of DA White Dwarf Stars with Deep Learning
• Uncertainty-guided Model Generalization to Unseen Domains
• SAVERS: SAR ATR with Verification Support Based on Convolutional Neural Network
• A Real-time Low-cost Artificial Intelligence System for Autonomous Spraying in Palm Plantations
• CDLNet: Robust and Interpretable Denoising Through Deep Convolutional Dictionary Learning
• Meta-Learned Attribute Self-Gating for Continual Generalized Zero-Shot Learning
• Probabilistic Vehicle Reconstruction Using a Multi-Task CNN
• Multi-Service Mobile Traffic Forecasting via Convolutional Long Short-Term Memories
• Improving Few-Shot Learning with Auxiliary Self-Supervised Pretext Tasks
• Real-Time Freespace Segmentation on Autonomous Robots for Detection of Obstacles and Drop-Offs
• Large Scale Fine-Grained Categorization and Domain-Specific Transfer Learning
• Inverse reinforcement learning for autonomous navigation via differentiable semantic mapping and planning
• Data augmentation and image understanding
• MC-LSTM: Mass-Conserving LSTM
• Towards Certifying L-infinity Robustness using Neural Networks with L-inf-dist Neurons
• Unsupervised Cross-Lingual Speech Emotion Recognition Using DomainAdversarial Neural Network
• SeqMobile: A Sequence Based Efficient Android Malware Detection System Using RNN on Mobile Devices
• Robust Raw Waveform Speech Recognition Using Relevance Weighted Representations
• Learning Eye-in-Hand Camera Calibration from a Single Image
• Incorporating Luminance, Depth and Color Information by a Fusion-based Network for Semantic Segmentation
• Continual Learning: Tackling Catastrophic Forgetting in Deep Neural Networks with Replay Processes
• An Empirical Study of Graph Contrastive Learning
• NAS-HPO-Bench-II: A Benchmark Dataset on Joint Optimization of Convolutional Neural Network Architecture and Training Hyperparameters
• Deep Multi-View Learning via Task-Optimal CCA
• Evaluation of Error and Correlation-Based Loss Functions For Multitask Learning Dimensional Speech Emotion Recognition
• Identifying Critical Neurons in ANN Architectures using Mixed Integer Programming
• TreeNet: A lightweight One-Shot Aggregation Convolutional Network
• Dynamic Inference: A New Approach Toward Efficient Video Action Recognition
• Global-Local Transformer for Brain Age Estimation
• RePr: Improved Training of Convolutional Filters
• Piecewise Linear Units Improve Deep Neural Networks
• Deep Self-Supervised Representation Learning for Free-Hand Sketch
• Class-Distinct and Class-Mutual Image Generation with GANs
• Gradient-Coherent Strong Regularization for Deep Neural Networks
• RotoGrad: Gradient Homogenization in Multitask Learning
• Unsupervised Domain Adaptation for Retinal Vessel Segmentation with Adversarial Learning and Transfer Normalization
• On the Role of Optimization in Double Descent: A Least Squares Study
• A Comparison for Patch-level Classification of Deep Learning Methods on Transparent Environmental Microorganism Images: from Convolutional Neural Networks to Visual Transformers
• Deep Multi-task Learning for Facial Expression Recognition and Synthesis Based on Selective Feature Sharing
• On a Sparse Shortcut Topology of Artificial Neural Networks
• Incorporating Multi-Target in Multi-Stage Speech Enhancement Model for Better Generalization
• Learning to match transient sound events using attentional similarity for few-shot sound recognition
• Multimodal Reward Shaping for Efficient Exploration in Reinforcement Learning
• AdaptCL: Efficient Collaborative Learning with Dynamic and Adaptive Pruning
• Have you forgotten? A method to assess if machine learning models have forgotten data
• A Deep Learning Model for Chilean Bills Classification
• Task-agnostic Continual Learning with Hybrid Probabilistic Models
• Adapting Off-the-Shelf Source Segmenter for Target Medical Image Segmentation
• Scaling Properties of Deep Residual Networks
• Clinical Predictive Models for COVID-19: Systematic Study
• Learning Class Regularized Features for Action Recognition
• Tensor Processing Primitives: A Programming Abstraction for Efficiency and Portability in Deep Learning & HPC Workloads
• SDGMNet: Statistic-based Dynamic Gradient Modulation for Local Descriptor Learning
• A contrastive rule for meta-learning
• Tracking Without Re-recognition in Humans and Machines
• Investigation of Uncertainty of Deep Learning-based Object Classification on Radar Spectra
• Regularity Normalization: Neuroscience-Inspired Unsupervised Attention across Neural Network Layers
• Aligning Visual Prototypes with BERT Embeddings for Few-Shot Learning
• StampNet: unsupervised multi-class object discovery
• On the Importance of Video Action Recognition for Visual Lipreading
• Deep Sigma Point Processes
• Efficient Reinforcement Learning for StarCraft by Abstract Forward Models and Transfer Learning
• SketchBetween: Video-to-Video Synthesis for Sprite Animation via Sketches
• Transfer Learning via Test-Time Neural Networks Aggregation
• Scaling Object Detection by Transferring Classification Weights
• Robust Deep Graph Based Learning for Binary Classification
• Visual deep learning-based explanation for neuritic plaques segmentation in Alzheimer's Disease using weakly annotated whole slide histopathological images
• A Possible Converter to Denoise the Images of Exoplanet Candidates through Machine Learning Techniques
• Differential Evolution Algorithm based Hyper-Parameters Selection of Convolutional Neural Network for Speech Command Recognition
• Variational Depth Search in ResNets
• Controllable Orthogonalization in Training DNNs
• Layer-wise Conditioning Analysis in Exploring the Learning Dynamics of DNNs
• Exploring the Loss Landscape in Neural Architecture Search
• Hypernetwork-Based Augmentation
• Region-based Non-local Operation for Video Classification
• Gradient Origin Networks
• Deep Dynamic Factor Models
• Consistent Batch Normalization for Weighted Loss in Imbalanced-Data Environment
• Curriculum learning for multilevel budgeted combinatorial problems
• AQD: Towards Accurate Fully-Quantized Object Detection
• Lessons Learned from the Training of GANs on Artificial Datasets
• NASirt: AutoML based learning with instance-level complexity information
• Random Polytope Descriptors
• On the Power of Deep but Naive Partial Label Learning
• AdaCrowd: Unlabeled Scene Adaptation for Crowd Counting
• Learning to Embed Categorical Features without Embedding Tables for Recommendation
• Neural Machine Translation: A Review and Survey
• Locality Preserving Dense Graph Convolutional Networks with Graph Context-Aware Node Representations
• Deep-HOSeq: Deep Higher Order Sequence Fusion for Multimodal Sentiment Analysis
• Interpretable Visual Reasoning via Induced Symbolic Space
• Automatic artifact removal of resting-state fMRI with Deep Neural Networks
• CG-Net: Conditional GIS-aware Network for Individual Building Segmentation in VHR SAR Images
• Initializing ReLU networks in an expressive subspace of weights
• Hierarchical Proxy-based Loss for Deep Metric Learning
• Rethinking Neural Operations for Diverse Tasks
• Contextual Joint Factor Acoustic Embeddings
• Embracing the Disharmony in Medical Imaging: A Simple and Effective Framework for Domain Adaptation
• Learning Classifiers on Positive and Unlabeled Data with Policy Gradient
• Real Negatives Matter: Continuous Training with Real Negatives for Delayed Feedback Modeling
• Soft Expectation and Deep Maximization for Image Feature Detection
• SNDCNN: Self-normalizing deep CNNs with scaled exponential linear units for speech recognition
• LEt-SNE: A Hybrid Approach To Data Embedding and Visualization of Hyperspectral Imagery
• Acoustic scene analysis with multi-head attention networks
• Recurrent Connectivity Aids Recognition of Partly Occluded Objects
• Local Latent Representation based on Geometric Convolution for Particle Data Feature Exploration
• Understanding the Effects of Pre-Training for Object Detectors via Eigenspectrum
• Initialization and Regularization of Factorized Neural Layers
• RADDet: Range-Azimuth-Doppler based Radar Object Detection for Dynamic Road Users
• A few filters are enough: Convolutional Neural Network for P300 Detection
• Thanks for Nothing: Predicting Zero-Valued Activations with Lightweight Convolutional Neural Networks
• Towards Deeper Deep Reinforcement Learning with Spectral Normalization
• On the Periodic Behavior of Neural Network Training with Batch Normalization and Weight Decay
• DECORE: Deep Compression with Reinforcement Learning
• A Deep Learning Approach to Grasping the Invisible
• Linear Context Transform Block
• 3D Human Pose Estimation Based on 2D-3D Consistency with Synchronized Adversarial Training
• Deep Reinforcement Learning for Chatbots Using Clustered Actions and Human-Likeness Rewards
• How many degrees of freedom do we need to train deep networks: a loss landscape perspective
• InsPose: Instance-Aware Networks for Single-Stage Multi-Person Pose Estimation
• Distributionally Robust Policy Learning via Adversarial Environment Generation
• Deep Neural Network-Based Blind Multiple User Detection for Grant-free Multi-User Shared Access
• HBONet: Harmonious Bottleneck on Two Orthogonal Dimensions
• DSIC: Deep Stereo Image Compression
• Noise-Resistant Deep Metric Learning with Probabilistic Instance Filtering
• Grasp Type Estimation for Myoelectric Prostheses using Point Cloud Feature Learning
• Compressive Visual Representations
• A deep learning guided memetic framework for graph coloring problems
• Scarce Data Driven Deep Learning of Drones via Generalized Data Distribution Space
• Automated Brain Tumour Segmentation Using Deep Fully Residual Convolutional Neural Networks
• An Empirical Study of Batch Normalization and Group Normalization in Conditional Computation
• Why Lottery Ticket Wins? A Theoretical Perspective of Sample Complexity on Pruned Neural Networks
• Towards Learning Universal Audio Representations
• Evaluating Self and Semi-Supervised Methods for Remote Sensing Segmentation Tasks
• Neuron with Steady Response Leads to Better Generalization
• All-In-One: Artificial Association Neural Networks
• Joint Learning of Visual-Audio Saliency Prediction and Sound Source Localization on Multi-face Videos
• Particle Graph Autoencoders and Differentiable, Learned Energy Mover's Distance
• Generative Adversarial Networks and Adversarial Autoencoders: Tutorial and Survey
• Benchmarking Shadow Removal for Facial Landmark Detection and Beyond
• Interpretable Neural Network Decoupling
• Trap of Feature Diversity in the Learning of MLPs
• Monocular Spherical Depth Estimation with Explicitly Connected Weak Layout Cues
• Exploring the Effects of Data Augmentation for Drivable Area Segmentation
• Fashion Editing with Adversarial Parsing Learning
• Optimization of convolutional neural networks for background suppression in the PandaX-III experiment
• Video Segmentation Learning Using Cascade Residual Convolutional Neural Network
• Investigating and Improving Latent Density Segmentation Models for Aleatoric Uncertainty Quantification in Medical Imaging
• Bayesian Optimization with Approximate Set Kernels
• LiStereo: Generate Dense Depth Maps from LIDAR and Stereo Imagery
• ICTSurF: Implicit Continuous-Time Survival Functions with Neural Networks
• RecNets: Channel-wise Recurrent Convolutional Neural Networks
• Using deep neural networks to improve the precision of fast-sampled particle timing detectors
• DVL Calibration using Data-driven Methods
• Towards Diverse Perspective Learning with Selection over Multiple Temporal Poolings
• Enhancing Rover Mobility Monitoring: Autoencoder-driven Anomaly Detection for Curiosity
• Role of Delay in Brain Dynamics
• Application of Graph Networks to a wide-field Water-Cherenkov-based Gamma-Ray Observatory
• Software implemented fault diagnosis of natural gas pumping unit based on feedforward neural network
• Automated ultrasound doppler angle estimation using deep learning
• Two Deep Learning Approaches for Automated Segmentation of Left Ventricle in Cine Cardiac MRI
• ThumbNet: One Thumbnail Image Contains All You Need for Recognition
• BILLNET: A Binarized Conv3D-LSTM Network with Logic-gated residual architecture for hardware-efficient video inference
• Automatic Grouping of Redundant Sensors and Actuators Using Functional and Spatial Connections: Application to Muscle Grouping for Musculoskeletal Humanoids
• Reducing Bias in Pre-trained Models by Tuning while Penalizing Change
• Novel View Synthesis of Humans using Differentiable Rendering
• Information Geometrically Generalized Covariate Shift Adaptation
• Real-Time Oil Leakage Detection on Aftermarket Motorcycle Damping System with Convolutional Neural Networks
• 3D Photo Stylization: Learning to Generate Stylized Novel Views from a Single Image
• Single-view 3D Body and Cloth Reconstruction under Complex Poses
• Importance Weighted Adversarial Discriminative Transfer for Anomaly Detection
• Rectangular Flows for Manifold Learning
• Tips and Tricks to Improve CNN-based Chest X-ray Diagnosis: A Survey
• NeuraCrypt: Hiding Private Health Data via Random Neural Networks for Public Training
• Ex uno plures: Splitting One Model into an Ensemble of Subnetworks
• Automatic CT Segmentation from Bounding Box Annotations using Convolutional Neural Networks
• Scaling-up Diverse Orthogonal Convolutional Networks with a Paraunitary Framework
• SE-MD: A Single-encoder multiple-decoder deep network for point cloud generation from 2D images
• Fast Adjustable Threshold For Uniform Neural Network Quantization (Winning solution of LPIRC-II)
• Cross-Modal Knowledge Distillation Method for Automatic Cued Speech Recognition
• PoliTO-IIT Submission to the EPIC-KITCHENS-100 Unsupervised Domain Adaptation Challenge for Action Recognition
• Learning to Find Correlated Features by Maximizing Information Flow in Convolutional Neural Networks
• EEG-ConvTransformer for Single-Trial EEG based Visual Stimuli Classification
• Meta-Optimization of Deep CNN for Image Denoising Using LSTM
• SA-GD: Improved Gradient Descent Learning Strategy with Simulated Annealing
• Speech Intention Understanding in a Head-final Language: A Disambiguation Utilizing Intonation-dependency
• Cycled Compositional Learning between Images and Text
• Semi-weakly Supervised Contrastive Representation Learning for Retinal Fundus Images
• Reconstructing a dynamical system and forecasting time series by self-consistent deep learning
• Rotaflip: A New CNN Layer for Regularization and Rotational Invariance in Medical Images
• CNN-based MultiChannel End-to-End Speech Recognition for everyday home environments
• On Procedural Adversarial Noise Attack And Defense
• Second-Order Neural ODE Optimizer
• Fine-grained Video Categorization with Redundancy Reduction Attention
• Machine learning moment closure models for the radiative transfer equation III: enforcing hyperbolicity and physical characteristic speeds
• An ETF view of Dropout regularization
• AdaPruner: Adaptive Channel Pruning and Effective Weights Inheritance
• Overfitting the Data: Compact Neural Video Delivery via Content-aware Feature Modulation
• Manifold-preserved GANs
• Scene Graph Generation for Better Image Captioning?
• Designing Counterfactual Generators using Deep Model Inversion
• LCS: Learning Compressible Subspaces for Adaptive Network Compression at Inference Time
• From Image to Imuge: Immunized Image Generation
• MisConv: Convolutional Neural Networks for Missing Data
• Arbitrary Marginal Neural Ratio Estimation for Simulation-based Inference
• MUFold-BetaTurn: A Deep Dense Inception Network for Protein Beta-Turn Prediction
• Decoupled Appearance and Motion Learning for Efficient Anomaly Detection in Surveillance Video
• Deep Data Flow Analysis
• MelGlow: Efficient Waveform Generative Network Based on Location-Variable Convolution
• Efficient Heuristic Generation for Robot Path Planning with Recurrent Generative Model
• Generative Learning With Euler Particle Transport
• Two at Once: Enhancing Learning and Generalization Capacities via IBN-Net
• Nested Named Entity Recognition with Partially-Observed TreeCRFs
• Learning based signal detection for MIMO systems with unknown noise statistics
• q-Neurons: Neuron Activations based on Stochastic Jackson's Derivative Operators
• Deep Neural Networks for Active Wave Breaking Classification
• Spatio-Temporal Channel Correlation Networks for Action Classification
• Intraclass clustering: an implicit learning ability that regularizes DNNs
• Pre-interpolation loss behaviour in neural networks
• BA^2M: A Batch Aware Attention Module for Image Classification
• Optimizer Fusion: Efficient Training with Better Locality and Parallelism
• Streaming Self-Training via Domain-Agnostic Unlabeled Images
• Sequential Learning for Domain Generalization
• Deep Homography Estimation for Dynamic Scenes
• Simulation-based Lidar Super-resolution for Ground Vehicles
• Improving correlation method with convolutional neural networks
• Residual Channel Attention Generative Adversarial Network for Image Super-Resolution and Noise Reduction
• Transfer Learning-Based Received Power Prediction with Ray-tracing Simulation and Small Amount of Measurement Data
• A Mixture of $h-1$ Heads is Better than $h$ Heads
• FA-GANs: Facial Attractiveness Enhancement with Generative Adversarial Networks on Frontal Faces
• Progressively Unfreezing Perceptual GAN
• ODE-CNN: Omnidirectional Depth Extension Networks
• Scalable Data Classification for Security and Privacy
• Tree-Augmented Cross-Modal Encoding for Complex-Query Video Retrieval
• Generalizing Tensor Decomposition for N-ary Relational Knowledge Bases
• Capturing scattered discriminative information using a deep architecture in acoustic scene classification
• SCNet: A Neural Network for Automated Side-Channel Attack
• Representative Graph Neural Network
• Yet Another Intermediate-Level Attack
• On Target Segmentation for Direct Speech Translation
• CLASS: Cross-Level Attention and Supervision for Salient Objects Detection
• Deep Eyes: Binocular Depth-from-Focus on Focal Stack Pairs
• Learning to Remember from a Multi-Task Teacher
• ReActNet: Temporal Localization of Repetitive Activities in Real-World Videos
• On Modelling Label Uncertainty in Deep Neural Networks: Automatic Estimation of Intra-observer Variability in 2D Echocardiography Quality Assessment
• MRNN: A Multi-Resolution Neural Network with Duplex Attention for Document Retrieval in the Context of Question Answering
• Likelihood Assignment for Out-of-Distribution Inputs in Deep Generative Models is Sensitive to Prior Distribution Choice
• AnoNet: Weakly Supervised Anomaly Detection in Textured Surfaces
• On the Bias-Variance Tradeoff: Textbooks Need an Update
• A Neural Network model with Bidirectional Whitening
• Transfer Learning in General Lensless Imaging through Scattering Media
• Lightweight 3D Human Pose Estimation Network Training Using Teacher-Student Learning
• Scalable and Practical Natural Gradient for Large-Scale Deep Learning
• Learning Identity Mappings with Residual Gates
• Intelligent Home 3D: Automatic 3D-House Design from Linguistic Descriptions Only
• Removal of Batch Effects using Generative Adversarial Networks
• Using fuzzy bits and neural networks to partially invert few rounds of some cryptographic hash functions
• Trajectory Normalized Gradients for Distributed Optimization
• A* Tree Search for Portfolio Management
• Learning to Modulate for Non-coherent MIMO
• Robust Super-Resolution GAN, with Manifold-based and Perception Loss
• Auto-Embedding Generative Adversarial Networks for High Resolution Image Synthesis
• Palmprint image registration using convolutional neural networks and Hough transform
• Skeleton-Based Online Action Prediction Using Scale Selection Network
• Graph Attribute Aggregation Network with Progressive Margin Folding
• What Do Adversarially Robust Models Look At?
• Channel Pruning via Optimal Thresholding
• Investigating the Compositional Structure Of Deep Neural Networks
• Blur, Noise, and Compression Robust Generative Adversarial Networks
• Regularized Evolutionary Population-Based Training
• Analysis of Hyper-Parameters for Small Games: Iterations or Epochs in Self-Play?
• On the effectiveness of convolutional autoencoders on image-based personalized recommender systems
• What Deep CNNs Benefit from Global Covariance Pooling: An Optimization Perspective
• Towards Sustainable Artificial Intelligence: A Comprehensive Review and Comparative Analysis of Deep Learning Models' Carbon Footprint
• Perceptual Attention-based Predictive Control
• Optimal message passing for molecular prediction is simple, attentive and spatial
• Performance of artificial neural networks in an inverse problem of laser beam diagnostics
• Deep Likelihood Network for Image Restoration with Multiple Degradation Levels
• Data-driven Weight Initialization with Sylvester Solvers
• Polygonal Unadjusted Langevin Algorithms: Creating stable and efficient adaptive algorithms for neural networks
• Temporal Network Representation Learning via Historical Neighborhoods Aggregation
• Exploring Autoencoder-based Error-bounded Compression for Scientific Data
• Egocentric Activity Recognition and Localization on a 3D Map
• CodedVO: Coded Visual Odometry
• Adaptive Region Embedding for Text Classification
• Multi-Task Learning for Front-End Text Processing in TTS
• Linearly Constrained Weights: Reducing Activation Shift for Faster Training of Neural Networks
• Object-Oriented Dynamics Learning through Multi-Level Abstraction
• Neural Loop Combiner: Neural Network Models for Assessing the Compatibility of Loops
• Unsupervised Visual Representation Learning by Online Constrained K-Means
• Benchmarking Local Robustness of High-Accuracy Binary Neural Networks for Enhanced Traffic Sign Recognition
• Multi-Task, Multi-Domain Deep Segmentation with Shared Representations and Contrastive Regularization for Sparse Pediatric Datasets
• Deep Neural Networks as Point Estimates for Deep Gaussian Processes
• Multi-stage domain adversarial style reconstruction for cytopathological image stain normalization
• GAN-based Intrinsic Exploration For Sample Efficient Reinforcement Learning
• Discrete Word Embedding for Logical Natural Language Understanding
• Fast and Efficient Scene Categorization for Autonomous Driving using VAEs
• Noether's Learning Dynamics: Role of Symmetry Breaking in Neural Networks
• Informative Sample-Aware Proxy for Deep Metric Learning
• Generating 2D and 3D Master Faces for Dictionary Attacks with a Network-Assisted Latent Space Evolution
• Contrastive Adaptive Propagation Graph Neural Networks for Efficient Graph Learning
• Deep End-to-End Alignment and Refinement for Time-of-Flight RGB-D Module
• Loss Landscape Dependent Self-Adjusting Learning Rates in Decentralized Stochastic Gradient Descent
• RED-NET: A Recursive Encoder-Decoder Network for Edge Detection
• Can AI Generate Love Advice?: Toward Neural Answer Generation for Non-Factoid Questions
• Is In-Domain Data Really Needed? A Pilot Study on Cross-Domain Calibration for Network Quantization
• Towards Object Detection from Motion
• Biologically Inspired Semantic Lateral Connectivity for Convolutional Neural Networks
• IDEAL: Independent Domain Embedding Augmentation Learning
• Multi Voxel-Point Neurons Convolution (MVPConv) for Fast and Accurate 3D Deep Learning
• Deep-learning based Tools for Automated Protocol Definition of Advanced Diagnostic Imaging Exams
• An Empirical Study on Regularization of Deep Neural Networks by Local Rademacher Complexity
• Coupled Generative Adversarial Network for Continuous Fine-grained Action Segmentation
• Estimating the Robustness of Classification Models by the Structure of the Learned Feature-Space
• Combinatorial Optimization for Panoptic Segmentation: A Fully Differentiable Approach
• Generative Adversarial Networks for Real-time Stability of Inverter-based Systems
• Dynamic Resolution Network
• Diverse and Styled Image Captioning Using SVD-Based Mixture of Recurrent Experts
• GMAIR: Unsupervised Object Detection Based on Spatial Attention and Gaussian Mixture
• LLM4Laser: Large Language Models Automate the Design of Lasers
• Boosting Invisible Higgs Searches by Tagging a Gluon Jet for Gluon Fusion Process
• PURS: Personalized Unexpected Recommender System for Improving User Satisfaction
• Deep Interaction between Masking and Mapping Targets for Single-Channel Speech Enhancement
• CProp: Adaptive Learning Rate Scaling from Past Gradient Conformity
• A Low-Compexity Deep Learning Framework For Acoustic Scene Classification
• Recomposing the Reinforcement Learning Building Blocks with Hypernetworks
• Mapping Motor Cortex Stimulation to Muscle Responses: A Deep Neural Network Modeling Approach
• Joint Learning of Portrait Intrinsic Decomposition and Relighting
• CoPE: Conditional image generation using Polynomial Expansions
• HyperNP: Interactive Visual Exploration of Multidimensional Projection Hyperparameters
• Fast and robust multiplane single molecule localization microscopy using deep neural network
• Basis-MelGAN: Efficient Neural Vocoder Based on Audio Decomposition
• Context-Gated Convolution
• Using Anomaly Feature Vectors for Detecting, Classifying and Warning of Outlier Adversarial Examples
• Optimizing the Whole-life Cost in End-to-end CNN Acceleration
• Coupled Recurrent Network (CRN)
• Fast Monte Carlo Dropout and Error Correction for Radio Transmitter Classification
• Multi-Task Audio Source Separation
• How Does BN Increase Collapsed Neural Network Filters?
• Separation of time scales and direct computation of weights in deep neural networks
• Self-supervised pre-training with acoustic configurations for replay spoofing detection
• StarEnhancer: Learning Real-Time and Style-Aware Image Enhancement
• Multi-Label Gold Asymmetric Loss Correction with Single-Label Regulators
• Accumulated Polar Feature-based Deep Learning for Efficient and Lightweight Automatic Modulation Classification with Channel Compensation Mechanism
• Variational Auto-Encoder Based Approximate Bayesian Computation Uncertian Inverse Method for Sheet Metal Forming Problem
• Multi-Level Attention Pooling for Graph Neural Networks: Unifying Graph Representations with Multiple Localities
• Rotational and Reflectional Equivariant Convolutional Neural Network for data-limited applications: Multiphase Flow demonstration
• BN-NAS: Neural Architecture Search with Batch Normalization
• Learning Maximally Predictive Prototypes in Multiple Instance Learning
• Unsupervised Domain Alignment to Mitigate Low Level Dataset Biases
• Small Object Detection Based on Modified FSSD and Model Compression
• Reducing Geographic Performance Differential for Face Recognition
• An Efficient Method of Training Small Models for Regression Problems with Knowledge Distillation
• Length Scale Control in Topology Optimization using Fourier Enhanced Neural Networks
• Reconstructing High-resolution Turbulent Flows Using Physics-Guided Neural Networks
• Convolutional Neural Network for emotion recognition to assist psychiatrists and psychologists during the COVID-19 pandemic: experts opinion
• Set Aggregation Network as a Trainable Pooling Layer
• Luminance Attentive Networks for HDR Image and Panorama Reconstruction
• Gradient-based Data Augmentation for Semi-Supervised Learning
• Joint Spatial and Layer Attention for Convolutional Networks
• Feature Correlation Aggregation: on the Path to Better Graph Neural Networks
• Differentiating through the Fréchet Mean
• Structure-aware scale-adaptive networks for cancer segmentation in whole-slide images
• Time-Distributed Feature Learning in Network Traffic Classification for Internet of Things
• The Elastic Lottery Ticket Hypothesis
• Video Temporal Relationship Mining for Data-Efficient Person Re-identification
• Deep Learning on Attributed Graphs: A Journey from Graphs to Their Embeddings and Back
• Imitating Deep Learning Dynamics via Locally Elastic Stochastic Differential Equations
• False Negative Distillation and Contrastive Learning for Personalized Outfit Recommendation
• Domain Adaptation on Semantic Segmentation with Separate Affine Transformation in Batch Normalization
• Perceptual Score: What Data Modalities Does Your Model Perceive?
• Dissecting Supervised Contrastive Learning
• Sparse Label Smoothing Regularization for Person Re-Identification
• 3D Human Pose Estimation with Siamese Equivariant Embedding
• Visualizing key features in X-ray images of epoxy resins for improved material classification using singular value decomposition of deep learning features
• The Uncanny Similarity of Recurrence and Depth
• Solving Traffic4Cast Competition with U-Net and Temporal Domain Adaptation
• Self-paced Data Augmentation for Training Neural Networks
• Automatic Whole-body Bone Age Assessment Using Deep Hierarchical Features
• Deep Learning Assisted mmWave Beam Prediction with Prior Low-frequency Information
• Wrapped Loss Function for Regularizing Nonconforming Residual Distributions
• Unsupervised Object Detection with LiDAR Clues
• Scribble-Supervised Semantic Segmentation by Random Walk on Neural Representation and Self-Supervision on Neural Eigenspace
• Multikernel activation functions: formulation and a case study
• Irregularly Tabulated MLP for Fast Point Feature Embedding
• Reducing Inference Latency with Concurrent Architectures for Image Recognition
• Channel Estimation for Large Intelligent Surface Aided MISO Communications: From LMMSE to Deep Learning Solutions
• Data-driven Accelerogram Synthesis using Deep Generative Models
• NeVer 2.0: Learning, Verification and Repair of Deep Neural Networks
• Batch Normalization with Enhanced Linear Transformation
• Resolution Switchable Networks for Runtime Efficient Image Recognition
• CT Image Enhancement Using Stacked Generative Adversarial Networks and Transfer Learning for Lesion Segmentation Improvement
• Trust-Region Algorithms for Training Responses: Machine Learning Methods Using Indefinite Hessian Approximations
• A Memory-Augmented Neural Network Model of Abstract Rule Learning
• Towards Recognizing New Semantic Concepts in New Visual Domains
• Image-Based Jet Analysis
• Knowledge Transfer Based Fine-grained Visual Classification
• Deep Unitary Convolutional Neural Networks
• Dual-CyCon Net: A Cycle Consistent Dual-Domain Convolutional Neural Network Framework for Detection of Partial Discharge
• Towards Fair Deep Anomaly Detection
• Take More Positives: An Empirical Study of Contrastive Learing in Unsupervised Person Re-Identification
• A New Benchmark and Progress Toward Improved Weakly Supervised Learning
• FOSNet: An End-to-End Trainable Deep Neural Network for Scene Recognition
• Speech Paralinguistic Approach for Detecting Dementia Using Gated Convolutional Neural Network
• A Capsule-unified Framework of Deep Neural Networks for Graphical Programming
• A Multilingual Encoding Method for Text Classification and Dialect Identification Using Convolutional Neural Network
• Rogue-Gym: A New Challenge for Generalization in Reinforcement Learning
• Deeply supervised UNet for semantic segmentation to assist dermatopathological assessment of Basal Cell Carcinoma (BCC)
• The Pitfall of More Powerful Autoencoders in Lidar-Based Navigation
• Sim2Real 3D Object Classification using Spherical Kernel Point Convolution and a Deep Center Voting Scheme
• Deep Learning Estimation of Absorbed Dose for Nuclear Medicine Diagnostics
• Preprint: Norm Loss: An efficient yet effective regularization method for deep neural networks
• GAN-based Pose-aware Regulation for Video-based Person Re-identification
• IMU-Assisted Learning of Single-View Rolling Shutter Correction
• Ro-SOS: Metric Expression Network (MEnet) for Robust Salient Object Segmentation
• Learning Instance-Aware Object Detection Using Determinantal Point Processes
• Machine learning based in situ quality estimation by molten pool condition-quality relations modeling using experimental data
• Graph Pruning for Model Compression
• SubSpectral Normalization for Neural Audio Data Processing
• Separating the Effects of Batch Normalization on CNN Training Speed and Stability Using Classical Adaptive Filter Theory
• Fully Convolutional Scene Graph Generation
• Explainability-aided Domain Generalization for Image Classification
• Invertible Image Signal Processing
• Decoupling Global and Local Representations via Invertible Generative Flows
• Post-Hoc Domain Adaptation via Guided Data Homogenization
• "BNN - BN = ?": Training Binary Neural Networks without Batch Normalization
• Context Prior for Scene Segmentation
• Sparse Perturbations for Improved Convergence in Stochastic Zeroth-Order Optimization
• Energy Predictive Models for Convolutional Neural Networks on Mobile Platforms
• Artificial Intelligence for Pediatric Ophthalmology
• Patch-level Neighborhood Interpolation: A General and Effective Graph-based Regularization Strategy
• Gated Texture CNN for Efficient and Configurable Image Denoising
• Weakly Supervised Training of Hierarchical Attention Networks for Speaker Identification
• Finet: Using Fine-grained Batch Normalization to Train Light-weight Neural Networks
• PyChain: A Fully Parallelized PyTorch Implementation of LF-MMI for End-to-End ASR
• Motion deblurring of faces
• Learning Various Length Dependence by Dual Recurrent Neural Networks
• A Chain Graph Interpretation of Real-World Neural Networks
• Split Slice Training Augmentation and Hyperparameter Tuning of RAKI Networks for Simultaneous Multi-Slice Reconstruction
• Factorized Neural Processes for Neural Processes: $K$-Shot Prediction of Neural Responses
• Cross-Correlated Attention Networks for Person Re-Identification
• Deeply Equal-Weighted Subset Portfolios
• Improving task-specific representation via 1M unlabelled images without any extra knowledge
• Deep Low-Shot Learning for Biological Image Classification and Visualization from Limited Training Samples
• Flexible Image Denoising with Multi-layer Conditional Feature Modulation
• Regularly Updated Deterministic Policy Gradient Algorithm
• Learning to Prune in Training via Dynamic Channel Propagation
• Adversarial Dropout for Recurrent Neural Networks
• Learning Discriminative Features Via Weights-biased Softmax Loss
• Uncertainty Quantification in Deep Residual Neural Networks
• Locality Guided Neural Networks for Explainable Artificial Intelligence
• Cross-scale Attention Model for Acoustic Event Classification
• 2nd Place Solution to ECCV 2020 VIPriors Object Detection Challenge
• Towards Hardware-Agnostic Gaze-Trackers
• DDR-ID: Dual Deep Reconstruction Networks Based Image Decomposition for Anomaly Detection
• Sound2Sight: Generating Visual Dynamics from Sound and Context
• Interpreting Spatially Infinite Generative Models
• On the Importance of Adaptive Data Collection for Extremely Imbalanced Pairwise Tasks
• Generative networks as inverse problems with fractional wavelet scattering networks
• Encrypted Speech Recognition using Deep Polynomial Networks
• Attention as Activation
• "Tom" pet robot applied to urban autism
• Hey Human, If your Facial Emotions are Uncertain, You Should Use Bayesian Neural Networks!
• Disentangled Representations for Domain-generalized Cardiac Segmentation
• ROI Regularization for Semi-supervised and Supervised Learning
• Fine-Grained Classroom Activity Detection from Audio with Neural Networks
• Don't ignore Dropout in Fully Convolutional Networks
• Effective Regularization Through Loss-Function Metalearning
• Fairness-aware Summarization for Justified Decision-Making
• Spectral Metric for Dataset Complexity Assessment
• Volume of hyperintense inflammation (VHI): a deep learning-enabled quantitative imaging biomarker of inflammation load in spondyloarthritis
• Seq-SetNet: Exploring Sequence Sets for Inferring Structures
• Orthonormal Product Quantization Network for Scalable Face Image Retrieval
• Neural Topic Modeling by Incorporating Document Relationship Graph
• An Introduction to Variational Inference
• Improving Network Slimming with Nonconvex Regularization
• Single Image Super-Resolution Using Lightweight CNN with Maxout Units
• Using convolutional neural networks for the classification of breast cancer images
• Numerical influence of ReLU'(0) on backpropagation
• A Self Validation Network for Object-Level Human Attention Estimation
• Towards Controllable and Personalized Review Generation
• Multirate Training of Neural Networks
• Continual Learning in Deep Networks: an Analysis of the Last Layer
• FOCUS: Familiar Objects in Common and Uncommon Settings
• Delving into VoxCeleb: environment invariant speaker recognition
• No-regret Non-convex Online Meta-Learning
• Learn Locally, Correct Globally: A Distributed Algorithm for Training Graph Neural Networks
• Arch-Net: Model Distillation for Architecture Agnostic Model Deployment
• ARCA23K: An audio dataset for investigating open-set label noise
• Graph Analysis and Graph Pooling in the Spatial Domain
• PANet: Perspective-Aware Network with Dynamic Receptive Fields and Self-Distilling Supervision for Crowd Counting
• Self-Distilled Self-Supervised Representation Learning
• Learning Combinatorial Node Labeling Algorithms
• Privileged Features Distillation at Taobao Recommendations
• Exploring Semantic Segmentation on the DCT Representation
• Global Pixel Transformers for Virtual Staining of Microscopy Images
• Many-to-Many Voice Conversion using Cycle-Consistent Variational Autoencoder with Multiple Decoders
• Supervized Segmentation with Graph-Structured Deep Metric Learning
• Leveraging Sequence Embedding and Convolutional Neural Network for Protein Function Prediction
• ALTIS: Modernizing GPGPU Benchmarking
• Tell-the-difference: Fine-grained Visual Descriptor via a Discriminating Referee
• Classifying Textual Data with Pre-trained Vision Models through Transfer Learning and Data Transformations
• Embedding Principle in Depth for the Loss Landscape Analysis of Deep Neural Networks
• A Procedural World Generation Framework for Systematic Evaluation of Continual Learning
• APNN-TC: Accelerating Arbitrary Precision Neural Networks on Ampere GPU Tensor Cores
• Deep Learning-Based MR Image Re-parameterization
• DeepInSAR: A Deep Learning Framework for SAR Interferometric Phase Restoration and Coherence Estimation
• Latent Space Arc Therapy Optimization
• CAMRI Loss: Improving Recall of a Specific Class without Sacrificing Accuracy
• Target-Oriented Deformation of Visual-Semantic Embedding Space
• Artificial ASMR: A Cyber-Psychological Approach
• Separate In Latent Space: Unsupervised Single Image Layer Separation
• Optimal Transport Based Generative Autoencoders
• Open-Set Face Identification on Few-Shot Gallery by Fine-Tuning
• Detection and classification of vocal productions in large scale audio recordings
• H-VECTORS: Utterance-level Speaker Embedding Using A Hierarchical Attention Model
• Cryo-forum: A framework for orientation recovery with uncertainty measure with the application in cryo-EM image analysis
• DeepFDR: A Deep Learning-based False Discovery Rate Control Method for Neuroimaging Data
• Differentiable Sorting Networks for Scalable Sorting and Ranking Supervision
• Connecting Graph Convolutional Networks and Graph-Regularized PCA
• Unsupervised End-to-End Training with a Self-Defined Target
• Solving deep-learning density functional theory via variational autoencoders
• Knowledge Representing: Efficient, Sparse Representation of Prior Knowledge for Knowledge Distillation
• Interaction Detection Between Vehicles and Vulnerable Road Users: A Deep Generative Approach with Attention
• A Multivariate Density Forecast Approach for Online Power System Security Assessment
• Sequence-Aware Factorization Machines for Temporal Predictive Analytics
• Connections Between Pairs of Filters Improve the Accuracy of Convolutional Neural Networks
• Input Invex Neural Network
• 3D attention mechanism for fine-grained classification of table tennis strokes using a Twin Spatio-Temporal Convolutional Neural Networks
• Combining Deep Transfer Learning with Signal-image Encoding for Multi-Modal Mental Wellbeing Classification
• Learning to Predict Ego-Vehicle Poses for Sampling-Based Nonholonomic Motion Planning
• Improving Shape Deformation in Unsupervised Image-to-Image Translation
• Neighbor Oblivious Learning (NObLe) for Device Localization and Tracking
• Play Fair: Frame Attributions in Video Models
• Regularizing Recurrent Neural Networks via Sequence Mixup
• Unveiling the Potential: Harnessing Deep Metric Learning to Circumvent Video Streaming Encryption
• Neural Bootstrapper
• Estimating the electrical power output of industrial devices with end-to-end time-series classification in the presence of label noise
• Learning Equivariant Representations
• Optical Wavelength Guided Self-Supervised Feature Learning For Galaxy Cluster Richness Estimate
• Deep Interactive Denoiser (DID) for X-Ray Computed Tomography
• Learning to see across Domains and Modalities
• Solving Inverse Problems for Spectral Energy Distributions with Deep Generative Networks
• 3D Scattering Tomography by Deep Learning with Architecture Tailored to Cloud Fields
• Topologically Densified Distributions
• PosNeg-Balanced Anchors with Aligned Features for Single-Shot Object Detection
• Graphs for deep learning representations
• Bi-stream Pose Guided Region Ensemble Network for Fingertip Localization from Stereo Images
• Automatic travel pattern extraction from visa page stamps using CNN models
• Veritatem Dies Aperit- Temporally Consistent Depth Prediction Enabled by a Multi-Task Geometric and Semantic Scene Understanding Approach
• STDI-Net: Spatial-Temporal Network with Dynamic Interval Mapping for Bike Sharing Demand Prediction
• Learning Local Feature Descriptor with Motion Attribute for Vision-based Localization
• Guidance Module Network for Video Captioning
• Improved Robustness of Vision Transformer via PreLayerNorm in Patch Embedding
• FTBNN: Rethinking Non-linearity for 1-bit CNNs and Going Beyond
• Hierarchical Recurrent Attention Networks for Structured Online Maps
• Direct Quantization for Training Highly Accurate Low Bit-width Deep Neural Networks
• Adaptive Weight Decay for Deep Neural Networks
• An End-to-End Text-independent Speaker Verification Framework with a Keyword Adversarial Network
• Generative Parameter Sampler For Scalable Uncertainty Quantification
• Uniform Sampling over Episode Difficulty
• BRIEF: Backward Reduction of CNNs with Information Flow Analysis
• Trimap-guided Feature Mining and Fusion Network for Natural Image Matting
• Multi-Adapter RGBT Tracking
• CNN with large memory layers
• BN-invariant sharpness regularizes the training model to better generalization
• Learning from Matured Dumb Teacher for Fine Generalization
• Semi Supervised Deep Quick Instance Detection and Segmentation
• Efficient Semantic Image Synthesis via Class-Adaptive Normalization
• Measurement of Hybrid Rocket Solid Fuel Regression Rate for a Slab Burner using Deep Learning
• Neural Network Training Techniques Regularize Optimization Trajectory: An Empirical Study
• Automatic brain tissue segmentation in fetal MRI using convolutional neural networks
• Interaction Graphs for Object Importance Estimation in On-road Driving Videos
• Improving Protein Gamma-Turn Prediction Using Inception Capsule Networks
• Edge-Labeling based Directed Gated Graph Network for Few-shot Learning
• Machine Learning based Soil VWC and Field Capacity Estimation Using Low Cost Sensors
• GIID-Net: Generalizable Image Inpainting Detection via Neural Architecture Search and Attention
• A Unified Light Framework for Real-time Fault Detection of Freight Train Images
• Investigating Memorability of Dynamic Media
• In-Loop Meta-Learning with Gradient-Alignment Reward
• Attribution Mask: Filtering Out Irrelevant Features By Recursively Focusing Attention on Inputs of DNNs
• Convolutional Normalization
• Introducing the DOME Activation Functions
• Regularization with Latent Space Virtual Adversarial Training
• Intelligent image synthesis to attack a segmentation CNN using adversarial learning
• A Neural Text-to-Speech Model Utilizing Broadcast Data Mixed with Background Music
• Real-time RGBD-based Extended Body Pose Estimation
• Noise Robust Generative Adversarial Networks
• An Ensemble with Shared Representations Based on Convolutional Networks for Continually Learning Facial Expressions
• Hierarchically Robust Representation Learning
• Predictive Process Model Monitoring using Recurrent Neural Networks
• Learning Mechanically Driven Emergent Behavior with Message Passing Neural Networks
• Learning to Represent and Predict Sets with Deep Neural Networks
• Patch-based Medical Image Segmentation using Matrix Product State Tensor Networks
• State-Aware Rate Adaptation for UAVs by Incorporating On-Board Sensors
• BitSplit-Net: Multi-bit Deep Neural Network with Bitwise Activation Function
• Generative Wind Power Curve Modeling Via Machine Vision: A Self-learning Deep Convolutional Network Based Method
• Space Time Recurrent Memory Network
• LEAN: graph-based pruning for convolutional neural networks by extracting longest chains
• ISyNet: Convolutional Neural Networks design for AI accelerator
• Semi-Supervised Learning for Lensed Quasar Detection
• Improved Deep Classwise Hashing With Centers Similarity Learning for Image Retrieval
• Almost Sure Asymptotic Freeness of Neural Network Jacobian with Orthogonal Weights
• New Perspective on Progressive GANs Distillation for One-class Novelty Detection
• Deep Label Fusion: A 3D End-to-End Hybrid Multi-Atlas Segmentation and Deep Learning Pipeline
• Metastatic Cancer Image Classification Based On Deep Learning Method
• Connecting Images through Time and Sources: Introducing Low-data, Heterogeneous Instance Retrieval
• Semantic Conditioned Dynamic Modulation for Temporal Sentence Grounding in Videos
• A Note on Knowledge Distillation Loss Function for Object Classification
• A Novel Sleep Stage Classification Using CNN Generated by an Efficient Neural Architecture Search with a New Data Processing Trick
• CalibDNN: Multimodal Sensor Calibration for Perception Using Deep Neural Networks
• Random matrices in service of ML footprint: ternary random features with no performance loss
• Picasso: A CUDA-based Library for Deep Learning over 3D Meshes
• Learning disentangled representation for classical models
• Speech Enhancement using Separable Polling Attention and Global Layer Normalization followed with PReLU
• Two-stage Discriminative Re-ranking for Large-scale Landmark Retrieval
• Fast and Flexible Image Blind Denoising via Competition of Experts
• SS-CADA: A Semi-Supervised Cross-Anatomy Domain Adaptation for Coronary Artery Segmentation
• Breaking the Conventional Forward-Backward Tie in Neural Networks: Activation Functions
• Bidirectional Multiscale Feature Aggregation for Speaker Verification
• Beyond Short Clips: End-to-End Video-Level Learning with Collaborative Memories
• Deep Learning for Constrained Utility Maximisation
• U-NetMN and SegNetMN: Modified U-Net and SegNet models for bimodal SAR image segmentation
• MuSLCAT: Multi-Scale Multi-Level Convolutional Attention Transformer for Discriminative Music Modeling on Raw Waveforms
• Quotient Network -- A Network Similar to ResNet but Learning Quotients
• Spatially Constrained Transformer with Efficient Global Relation Modelling for Spatio-Temporal Prediction
• Compression Method for Solar Polarization Spectra Collected from Hinode SOT/SP Observations
• Combining Diverse Feature Priors
• Decoupled Box Proposal and Featurization with Ultrafine-Grained Semantic Labels Improve Image Captioning and Visual Question Answering
• SERE: Exploring Feature Self-relation for Self-supervised Transformer
• Towards Data-Free Domain Generalization
• An Empirical Study of the Effects of Sample-Mixing Methods for Efficient Training of Generative Adversarial Networks
• Greedy Bayesian Posterior Approximation with Deep Ensembles
• Simpler Certified Radius Maximization by Propagating Covariances
• CelebHair: A New Large-Scale Dataset for Hairstyle Recommendation based on CelebA
• NePTuNe: Neural Powered Tucker Network for Knowledge Graph Completion
• Taco-VC: A Single Speaker Tacotron based Voice Conversion with Limited Data
• Applications of Machine Learning to Optimizing Polyolefin Manufacturing
• A Coarse-to-Fine Framework for Learned Color Enhancement with Non-Local Attention
• An Investigation into the Stochasticity of Batch Whitening
• Development of digitally obtainable 10-year risk scores for depression and anxiety in the general population
• Complete and separate: Conditional separation with missing target source attribute completion
• CASU2Net: Cascaded Unification Network by a Two-step Early Fusion for Fault Detection in Offshore Wind Turbines
• Are Nearby Neighbors Relatives?: Testing Deep Music Embeddings
• Link Prediction on N-ary Relational Data Based on Relatedness Evaluation
• VeriMedi: Pill Identification using Proxy-based Deep Metric Learning and Exact Solution
• Inductive biases and Self Supervised Learning in modelling a physical heating system
• Recurrent networks improve neural response prediction and provide insights into underlying cortical circuits
• Decision Propagation Networks for Image Classification
• Whitening and second order optimization both make information in the dataset unusable during training, and can reduce or prevent generalization
• LVIS: A Dataset for Large Vocabulary Instance Segmentation
• Sparsity-Probe: Analysis tool for Deep Learning Models
• Bayesian Recurrent Units and the Forward-Backward Algorithm
• Deep Neural Network Embeddings with Gating Mechanisms for Text-Independent Speaker Verification
• FFCNN: Fast FPGA based Acceleration for Convolution neural network inference
• Self-Improving Semantic Perception for Indoor Localisation
• Deep Multi-Kernel Convolutional LSTM Networks and an Attention-Based Mechanism for Videos
• Learning Deep Image Priors for Blind Image Denoising
• End-to-End Bengali Speech Recognition
• Equivariant Contrastive Learning
• Putting 3D Spatially Sparse Networks on a Diet
• PokeBNN: A Binary Pursuit of Lightweight Accuracy
• Instance-Level Meta Normalization
• On Large Batch Training and Sharp Minima: A Fokker-Planck Perspective
• Deep Virtual Networks for Memory Efficient Inference of Multiple Tasks
• Lattice Fusion Networks for Image Denoising
• Spectrum Attention Mechanism for Time Series Classification
• Docking-based Virtual Screening with Multi-Task Learning
• Learning in Sparse Rewards settings through Quality-Diversity algorithms
• Learning Quantized Neural Nets by Coarse Gradient Method for Non-linear Classification
• Deep Learning for CSI Feedback Based on Superimposed Coding
• Reinforced Temporal Attention and Split-Rate Transfer for Depth-Based Person Re-Identification
• Shakeout: A New Approach to Regularized Deep Neural Network Training
• Large-Scale Multi-Agent Deep FBSDEs
• Style-Restricted GAN: Multi-Modal Translation with Style Restriction Using Generative Adversarial Networks
• Occlusion-guided compact template learning for ensemble deep network-based pose-invariant face recognition
• Fine-grained Optimization of Deep Neural Networks
• Real-time People Tracking and Identification from Sparse mm-Wave Radar Point-clouds
• Performance Analysis of a Foreground Segmentation Neural Network Model
• Measuring Fine-Grained Domain Relevance of Terms: A Hierarchical Core-Fringe Approach
• CNN-based Steganalysis and Parametric Adversarial Embedding: a Game-Theoretic Framework
• Estimating air quality co-benefits of energy transition using machine learning
• Boosting Scene Character Recognition by Learning Canonical Forms of Glyphs
• Enhancing Resilience of Deep Learning Networks by Means of Transferable Adversaries
• NodeDrop: A Condition for Reducing Network Size without Effect on Output
• Double Descent Optimization Pattern and Aliasing: Caveats of Noisy Labels
• Equivariance-bridged SO(2)-Invariant Representation Learning using Graph Convolutional Network
• Physics-Aware Downsampling with Deep Learning for Scalable Flood Modeling
• Accumulative Poisoning Attacks on Real-time Data
• Cross Attention Network for Semantic Segmentation
• REVE: Regularizing Deep Learning with Variational Entropy Bound
• Tightening the Approximation Error of Adversarial Risk with Auto Loss Function Search
• Deeply Shared Filter Bases for Parameter-Efficient Convolutional Neural Networks
• What Else Can Fool Deep Learning? Addressing Color Constancy Errors on Deep Neural Network Performance
• Learning Multi-Object Symbols for Manipulation with Attentive Deep Effect Predictors
• DDLSTM: Dual-Domain LSTM for Cross-Dataset Action Recognition
• Neural Enhancement in Content Delivery Systems: The State-of-the-Art and Future Directions
• Regularization and Reparameterization Avoid Vanishing Gradients in Sigmoid-Type Networks
• SetGAN: Improving the stability and diversity of generative models through a permutation invariant architecture
• Hierarchical Graph-Convolutional Variational AutoEncoding for Generative Modelling of Human Motion
• Generalizing Emergent Communication
• Anomaly Detection for Solder Joints Using $\beta$-VAE
• Neural Approximation of an Auto-Regressive Process through Confidence Guided Sampling
• Accuracy Improvement for Fully Convolutional Networks via Selective Augmentation with Applications to Electrocardiogram Data
• Regularizing Neural Networks via Stochastic Branch Layers
• Attending Category Disentangled Global Context for Image Classification
• Learning Visual Voice Activity Detection with an Automatically Annotated Dataset
• Go Small and Similar: A Simple Output Decay Brings Better Performance
• Structure-Regularized Attention for Deformable Object Representation
• On-device Filtering of Social Media Images for Efficient Storage
• ShuffleBlock: Shuffle to Regularize Deep Convolutional Neural Networks
• Neural network emulator to constrain the high-$z$ IGM thermal state from Lyman-$\alpha$ forest flux auto-correlation function
• Deep Reinforcement Learning Models Predict Visual Responses in the Brain: A Preliminary Result
• Quantized Neural Networks via {-1, +1} Encoding Decomposition and Acceleration
• Unsupervised Deep Learning by Injecting Low-Rank and Sparse Priors
• Attention-based cross-modal fusion for audio-visual voice activity detection in musical video streams
• Competing Ratio Loss for Discriminative Multi-class Image Classification
• An Adaptive Empirical Bayesian Method for Sparse Deep Learning
• Group Whitening: Balancing Learning Efficiency and Representational Capacity
• Feature Completion for Occluded Person Re-Identification
• Surrogate-assisted Particle Swarm Optimisation for Evolving Variable-length Transferable Blocks for Image Classification
• Modeling Musical Structure with Artificial Neural Networks
• On Connections between Regularizations for Improving DNN Robustness
• Controlling Covariate Shift using Balanced Normalization of Weights
• Deep Anchored Convolutional Neural Networks
• CoopSubNet: Cooperating Subnetwork for Data-Driven Regularization of Deep Networks under Limited Training Budgets
• Dep-$L_0$: Improving $L_0$-based Network Sparsification via Dependency Modeling
• Reflection-based Word Attribute Transfer
• An Improving Framework of regularization for Network Compression
• Holistic and Comprehensive Annotation of Clinically Significant Findings on Diverse CT Images: Learning from Radiology Reports and Label Ontology
• Simple2Complex: Global Optimization by Gradient Descent
• An Efficient Agreement Mechanism in CapsNets By Pairwise Product
• Network Space Search for Pareto-Efficient Spaces
• Viscos Flows: Variational Schur Conditional Sampling With Normalizing Flows
• 3D Scene Parsing via Class-Wise Adaptation
• Exact Backpropagation in Binary Weighted Networks with Group Weight Transformations
• NP-DRAW: A Non-Parametric Structured Latent Variable Model for Image Generation
• VolNet: Estimating Human Body Part Volumes from a Single RGB Image
• Generalization by design: Shortcuts to Generalization in Deep Learning
• VAENAR-TTS: Variational Auto-Encoder based Non-AutoRegressive Text-to-Speech Synthesis
• Hyperparameter Optimization for Forecasting Stock Returns
• Mitigating Memorization in Sample Selection for Learning with Noisy Labels
• Unpaired Single-Image Depth Synthesis with cycle-consistent Wasserstein GANs
• Similarity Guided Deep Face Image Retrieval
• Generating Relevant Counter-Examples from a Positive Unlabeled Dataset for Image Classification
• Do We Need Sound for Sound Source Localization?
• Details Preserving Deep Collaborative Filtering-Based Method for Image Denoising
• Deep Learning generated observations of galaxy clusters from dark-matter-only simulations
• MODRL/D-EL: Multiobjective Deep Reinforcement Learning with Evolutionary Learning for Multiobjective Optimization
• Towards Lower-Dose PET using Physics-Based Uncertainty-Aware Multimodal Learning with Robustness to Out-of-Distribution Data
• NegDL: Privacy-Preserving Deep Learning Based on Negative Database
• Neutral pion reconstruction using machine learning in the MINERvA experiment at $⟨E_{\nu }⟩\sim 6$ GeV
• MIO : Mutual Information Optimization using Self-Supervised Binary Contrastive Learning
• External-Memory Networks for Low-Shot Learning of Targets in Forward-Looking-Sonar Imagery
• Single Channel Speech Enhancement Using Temporal Convolutional Recurrent Neural Networks
• Modeling Cross-view Interaction Consistency for Paired Egocentric Interaction Recognition
• Recognizing Emotions evoked by Movies using Multitask Learning
• Irregular Convolutional Auto-Encoder on Point Clouds
• From augmented microscopy to the topological transformer: a new approach in cell image analysis for Alzheimer's research
• Deep GAN-Based Cross-Spectral Cross-Resolution Iris Recognition
• Improving Neural Networks by Adopting Amplifying and Attenuating Neurons
• Volumetric Transformer Networks
• Multiple Code Hashing for Efficient Image Retrieval
• Kanerva++: extending The Kanerva Machine with differentiable, locally block allocated latent memory
• A Survey on Green Deep Learning
• Redesigning Fully Convolutional DenseUNets for Large Histopathology Images
• CAN: Composite Appearance Network for Person Tracking and How to Model Errors in a Tracking System
• Automatically identifying a mobile phone user's position within a vehicle
• Probabilistic bounds on neuron death in deep rectifier networks
• #StayHome or #Marathon? Social Media Enhanced Pandemic Surveillance on Spatial-temporal Dynamic Graphs
• Sequentially Aggregated Convolutional Networks
• Tensor Yard: One-Shot Algorithm of Hardware-Friendly Tensor-Train Decomposition for Convolutional Neural Networks
• ODE guided Neural Data Augmentation Techniques for Time Series Data and its Benefits on Robustness
• How well do U-Net-based segmentation trained on adult cardiac magnetic resonance imaging data generalise to rare congenital heart diseases for surgical planning?
• Iterative Training: Finding Binary Weight Deep Neural Networks with Layer Binarization
• Emulating ultrafast dissipative quantum dynamics with deep neural networks
• Identifying and Exploiting Structures for Reliable Deep Learning
• Machine Learning for CSI Recreation Based on Prior Knowledge
• Neural Wireframe Renderer: Learning Wireframe to Image Translations
• Pose-Guided Feature Learning with Knowledge Distillation for Occluded Person Re-Identification
• Learning Musical Relations using Gated Autoencoders
• Utilizing Complex-valued Network for Learning to Compare Image Patches
• Generating Videos of Zero-Shot Compositions of Actions and Objects
• Normalized Convolutional Neural Network
• A stepped sampling method for video detection using LSTM
• Characterizing and Improving the Robustness of Self-Supervised Learning through Background Augmentations
• Residual Continual Learning
• Distilling Visual Priors from Self-Supervised Learning
• Versatile Inverse Reinforcement Learning via Cumulative Rewards
• On-target Adaptation
• Generalization over different cellular automata rules learned by a deep feed-forward neural network
• Deep Photovoltaic Nowcasting
• Exploring the Vision Processing Unit as Co-processor for Inference
• Searching for TrioNet: Combining Convolution with Local and Global Self-Attention
• Learning Deep-Latent Hierarchies by Stacking Wasserstein Autoencoders
• Application of Video-to-Video Translation Networks to Computational Fluid Dynamics
• Nonlinearities in Steerable SO(2)-Equivariant CNNs
• Reliable Liver Fibrosis Assessment from Ultrasound using Global Hetero-Image Fusion and View-Specific Parameterization
• Covariate Shift in High-Dimensional Random Feature Regression
• SDCNet: Smoothed Dense-Convolution Network for Restoring Low-Dose Cerebral CT Perfusion
• Deep Controllable Backlight Dimming
• Improving Streaming Transformer Based ASR Under a Framework of Self-supervised Learning
• Adversarial Mixing Policy for Relaxing Locally Linear Constraints in Mixup
• Stochastic Function Norm Regularization of Deep Networks
• An Elementary Approach to Convergence Guarantees of Optimization Algorithms for Deep Networks
• Towards Earnings Call and Stock Price Movement
• PDFNet: Pointwise Dense Flow Network for Urban-Scene Segmentation
• DiverseNet: When One Right Answer is not Enough
• Detecting and Tracking Small Moving Objects in Wide Area Motion Imagery (WAMI) Using Convolutional Neural Networks (CNNs)
• Partial to Whole Knowledge Distillation: Progressive Distilling Decomposed Knowledge Boosts Student Better
• Langevin Cooling for Domain Translation
• Online trajectory recovery from offline handwritten Japanese kanji characters
• Automated airway segmentation by learning graphical structure
• Genome Variant Calling with a Deep Averaging Network
• Summarize and Search: Learning Consensus-aware Dynamic Convolution for Co-Saliency Detection
• Q-Net: A Quantitative Susceptibility Mapping-based Deep Neural Network for Differential Diagnosis of Brain Iron Deposition in Hemochromatosis
• Optimizing Neural Network for Computer Vision task in Edge Device
• Efficient Modelling Across Time of Human Actions and Interactions
• SAFE: Scale Aware Feature Encoder for Scene Text Recognition
• Rapid training of deep neural networks without skip connections or normalization layers using Deep Kernel Shaping
• Learning post-processing for QRS detection using Recurrent Neural Network
• Face Sketch Synthesis with Style Transfer using Pyramid Column Feature
• Space-Time-Separable Graph Convolutional Network for Pose Forecasting
• Meta-learning of Pooling Layers for Character Recognition
• Weight Evolution: Improving Deep Neural Networks Training through Evolving Inferior Weight Values
• Procrustes: a Dataflow and Accelerator for Sparse Deep Neural Network Training
• Hiding Images into Images with Real-world Robustness
• Deep Neural Networks with Short Circuits for Improved Gradient Learning
• Student Helping Teacher: Teacher Evolution via Self-Knowledge Distillation
• Extracting representations of cognition across neuroimaging studies improves brain decoding
• Text Steganalysis with Attentional LSTM-CNN
• Meta-Learning with Task-Adaptive Loss Function for Few-Shot Learning
• Multi-concept adversarial attacks
• Efficient Training Convolutional Neural Networks on Edge Devices with Gradient-pruned Sign-symmetric Feedback Alignment
• GTM: Gray Temporal Model for Video Recognition
• Rediscovering Deep Neural Networks Through Finite-State Distributions
• Domain Adaptation and Active Learning for Fine-Grained Recognition in the Field of Biodiversity
• CBP: Backpropagation with constraint on weight precision using a pseudo-Lagrange multiplier method
• Semi-Supervised Learning for Bone Mineral Density Estimation in Hip X-ray Images
• Quantal synaptic dilution enhances sparse encoding and dropout regularisation in deep networks
• BAMSProd: A Step towards Generalizing the Adaptive Optimization Methods to Deep Binary Model
• Deep Closed-Form Subspace Clustering
• Network Implosion: Effective Model Compression for ResNets via Static Layer Pruning and Retraining
• Audiovisual transfer learning for audio tagging and sound event detection
• Dirty Pixels: Towards End-to-End Image Processing and Perception
• Rotation Equivariant 3D Hand Mesh Generation from a Single RGB Image
• Regularising Deep Networks with Deep Generative Models
• Dynamic Parameterized Network for CTR Prediction
• Evaluation Function Approximation for Scrabble
• Disentangling Transfer and Interference in Multi-Domain Learning
• A Neural Frequency-Severity Model and Its Application to Insurance Claims
• Dense for the Price of Sparse: Improved Performance of Sparsely Initialized Networks via a Subspace Offset
• Deep Learning in Ultrasound Elastography Imaging
• Backtracking gradient descent method for general $C^1$ functions, with applications to Deep Learning
• Coarse-to-fine Optimization for Speech Enhancement
• Learning from Incomplete Features by Simultaneous Training of Neural Networks and Sparse Coding
• Learning Data-adaptive Nonparametric Kernels
• Template-Instance Loss for Offline Handwritten Chinese Character Recognition
• Decoupled Low-light Image Enhancement
• Conflicting Bundles: Adapting Architectures Towards the Improved Training of Deep Neural Networks
• Online Graph Dictionary Learning
• Automatic Segmentation, Localization, and Identification of Vertebrae in 3D CT Images Using Cascaded Convolutional Neural Networks
• Thick-Net: Parallel Network Structure for Sequential Modeling
• Sifting out the features by pruning: Are convolutional networks the winning lottery ticket of fully connected ones?
• Training BatchNorm Only in Neural Architecture Search and Beyond
• Leveraging Cross-Utterance Context For ASR Decoding
• Dense-Sparse Deep Convolutional Neural Networks Training for Image Denoising