Deep Residual Learning for Image Recognition
arXiv:1512.03385
Abstract
Deeper neural networks are more difficult to train. We present a residual learning framework to ease the training of networks that are substantially deeper than those used previously. We explicitly reformulate the layers as learning residual functions with reference to the layer inputs, instead of learning unreferenced functions. We provide comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth. On the ImageNet dataset we evaluate residual nets with a depth of up to 152 layers---8x deeper than VGG nets but still having lower complexity. An ensemble of these residual nets achieves 3.57% error on the ImageNet test set. This result won the 1st place on the ILSVRC 2015 classification task. We also present analysis on CIFAR-10 with 100 and 1000 layers. The depth of representations is of central importance for many visual recognition tasks. Solely due to our extremely deep representations, we obtain a 28% relative improvement on the COCO object detection dataset. Deep residual nets are foundations of our submissions to ILSVRC & COCO 2015 competitions, where we also won the 1st places on the tasks of ImageNet detection, ImageNet localization, COCO detection, and COCO segmentation.
arXiv commentTech report
References in corpus (11)
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- Improving neural networks by preventing co-adaptation of feature detectors
- Caffe: Convolutional Architecture for Fast Feature Embedding
- Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
- Training Very Deep Networks
- Deeply-Supervised Nets
- Exact solutions to the nonlinear dynamics of learning in deep linear neural networks
- On the Number of Linear Regions of Deep Neural Networks
- Highway Networks
- Object Detection Networks on Convolutional Feature Maps
Cited by in corpus (1532)
- A Survey on Deep Learning in Medical Image Analysis
- TensorFlow: A system for large-scale machine learning
- YOLOv3: An Incremental Improvement
- Convolutional Sequence to Sequence Learning
- Attention Mechanisms in Computer Vision: A Survey
- ResUNet-a: a deep learning framework for semantic segmentation of remotely sensed data
- Focal Loss for Dense Object Detection
- Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigence
- Mixed Precision Training
- Representation Learning on Graphs with Jumping Knowledge Networks
- YouTube-8M: A Large-Scale Video Classification Benchmark
- Contrastive Representation Learning: A Framework and Review
- Snorkel: Rapid Training Data Creation with Weak Supervision
- Searching for Activation Functions
- Efficient Neural Architecture Search via Parameter Sharing
- Fixed Point Quantization of Deep Convolutional Networks
- TernausNet: U-Net with VGG11 Encoder Pre-Trained on ImageNet for Image Segmentation
- AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty
- Achieving Human Parity on Automatic Chinese to English News Translation
- Deep Representation Learning with Part Loss for Person Re-Identification
- COVID-ResNet: A Deep Learning Framework for Screening of COVID19 from Radiographs
- From Perception to Decision: A Data-driven Approach to End-to-end Motion Planning for Autonomous Ground Robots
- Born Again Neural Networks
- Deformable Convolutional Networks
- Decomposing Motion and Content for Natural Video Sequence Prediction
- Improved Denoising Diffusion Probabilistic Models
- Deep Predictive Coding Networks for Video Prediction and Unsupervised Learning
- SphereFace: Deep Hypersphere Embedding for Face Recognition
- Multimodal Compact Bilinear Pooling for Visual Question Answering and Visual Grounding
- Modeling the Dynamics of PDE Systems with Physics-Constrained Deep Auto-Regressive Networks
- Like What You Like: Knowledge Distill via Neuron Selectivity Transfer
- The Microsoft 2016 Conversational Speech Recognition System
- A Fully Convolutional Neural Network for Cardiac Segmentation in Short-Axis MRI
- #Exploration: A Study of Count-Based Exploration for Deep Reinforcement Learning
- VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection
- Residual Attention Network for Image Classification
- Pyramid Scene Parsing Network
- Deep Roots: Improving CNN Efficiency with Hierarchical Filter Groups
- What makes ImageNet good for transfer learning?
- FusionNet: A deep fully residual convolutional neural network for image segmentation in connectomics
- LocalViT: Analyzing Locality in Vision Transformers
- End-to-End Learning of Geometry and Context for Deep Stereo Regression
- XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks
- CosFace: Large Margin Cosine Loss for Deep Face Recognition
- Real-time Hand Tracking under Occlusion from an Egocentric RGB-D Sensor
- Compact Convolutional Neural Networks for Classification of Asynchronous Steady-state Visual Evoked Potentials
- DeeperGCN: All You Need to Train Deeper GCNs
- Deep Learning for Physical Processes: Incorporating Prior Scientific Knowledge
- Lossy Image Compression with Compressive Autoencoders
- Deep Learning Enables Automatic Detection and Segmentation of Brain Metastases on Multi-Sequence MRI
- Face Mask Detection using Transfer Learning of InceptionV3
- Learning Spatio-Temporal Representation with Pseudo-3D Residual Networks
- Model compression via distillation and quantization
- Deep learning to achieve clinically applicable segmentation of head and neck anatomy for radiotherapy
- Var-CNN: A Data-Efficient Website Fingerprinting Attack Based on Deep Learning
- Residual Dense Network for Image Super-Resolution
- Tensor Comprehensions: Framework-Agnostic High-Performance Machine Learning Abstractions
- Learnable pooling with Context Gating for video classification
- Single Path One-Shot Neural Architecture Search with Uniform Sampling
- Wider or Deeper: Revisiting the ResNet Model for Visual Recognition
- Scalability in Perception for Autonomous Driving: Waymo Open Dataset
- Hierarchical Representations for Efficient Architecture Search
- Superhuman Accuracy on the SNEMI3D Connectomics Challenge
- Deep Transfer Learning for Person Re-identification
- Star-galaxy Classification Using Deep Convolutional Neural Networks
- A Closer Look at Spatiotemporal Convolutions for Action Recognition
- Semantic Instance Segmentation via Deep Metric Learning
- Rapid Prediction of Electron-Ionization Mass Spectrometry using Neural Networks
- You Only Look Twice: Rapid Multi-Scale Object Detection In Satellite Imagery
- Deep Spatio-Temporal Residual Networks for Citywide Crowd Flows Prediction
- Transparency by Design: Closing the Gap Between Performance and Interpretability in Visual Reasoning
- Deep Aesthetic Quality Assessment with Semantic Information
- Attention Enriched Deep Learning Model for Breast Tumor Segmentation in Ultrasound Images
- Sensor-based Gait Parameter Extraction with Deep Convolutional Neural Networks
- Removal of Batch Effects using Distribution-Matching Residual Networks
- Mitigating Adversarial Effects Through Randomization
- CMU DeepLens: Deep Learning For Automatic Image-based Galaxy-Galaxy Strong Lens Finding
- Harmonious Attention Network for Person Re-Identification
- Temporal 3D ConvNets: New Architecture and Transfer Learning for Video Classification
- Natural Adversarial Examples
- An Uncertainty-aware Transfer Learning-based Framework for Covid-19 Diagnosis
- WRPN: Wide Reduced-Precision Networks
- Fathom: Reference Workloads for Modern Deep Learning Methods
- Deformable ConvNets v2: More Deformable, Better Results
- Scaling Out-of-Distribution Detection for Real-World Settings
- Glitch Classification and Clustering for LIGO with Deep Transfer Learning
- Parallel-Data-Free Voice Conversion Using Cycle-Consistent Adversarial Networks
- Deep Transfer Learning: A new deep learning glitch classification method for advanced LIGO
- Pose Invariant Embedding for Deep Person Re-identification
- Dilated Residual Networks
- Classification of Urban Morphology with Deep Learning: Application on Urban Vitality
- CvT: Introducing Convolutions to Vision Transformers
- Zoneout: Regularizing RNNs by Randomly Preserving Hidden Activations
- Deep Learning Based Robot for Automatically Picking up Garbage on the Grass
- Visual Entailment: A Novel Task for Fine-Grained Image Understanding
- Identification of heavy, energetic, hadronically decaying particles using machine-learning techniques
- Intrinsic dimension of data representations in deep neural networks
- Cosmological constraints with deep learning from KiDS-450 weak lensing maps
- StegNet: Mega Image Steganography Capacity with Deep Convolutional Network
- Learning Sparse Neural Networks through Regularization
- MONAS: Multi-Objective Neural Architecture Search using Reinforcement Learning
- MDMMT: Multidomain Multimodal Transformer for Video Retrieval
- Examining the Impact of Blur on Recognition by Convolutional Networks
- No bad local minima: Data independent training error guarantees for multilayer neural networks
- Maximum Classifier Discrepancy for Unsupervised Domain Adaptation
- Bag of Tricks for Image Classification with Convolutional Neural Networks
- Spinal cord gray matter segmentation using deep dilated convolutions
- Machine Learning for the Zwicky Transient Facility
- Improvements to context based self-supervised learning
- Deep Learning for Automatic Pneumonia Detection
- Fast Bayesian Optimization of Machine Learning Hyperparameters on Large Datasets
- ImageNet pre-trained models with batch normalization
- An Empirical Model of Large-Batch Training
- Faster CryptoNets: Leveraging Sparsity for Real-World Encrypted Inference
- Multi-graph convolutional network for short-term passenger flow forecasting in urban rail transit
- Learning the PE Header, Malware Detection with Minimal Domain Knowledge
- Image Classification of Melanoma, Nevus and Seborrheic Keratosis by Deep Neural Network Ensemble
- ALWANN: Automatic Layer-Wise Approximation of Deep Neural Network Accelerators without Retraining
- R-C3D: Region Convolutional 3D Network for Temporal Activity Detection
- Beyond Face Rotation: Global and Local Perception GAN for Photorealistic and Identity Preserving Frontal View Synthesis
- SVDNet for Pedestrian Retrieval
- SCNN: An Accelerator for Compressed-sparse Convolutional Neural Networks
- BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation
- Compression Artifacts Removal Using Convolutional Neural Networks
- Neural Networks for Entity Matching: A Survey
- Swapout: Learning an ensemble of deep architectures
- Learning Robust and High-Precision Quantum Controls
- 2018 Robotic Scene Segmentation Challenge
- Deep learning predictions of galaxy merger stage and the importance of observational realism
- Adapting Mask-RCNN for Automatic Nucleus Segmentation
- Multi-scale fully convolutional neural networks for histopathology image segmentation: from nuclear aberrations to the global tissue architecture
- Amulet: Aggregating Multi-level Convolutional Features for Salient Object Detection
- Chemception: A Deep Neural Network with Minimal Chemistry Knowledge Matches the Performance of Expert-developed QSAR/QSPR Models
- Training with Quantization Noise for Extreme Model Compression
- Revisiting Deep Learning Models for Tabular Data
- Face Detection through Scale-Friendly Deep Convolutional Networks
- Train Sparsely, Generate Densely: Memory-efficient Unsupervised Training of High-resolution Temporal GAN
- DeeperCut: A Deeper, Stronger, and Faster Multi-Person Pose Estimation Model
- Multi-style Generative Network for Real-time Transfer
- Single-Shot Refinement Neural Network for Object Detection
- The Importance of Skip Connections in Biomedical Image Segmentation
- B-CNN: Branch Convolutional Neural Network for Hierarchical Classification
- Convolutional Neural Networks Applied to Neutrino Events in a Liquid Argon Time Projection Chamber
- Wavelet Convolutional Neural Networks
- Boosted EfficientNet: Detection of Lymph Node Metastases in Breast Cancer Using Convolutional Neural Network
- Machine learning assisted multiscale modeling of composite phase change materials for Li-ion batteries thermal management
- NSML: Meet the MLaaS platform with a real-world case study
- Benchmarking Neural Network Robustness to Common Corruptions and Surface Variations
- Adaptive Inference through Early-Exit Networks: Design, Challenges and Directions
- Re-ranking Person Re-identification with k-reciprocal Encoding
- Flow-Guided Feature Aggregation for Video Object Detection
- Relay: A New IR for Machine Learning Frameworks
- Do Deep Convolutional Nets Really Need to be Deep and Convolutional?
- ThiNet: A Filter Level Pruning Method for Deep Neural Network Compression
- Sharpness-Aware Minimization for Efficiently Improving Generalization
- DeepSense: A Unified Deep Learning Framework for Time-Series Mobile Sensing Data Processing
- Finding Strong Gravitational Lenses in the DESI DECam Legacy Survey
- SLEEPNET: Automated Sleep Staging System via Deep Learning
- CLIP-Art: Contrastive Pre-training for Fine-Grained Art Classification
- Circle Loss: A Unified Perspective of Pair Similarity Optimization
- Ristretto: Hardware-Oriented Approximation of Convolutional Neural Networks
- Frame- and Segment-Level Features and Candidate Pool Evaluation for Video Caption Generation
- What Do We Understand About Convolutional Networks?
- DeepCorn: A Semi-Supervised Deep Learning Method for High-Throughput Image-Based Corn Kernel Counting and Yield Estimation
- Retina U-Net: Embarrassingly Simple Exploitation of Segmentation Supervision for Medical Object Detection
- Rethinking ImageNet Pre-training
- Fast Online Object Tracking and Segmentation: A Unifying Approach
- Label-Only Membership Inference Attacks
- SCAN: Self-and-Collaborative Attention Network for Video Person Re-identification
- The Shattered Gradients Problem: If resnets are the answer, then what is the question?
- CondenseNet: An Efficient DenseNet using Learned Group Convolutions
- A simple yet effective baseline for 3d human pose estimation
- Weakly Supervised Medical Diagnosis and Localization from Multiple Resolutions
- Machine learning active-nematic hydrodynamics
- DSOD: Learning Deeply Supervised Object Detectors from Scratch
- DenResCov-19: A deep transfer learning network for robust automatic classification of COVID-19, pneumonia, and tuberculosis from X-rays
- Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering
- Beyond 512 Tokens: Siamese Multi-depth Transformer-based Hierarchical Encoder for Long-Form Document Matching
- Re-ID done right: towards good practices for person re-identification
- Learning Deep Context-aware Features over Body and Latent Parts for Person Re-identification
- Universal adversarial perturbations
- MAttNet: Modular Attention Network for Referring Expression Comprehension
- Learning a Discriminative Feature Network for Semantic Segmentation
- Towards Interpretable Deep Neural Networks by Leveraging Adversarial Examples
- Learning Longer-term Dependencies in RNNs with Auxiliary Losses
- Measuring the Algorithmic Efficiency of Neural Networks
- Sampling Matters in Deep Embedding Learning
- Predicting Lung Nodule Malignancies by Combining Deep Convolutional Neural Network and Handcrafted Features
- Deep Image Retrieval: Learning global representations for image search
- Recognizing Partial Biometric Patterns
- Peephole: Predicting Network Performance Before Training
- Autoregressive Convolutional Neural Networks for Asynchronous Time Series
- Deep Koalarization: Image Colorization using CNNs and Inception-ResNet-v2
- Learning Rich Features for Image Manipulation Detection
- Incorporating Symmetry into Deep Dynamics Models for Improved Generalization
- Generative Adversarial Residual Pairwise Networks for One Shot Learning
- ME R-CNN: Multi-Expert R-CNN for Object Detection
- Instance-aware Semantic Segmentation via Multi-task Network Cascades
- Orthographic Feature Transform for Monocular 3D Object Detection
- Interleaved Group Convolutions for Deep Neural Networks
- The Devil is in the Middle: Exploiting Mid-level Representations for Cross-Domain Instance Matching
- Dissecting the Graphcore IPU Architecture via Microbenchmarking
- Putting An End to End-to-End: Gradient-Isolated Learning of Representations
- Learning Spatio-Temporal Features with 3D Residual Networks for Action Recognition
- APE-GAN: Adversarial Perturbation Elimination with GAN
- New high-quality strong lens candidates with deep learning in the Kilo Degree Survey
- Efficient and Robust Parallel DNN Training through Model Parallelism on Multi-GPU Platform
- Preserving Semantic Relations for Zero-Shot Learning
- A Low Effort Approach to Structured CNN Design Using PCA
- Complex-YOLO: Real-time 3D Object Detection on Point Clouds
- Adversarial Complementary Learning for Weakly Supervised Object Localization
- GAN-based Virtual Re-Staining: A Promising Solution for Whole Slide Image Analysis
- Residual Connections Encourage Iterative Inference
- Image-Based Size Analysis of Agglomerated and Partially Sintered Particles via Convolutional Neural Networks
- Neural Message Passing with Edge Updates for Predicting Properties of Molecules and Materials
- Gated Siamese Convolutional Neural Network Architecture for Human Re-Identification
- Dynamic Few-Shot Visual Learning without Forgetting
- TDAN: Temporally Deformable Alignment Network for Video Super-Resolution
- UNIT-DDPM: UNpaired Image Translation with Denoising Diffusion Probabilistic Models
- Full Page Handwriting Recognition via Image to Sequence Extraction
- The unreasonable effectiveness of the forget gate
- Learning Deep Models for Face Anti-Spoofing: Binary or Auxiliary Supervision
- OpenEDS: Open Eye Dataset
- CNN-SLAM: Real-time dense monocular SLAM with learned depth prediction
- Illuminating Pedestrians via Simultaneous Detection & Segmentation
- Towards 3D Human Pose Estimation in the Wild: a Weakly-supervised Approach
- The One Hundred Layers Tiramisu: Fully Convolutional DenseNets for Semantic Segmentation
- EfficientPose: An efficient, accurate and scalable end-to-end 6D multi object pose estimation approach
- Discriminability objective for training descriptive captions
- Incorporating the Knowledge of Dermatologists to Convolutional Neural Networks for the Diagnosis of Skin Lesions
- CityPersons: A Diverse Dataset for Pedestrian Detection
- Semantic-aware Grad-GAN for Virtual-to-Real Urban Scene Adaption
- SPCANet: Stellar Parameters and Chemical Abundances Network for LAMOST-II Medium Resolution Survey
- AddNet: Deep Neural Networks Using FPGA-Optimized Multipliers
- Latent Weights Do Not Exist: Rethinking Binarized Neural Network Optimization
- Stacking-Based Deep Neural Network: Deep Analytic Network for Pattern Classification
- Co-training for Demographic Classification Using Deep Learning from Label Proportions
- Pyramid Stereo Matching Network
- Bilinear CNNs for Fine-grained Visual Recognition
- Low-Shot Learning from Imaginary Data
- Privacy-preserving Machine Learning through Data Obfuscation
- And the Bit Goes Down: Revisiting the Quantization of Neural Networks
- Improved Recurrent Neural Networks for Session-based Recommendations
- Person Search with Natural Language Description
- VideoLSTM Convolves, Attends and Flows for Action Recognition
- How Can We Be So Dense? The Benefits of Using Highly Sparse Representations
- Three-Dimensional Shapes of Spinning Helium Nanodroplets
- A Real-time Hand Gesture Recognition and Human-Computer Interaction System
- Deep Unsupervised Saliency Detection: A Multiple Noisy Labeling Perspective
- Intriguing Properties of Contrastive Losses
- Memory-Efficient Pipeline-Parallel DNN Training
- Deep Reinforcement Learning-based Image Captioning with Embedding Reward
- Semantic Tagging with Deep Residual Networks
- COVID-19 Monitoring System using Social Distancing and Face Mask Detection on Surveillance video datasets
- Visual Translation Embedding Network for Visual Relation Detection
- Learning Feature Pyramids for Human Pose Estimation
- Adversarial PoseNet: A Structure-aware Convolutional Network for Human Pose Estimation
- Cyclic Functional Mapping: Self-supervised correspondence between non-isometric deformable shapes
- CDC: Convolutional-De-Convolutional Networks for Precise Temporal Action Localization in Untrimmed Videos
- High-quality strong lens candidates in the final Kilo Degree survey footprint
- Detecting and Recognizing Human-Object Interactions
- Posterior Network: Uncertainty Estimation without OOD Samples via Density-Based Pseudo-Counts
- Strong lens systems search in the Dark Energy Survey using Convolutional Neural Networks
- TFPose: Direct Human Pose Estimation with Transformers
- Deep Transfer Learning for Star Cluster Classification: I. Application to the PHANGS-HST Survey
- Attack-Resistant Federated Learning with Residual-based Reweighting
- Improving Fast Segmentation With Teacher-student Learning
- FermiNets: Learning generative machines to generate efficient neural networks via generative synthesis
- Comparison of Batch Normalization and Weight Normalization Algorithms for the Large-scale Image Classification
- Morphological classification of galaxies with deep learning: comparing 3-way and 4-way CNNs
- Reducing Noise in GAN Training with Variance Reduced Extragradient
- Mosaic Flows: A Transferable Deep Learning Framework for Solving PDEs on Unseen Domains
- PointFusion: Deep Sensor Fusion for 3D Bounding Box Estimation
- Lets keep it simple, Using simple architectures to outperform deeper and more complex architectures
- Cascade Residual Learning: A Two-stage Convolutional Neural Network for Stereo Matching
- Square Kilometre Array Science Data Challenge 1: analysis and results
- Fast and Accurate Image Super-Resolution with Deep Laplacian Pyramid Networks
- DeepSource: Point Source Detection using Deep Learning
- Attentive Generative Adversarial Network for Raindrop Removal from a Single Image
- Deblending galaxy superpositions with branched generative adversarial networks
- DeepStreaks: identifying fast-moving objects in the Zwicky Transient Facility data with deep learning
- Image-Image Domain Adaptation with Preserved Self-Similarity and Domain-Dissimilarity for Person Re-identification
- Deep Variation-structured Reinforcement Learning for Visual Relationship and Attribute Detection
- A survey of biodiversity informatics: Concepts, practices, and challenges
- Stiffness: A New Perspective on Generalization in Neural Networks
- TIC 168789840: A Sextuply-Eclipsing Sextuple Star System
- Deep residual detection of radio frequency interference for FAST
- A volumetric deep Convolutional Neural Network for simulation of mock dark matter halo catalogues
- SS-CAM: Smoothed Score-CAM for Sharper Visual Feature Localization
- Probabilistic Simulation of Quantum Circuits with the Transformer
- Deep SCNN-based Real-time Object Detection for Self-driving Vehicles Using LiDAR Temporal Data
- PiCANet: Learning Pixel-wise Contextual Attention for Saliency Detection
- MoleculeNet: A Benchmark for Molecular Machine Learning
- Pix3D: Dataset and Methods for Single-Image 3D Shape Modeling
- Diversity Regularized Spatiotemporal Attention for Video-based Person Re-identification
- A Comparison of CNN-based Face and Head Detectors for Real-Time Video Surveillance Applications
- Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphs
- Boosting Adversarial Attacks with Momentum
- Emergent Translation in Multi-Agent Communication
- Generative Image Translation for Data Augmentation in Colorectal Histopathology Images
- MEC: Memory-efficient Convolution for Deep Neural Network
- Integrated Object Detection and Tracking with Tracklet-Conditioned Detection
- Large-Scale Image Retrieval with Attentive Deep Local Features
- Self-Supervision Closes the Gap Between Weak and Strong Supervision in Histology
- Deep Spatial Feature Reconstruction for Partial Person Re-identification: Alignment-Free Approach
- SegFlow: Joint Learning for Video Object Segmentation and Optical Flow
- AstroVaDEr: Astronomical Variational Deep Embedder for Unsupervised Morphological Classification of Galaxies and Synthetic Image Generation
- On the effectiveness of task granularity for transfer learning
- Efficient Sparse-Winograd Convolutional Neural Networks
- DeepMerge II: Building Robust Deep Learning Algorithms for Merging Galaxy Identification Across Domains
- WasteNet: Waste Classification at the Edge for Smart Bins
- Lorentz Boost Networks: Autonomous Physics-Inspired Feature Engineering
- Deep Learning at Scale for the Construction of Galaxy Catalogs in the Dark Energy Survey
- GResNet: Graph Residual Network for Reviving Deep GNNs from Suspended Animation
- Comprehensive analysis of a dense sample of FRB 121102 bursts
- CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning
- Optimized and autonomous machine learning framework for characterizing pores, particles, grains and grain boundaries in microstructural images
- Scalable Person Re-identification on Supervised Smoothed Manifold
- Dual Attention Networks for Multimodal Reasoning and Matching
- Characterising Bias in Compressed Models
- YouTube-BoundingBoxes: A Large High-Precision Human-Annotated Data Set for Object Detection in Video
- Neutrino interaction classification with a convolutional neural network in the DUNE far detector
- Stacked Generative Adversarial Networks
- Using convolutional neural networks to predict galaxy metallicity from three-color images
- CANet: Class-Agnostic Segmentation Networks with Iterative Refinement and Attentive Few-Shot Learning
- Word2VisualVec: Image and Video to Sentence Matching by Visual Feature Prediction
- Multiple Document Datasets Pre-training Improves Text Line Detection With Deep Neural Networks
- Convolutional Neural Nets in Chemical Engineering: Foundations, Computations, and Applications
- Towards an astronomical foundation model for stars with a Transformer-based model
- Cache Telepathy: Leveraging Shared Resource Attacks to Learn DNN Architectures
- EvalAI: Towards Better Evaluation Systems for AI Agents
- On the dissection of degenerate cosmologies with machine learning
- Deep Video Deblurring
- SpotTune: Transfer Learning through Adaptive Fine-tuning
- Learning deep structured active contours end-to-end
- Deep Discriminative Clustering Analysis
- On the Feasibility of Generic Deep Disaggregation for Single-Load Extraction
- Data Distillation: Towards Omni-Supervised Learning
- High Performance Zero-Memory Overhead Direct Convolutions
- Revisiting Video Saliency: A Large-scale Benchmark and a New Model
- Mobile Video Object Detection with Temporally-Aware Feature Maps
- A deep architecture for unified aesthetic prediction
- An Attention Free Transformer
- Priority-based Parameter Propagation for Distributed DNN Training
- Annotating Object Instances with a Polygon-RNN
- Incorporating External Knowledge to Answer Open-Domain Visual Questions with Dynamic Memory Networks
- Higher Order Recurrent Neural Networks
- From Lost to Found: Discover Missing UI Design Semantics through Recovering Missing Tags
- End-to-End Dense Video Captioning with Masked Transformer
- SafetyNet: Detecting and Rejecting Adversarial Examples Robustly
- Direct Detection of Dark Matter Substructure in Strong Lens Images with Convolutional Neural Networks
- Structured Attention Guided Convolutional Neural Fields for Monocular Depth Estimation
- Combining Background Subtraction Algorithms with Convolutional Neural Network
- BlockDrop: Dynamic Inference Paths in Residual Networks
- SCA-CNN: Spatial and Channel-wise Attention in Convolutional Networks for Image Captioning
- Ranked Reward: Enabling Self-Play Reinforcement Learning for Combinatorial Optimization
- Evaluating prose style transfer with the Bible
- Understanding the Disharmony between Dropout and Batch Normalization by Variance Shift
- Rethinking the Usage of Batch Normalization and Dropout in the Training of Deep Neural Networks
- DeepRecSys: A System for Optimizing End-To-End At-scale Neural Recommendation Inference
- Application of Decision Rules for Handling Class Imbalance in Semantic Segmentation
- Visual Features for Context-Aware Speech Recognition
- Patch-based Progressive 3D Point Set Upsampling
- Stealing Links from Graph Neural Networks
- PVN3D: A Deep Point-wise 3D Keypoints Voting Network for 6DoF Pose Estimation
- NASNet: A Neuron Attention Stage-by-Stage Net for Single Image Deraining
- Weakly- and Semi-Supervised Object Detection with Expectation-Maximization Algorithm
- Camera Style Adaptation for Person Re-identification
- MaskLab: Instance Segmentation by Refining Object Detection with Semantic and Direction Features
- Towards High Performance Video Object Detection for Mobiles
- Document AI: Benchmarks, Models and Applications
- Detecting Out-of-Distribution Inputs in Deep Neural Networks Using an Early-Layer Output
- DecomposeMe: Simplifying ConvNets for End-to-End Learning
- Max-Mahalanobis Linear Discriminant Analysis Networks
- Few Shot Speaker Recognition using Deep Neural Networks
- Selective Convolutional Descriptor Aggregation for Fine-Grained Image Retrieval
- Hex2vec -- Context-Aware Embedding H3 Hexagons with OpenStreetMap Tags
- Pulsar Candidate Identification Using Semi-Supervised Generative Adversarial Networks
- OctNet: Learning Deep 3D Representations at High Resolutions
- A Comprehensive Survey of Machine Learning Applied to Radar Signal Processing
- Deep Verifier Networks: Verification of Deep Discriminative Models with Deep Generative Models
- Deep Convolutional Neural Networks with Merge-and-Run Mappings
- Robust Quantization: One Model to Rule Them All
- Temporal Generative Adversarial Nets with Singular Value Clipping
- All You Need is Beyond a Good Init: Exploring Better Solution for Training Extremely Deep Convolutional Neural Networks with Orthonormality and Modulation
- SFD: Single Shot Scale-invariant Face Detector
- Oriented Response Networks
- An Interactive Data Visualization and Analytics Tool to Evaluate Mobility and Sociability Trends During COVID-19
- Zero-shot Knowledge Transfer via Adversarial Belief Matching
- Learning Better Features for Face Detection with Feature Fusion and Segmentation Supervision
- Zero-shot Recognition via Semantic Embeddings and Knowledge Graphs
- Deep Triplet Ranking Networks for One-Shot Recognition
- PDNet: Semantic Segmentation integrated with a Primal-Dual Network for Document binarization
- Concurrent Activity Recognition with Multimodal CNN-LSTM Structure
- Understanding Infographics through Textual and Visual Tag Prediction
- Learning Deep Neural Networks for Vehicle Re-ID with Visual-spatio-temporal Path Proposals
- Dice Loss for Data-imbalanced NLP Tasks
- Galaxy Morphology Classification using Neural Ordinary Differential Equations
- Convolutional Neural Pyramid for Image Processing
- Grouped Convolutional Neural Networks for Multivariate Time Series
- Quantifying Perceptual Distortion of Adversarial Examples
- Baryon acoustic oscillations reconstruction using convolutional neural networks
- Im2Avatar: Colorful 3D Reconstruction from a Single Image
- It Takes Two to Tango: Towards Theory of AI's Mind
- Maintaining Discrimination and Fairness in Class Incremental Learning
- Training Competitive Binary Neural Networks from Scratch
- Learning Deep ResNet Blocks Sequentially using Boosting Theory
- FibeR-CNN: Expanding Mask R-CNN to Improve Image-Based Fiber Analysis
- Neural ODE and Holographic QCD
- Speaking the Same Language: Matching Machine to Human Captions by Adversarial Training
- Show, Adapt and Tell: Adversarial Training of Cross-domain Image Captioner
- Sharing Residual Units Through Collective Tensor Factorization in Deep Neural Networks
- Reliable Probability Forecast of Solar Flares: Deep Flare Net-Reliable (DeFN-R)
- Using Deep Learning for Segmentation and Counting within Microscopy Data
- Supervision-by-Registration: An Unsupervised Approach to Improve the Precision of Facial Landmark Detectors
- Natural Environment Benchmarks for Reinforcement Learning
- Bright, Relatively Isolated Star Clusters in PHANGS-HST Galaxies: Aperture Corrections, Quantitative Morphologies, and Comparison with Synthetic Stellar Population Models
- Bayesian Stokes inversion with Normalizing flows
- Impression Network for Video Object Detection
- TinySpeech: Attention Condensers for Deep Speech Recognition Neural Networks on Edge Devices
- Efficient Continual Learning with Modular Networks and Task-Driven Priors
- Rethinking Class-Balanced Methods for Long-Tailed Visual Recognition from a Domain Adaptation Perspective
- Grappa -- A Machine Learned Molecular Mechanics Force Field
- Text as Neural Operator: Image Manipulation by Text Instruction
- Action Machine: Rethinking Action Recognition in Trimmed Videos
- SipMask: Spatial Information Preservation for Fast Image and Video Instance Segmentation
- Single Image Deraining using Scale-Aware Multi-Stage Recurrent Network
- MegDet: A Large Mini-Batch Object Detector
- Hyperparameter Optimization: A Spectral Approach
- Can Graph Neural Networks Count Substructures?
- Deep Pyramidal Residual Networks
- Well Googled is Half Done: Multimodal Forecasting of New Fashion Product Sales with Image-based Google Trends
- Contrastive Learning Inverts the Data Generating Process
- Deep learning enabled multi-wavelength spatial coherence microscope for the classification of malaria-infected stages with limited labelled data size
- TFLMS: Large Model Support in TensorFlow by Graph Rewriting
- 3D Human Pose Estimation with Relational Networks
- Siamese Cascaded Region Proposal Networks for Real-Time Visual Tracking
- Regularizing RNNs for Caption Generation by Reconstructing The Past with The Present
- What Do You See? Evaluation of Explainable Artificial Intelligence (XAI) Interpretability through Neural Backdoors
- High-Resolution Image Inpainting using Multi-Scale Neural Patch Synthesis
- COVID-19 Screening Using Residual Attention Network an Artificial Intelligence Approach
- Detecting Photoshopped Faces by Scripting Photoshop
- Fashion IQ: A New Dataset Towards Retrieving Images by Natural Language Feedback
- Weakly Supervised Dense Video Captioning
- Shared Data and Algorithms for Deep Learning in Fundamental Physics
- Wide Compression: Tensor Ring Nets
- ImageAssist: Tools for Enhancing Touchscreen-Based Image Exploration Systems for Blind and Low Vision Users
- Searches for Compact Binary Coalescence Events using Neural Networks in LIGO/Virgo Second Observation Period
- RankIQA: Learning from Rankings for No-reference Image Quality Assessment
- Iterative Visual Reasoning Beyond Convolutions
- DVQA: Understanding Data Visualizations via Question Answering
- Learning Affinity via Spatial Propagation Networks
- Effect of Annotation Errors on Drone Detection with YOLOv3
- Machine Learning in High Energy Physics: A review of heavy-flavor jet tagging at the LHC
- Pose-Invariant Face Alignment with a Single CNN
- Instance-level Human Parsing via Part Grouping Network
- How Does Batch Normalization Help Binary Training?
- Learning to Detect Human-Object Interactions
- How fine can fine-tuning be? Learning efficient language models
- Less Is More: Picking Informative Frames for Video Captioning
- Deep Back-Projection Networks For Super-Resolution
- Scribbler: Controlling Deep Image Synthesis with Sketch and Color
- Text Detection and Recognition in the Wild: A Review
- Interpolated Adversarial Training: Achieving Robust Neural Networks without Sacrificing Too Much Accuracy
- HARRISON: A Benchmark on HAshtag Recommendation for Real-world Images in Social Networks
- Quark-Gluon Jet Discrimination Using Convolutional Neural Networks
- Demonstration of background rejection using deep convolutional neural networks in the NEXT experiment
- Deep Learning for Identifying Iran's Cultural Heritage Buildings in Need of Conservation Using Image Classification and Grad-CAM
- Predictive Analysis of Diabetic Retinopathy with Transfer Learning
- Models Matter, So Does Training: An Empirical Study of CNNs for Optical Flow Estimation
- Player Identification in Hockey Broadcast Videos
- 3D-A-Nets: 3D Deep Dense Descriptor for Volumetric Shapes with Adversarial Networks
- Online Video Deblurring via Dynamic Temporal Blending Network
- Improving Multi-Modal Learning with Uni-Modal Teachers
- Image to Image Translation for Domain Adaptation
- Learning Dual Convolutional Neural Networks for Low-Level Vision
- A semi-supervised self-training method to develop assistive intelligence for segmenting multiclass bridge elements from inspection videos
- Person Search via A Mask-Guided Two-Stream CNN Model
- Abnormality Detection in Mammography using Deep Convolutional Neural Networks
- Towards Frequency-Based Explanation for Robust CNN
- Rethinking Feature Distribution for Loss Functions in Image Classification
- Estimating 6D Pose From Localizing Designated Surface Keypoints
- Not All Pixels Are Equal: Difficulty-aware Semantic Segmentation via Deep Layer Cascade
- Quantization for Rapid Deployment of Deep Neural Networks
- Jet-Parton Assignment in ttH Events using Deep Learning
- CASENet: Deep Category-Aware Semantic Edge Detection
- Significance-aware Information Bottleneck for Domain Adaptive Semantic Segmentation
- DenseNet Models for Tiny ImageNet Classification
- DDRprog: A CLEVR Differentiable Dynamic Reasoning Programmer
- Natural Language Guided Visual Relationship Detection
- Crowd counting via scale-adaptive convolutional neural network
- Interpretable Convolutional Neural Networks
- Acting Thoughts: Towards a Mobile Robotic Service Assistant for Users with Limited Communication Skills
- BlockCNN: A Deep Network for Artifact Removal and Image Compression
- ElephantBook: A Semi-Automated Human-in-the-Loop System for Elephant Re-Identification
- A Convolutional Neural Network For Cosmic String Detection in CMB Temperature Maps
- Motion-Appearance Co-Memory Networks for Video Question Answering
- From phonemes to images: levels of representation in a recurrent neural model of visually-grounded language learning
- Colorectal cancer diagnosis from histology images: A comparative study
- Learning efficient haptic shape exploration with a rigid tactile sensor array
- NeuPDE: Neural Network Based Ordinary and Partial Differential Equations for Modeling Time-Dependent Data
- Teaching Categories to Human Learners with Visual Explanations
- Improving Fully Convolution Network for Semantic Segmentation
- Polygonal Building Segmentation by Frame Field Learning
- Viewmaker Networks: Learning Views for Unsupervised Representation Learning
- Constrained Neural Ordinary Differential Equations with Stability Guarantees
- Real-Time Value-Driven Data Augmentation in the Era of LSST
- Video Captioning via Hierarchical Reinforcement Learning
- Deep Neural Network Architectures for Modulation Classification
- AdaptivFloat: A Floating-point based Data Type for Resilient Deep Learning Inference
- DCAN: Dual Channel-wise Alignment Networks for Unsupervised Scene Adaptation
- Task-driven Visual Saliency and Attention-based Visual Question Answering
- A Fast and Accurate One-Stage Approach to Visual Grounding
- Solar Image Restoration with the Cycle-GAN Based on Multi-Fractal Properties of Texture Features
- A convolutional neural network approach for reconstructing polarization information of photoelectric X-ray polarimeters
- Abdominal synthetic CT reconstruction with intensity projection prior for MRI-only adaptive radiotherapy
- Deep learning versus kernel learning: an empirical study of loss landscape geometry and the time evolution of the Neural Tangent Kernel
- Knowledge Concentration: Learning 100K Object Classifiers in a Single CNN
- SARM: Sparse Autoregressive Model for Scalable Generation of Sparse Images in Particle Physics
- From Patch to Image Segmentation using Fully Convolutional Networks -- Application to Retinal Images
- An Analysis of Visual Question Answering Algorithms
- Anatomy of Catastrophic Forgetting: Hidden Representations and Task Semantics
- Revisiting Model Stitching to Compare Neural Representations
- Situation Recognition with Graph Neural Networks
- Image Super-Resolution via Dual-State Recurrent Networks
- All Weather Perception: Joint Data Association, Tracking, and Classification for Autonomous Ground Vehicles
- Repulsion Loss: Detecting Pedestrians in a Crowd
- Practical Block-wise Neural Network Architecture Generation
- Cosine Normalization: Using Cosine Similarity Instead of Dot Product in Neural Networks
- Batch Kalman Normalization: Towards Training Deep Neural Networks with Micro-Batches
- Comparison of projection domain, image domain, and comprehensive deep learning for sparse-view X-ray CT image reconstruction
- Lattice Long Short-Term Memory for Human Action Recognition
- Weakly-supervised Visual Grounding of Phrases with Linguistic Structures
- SAUNet: Shape Attentive U-Net for Interpretable Medical Image Segmentation
- Network of Experts for Large-Scale Image Categorization
- Pneumothorax Segmentation: Deep Learning Image Segmentation to predict Pneumothorax
- Macroscale fracture surface segmentation via semi-supervised learning considering the structural similarity
- High-Resolution Multispectral Dataset for Semantic Segmentation
- Automated Quality Control of Vacuum Insulated Glazing by Convolutional Neural Network Image Classification
- Learning a Discriminative Prior for Blind Image Deblurring
- Pose-Robust Face Recognition via Deep Residual Equivariant Mapping
- An Accurate and Real-time Self-blast Glass Insulator Location Method Based On Faster R-CNN and U-net with Aerial Images
- Stable Tensor Neural Networks for Rapid Deep Learning
- PPR-FCN: Weakly Supervised Visual Relation Detection via Parallel Pairwise R-FCN
- Quantizing Convolutional Neural Networks for Low-Power High-Throughput Inference Engines
- A Closer Look at Local Aggregation Operators in Point Cloud Analysis
- MRI Tumor Segmentation with Densely Connected 3D CNN
- Q-CapsNets: A Specialized Framework for Quantizing Capsule Networks
- RUN:Residual U-Net for Computer-Aided Detection of Pulmonary Nodules without Candidate Selection
- Automatic localization and decoding of honeybee markers using deep convolutional neural networks
- Zero-Shot Visual Recognition using Semantics-Preserving Adversarial Embedding Networks
- Agile Amulet: Real-Time Salient Object Detection with Contextual Attention
- Multiple People Tracking Using Hierarchical Deep Tracklet Re-identification
- Knowledge Adaptation for Efficient Semantic Segmentation
- Mass Estimation of Galaxy Clusters with Deep Learning II: CMB Cluster Lensing
- All about Structure: Adapting Structural Information across Domains for Boosting Semantic Segmentation
- Suppressing the Unusual: towards Robust CNNs using Symmetric Activation Functions
- Comparison of Deep learning models on time series forecasting : a case study of Dissolved Oxygen Prediction
- Learning to Segment Instances in Videos with Spatial Propagation Network
- SemStyle: Learning to Generate Stylised Image Captions using Unaligned Text
- Using deep Residual Networks to search for galaxy-Lyα emitter lens candidates based on spectroscopic-selection
- Star Cluster Classification using Deep Transfer Learning with PHANGS-HST
- Take it in your stride: Do we need striding in CNNs?
- Sketch-R2CNN: An Attentive Network for Vector Sketch Recognition
- Learning Convolutional Networks for Content-weighted Image Compression
- Physical Accuracy of Deep Neural Networks for 2D and 3D Multi-Mineral Segmentation of Rock micro-CT Images
- Unsupervised Learning of Monocular Depth Estimation with Bundle Adjustment, Super-Resolution and Clip Loss
- A survey of Object Classification and Detection based on 2D/3D data
- End-to-end Concept Word Detection for Video Captioning, Retrieval, and Question Answering
- Learning Discriminative Motion Features Through Detection
- Consensus-based Sequence Training for Video Captioning
- Efficient Execution of Quantized Deep Learning Models: A Compiler Approach
- Tensorial Neural Networks: Generalization of Neural Networks and Application to Model Compression
- LabelBank: Revisiting Global Perspectives for Semantic Segmentation
- Robust Policies via Mid-Level Visual Representations: An Experimental Study in Manipulation and Navigation
- Unsupervised state representation learning with robotic priors: a robustness benchmark
- Semantic Compositional Networks for Visual Captioning
- PeerNets: Exploiting Peer Wisdom Against Adversarial Attacks
- Temporal Non-Volume Preserving Approach to Facial Age-Progression and Age-Invariant Face Recognition
- Stabilizing Gradients for Deep Neural Networks via Efficient SVD Parameterization
- Connecting optical morphology, environment, and HI mass fraction for low-redshift galaxies using deep learning
- Scene Graph Generation via Conditional Random Fields
- Towards Optimal Signal Extraction for Imaging X-ray Polarimetry
- A Pixel-Based Framework for Data-Driven Clothing
- Few-Shot Image Recognition by Predicting Parameters from Activations
- Characterizing and Improving Stability in Neural Style Transfer
- Personalized Federated Deep Learning for Pain Estimation From Face Images
- Improving Simple Models with Confidence Profiles
- Feature Enhancement Network: A Refined Scene Text Detector
- Optimized Custom Dataset for Efficient Detection of Underwater Trash
- Generating Descriptions with Grounded and Co-Referenced People
- Materials property prediction using symmetry-labeled graphs as atomic-position independent descriptors
- Doubly Attentive Transformer Machine Translation
- Appliance Detection Using Very Low-Frequency Smart Meter Time Series
- Where to Focus: Query Adaptive Matching for Instance Retrieval Using Convolutional Feature Maps
- Learning Digital Camera Pipeline for Extreme Low-Light Imaging
- Fast robust peg-in-hole insertion with continuous visual servoing
- Spec-ResNet: A General Audio Steganalysis scheme based on Deep Residual Network of Spectrogram
- Seeing Small Faces from Robust Anchor's Perspective
- Full-Resolution Residual Networks for Semantic Segmentation in Street Scenes
- The iNaturalist Species Classification and Detection Dataset
- Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervision
- Multi-Scale Deep Learning for Estimating Horizontal Velocity Fields on the Solar Surface
- Training Deeper Neural Machine Translation Models with Transparent Attention
- Astroconformer: The Prospects of Analyzing Stellar Light Curves with Transformer-Based Deep Learning Models
- An Attempt towards Interpretable Audio-Visual Video Captioning
- Learning to Evaluate Image Captioning
- Structured Binary Neural Networks for Accurate Image Classification and Semantic Segmentation
- Advancing Self-supervised Monocular Depth Learning with Sparse LiDAR
- Decoding Dark Matter Substructure without Supervision
- Skeleton Key: Image Captioning by Skeleton-Attribute Decomposition
- Graph-Based Global Reasoning Networks
- Breaking Batch Normalization for better explainability of Deep Neural Networks through Layer-wise Relevance Propagation
- Attend to the Difference: Cross-Modality Person Re-identification via Contrastive Correlation
- FacePoseNet: Making a Case for Landmark-Free Face Alignment
- Programmable Neural Network Trojan for Pre-Trained Feature Extractor
- Global Planar Convolutions for improved context aggregation in Brain Tumor Segmentation
- CTAP: Complementary Temporal Action Proposal Generation
- Measuring the Transferability of Adversarial Examples
- Art of singular vectors and universal adversarial perturbations
- Fusion++: Volumetric Object-Level SLAM
- Learning to Synthesize a 4D RGBD Light Field from a Single Image
- Single View Stereo Matching
- Large Scale Language Modeling: Converging on 40GB of Text in Four Hours
- Scene Parsing with Global Context Embedding
- KTAN: Knowledge Transfer Adversarial Network
- Instance Embedding Transfer to Unsupervised Video Object Segmentation
- Rafiki: Machine Learning as an Analytics Service System
- Learning to Segment Every Thing
- PlaneNet: Piece-wise Planar Reconstruction from a Single RGB Image
- S3K: Self-Supervised Semantic Keypoints for Robotic Manipulation via Multi-View Consistency
- Scalable inference with Autoregressive Neural Ratio Estimation
- A deep learning based solution for construction equipment detection: from development to deployment
- SuPer Deep: A Surgical Perception Framework for Robotic Tissue Manipulation using Deep Learning for Feature Extraction
- A Smartphone based Application for Skin Cancer Classification Using Deep Learning with Clinical Images and Lesion Information
- Adaptive Semantic Segmentation with a Strategic Curriculum of Proxy Labels
- EraseReLU: A Simple Way to Ease the Training of Deep Convolution Neural Networks
- Towards Generalizable Surgical Activity Recognition Using Spatial Temporal Graph Convolutional Networks
- Iris and periocular recognition in arabian race horses using deep convolutional neural networks
- Binary Ensemble Neural Network: More Bits per Network or More Networks per Bit?
- Recognition Of Surface Defects On Steel Sheet Using Transfer Learning
- A Read-Write Memory Network for Movie Story Understanding
- Rethinking Re-Sampling in Imbalanced Semi-Supervised Learning
- Convolutional Random Walk Networks for Semantic Image Segmentation
- Single-Shot Object Detection with Enriched Semantics
- RMM: A Recursive Mental Model for Dialog Navigation
- Deep Extreme Cut: From Extreme Points to Object Segmentation
- Set-valued classification -- overview via a unified framework
- Learning Visual Knowledge Memory Networks for Visual Question Answering
- Bayesian Inference with Generative Adversarial Network Priors
- 3DB: A Framework for Debugging Computer Vision Models
- Triple consistency loss for pairing distributions in GAN-based face synthesis
- Constrained CycleGAN for Effective Generation of Ultrasound Sector Images of Improved Spatial Resolution
- Privacy-Preserving Action Recognition for Smart Hospitals using Low-Resolution Depth Images
- Clickbait Identification using Neural Networks
- Deep Spatial Regression Model for Image Crowd Counting
- Focal Loss based Residual Convolutional Neural Network for Speech Emotion Recognition
- AdaStereo: A Simple and Efficient Approach for Adaptive Stereo Matching
- Unsupervised Learning from Continuous Video in a Scalable Predictive Recurrent Network
- Exploring the Design Space of Deep Convolutional Neural Networks at Large Scale
- Correlated and Individual Multi-Modal Deep Learning for RGB-D Object Recognition
- A Revisit on Deep Hashings for Large-scale Content Based Image Retrieval
- Fair Comparison: Quantifying Variance in Resultsfor Fine-grained Visual Categorization
- To Share or Not To Share: A Comprehensive Appraisal of Weight-Sharing
- Joint Prediction of Depths, Normals and Surface Curvature from RGB Images using CNNs
- AI-assisted super-resolution cosmological simulations III: Time evolution
- CNN-based Facial Affect Analysis on Mobile Devices
- On Periodic Functions as Regularizers for Quantization of Neural Networks
- Automatic Diagnosis of Pneumothorax from Chest Radiographs: A Systematic Literature Review
- Improved Part Segmentation Performance by Optimising Realism of Synthetic Images using Cycle Generative Adversarial Networks
- An Analysis of Scale Invariance in Object Detection - SNIP
- An Empirical Analysis of the Impact of Data Augmentation on Knowledge Distillation
- PolyTransform: Deep Polygon Transformer for Instance Segmentation
- Understanding Traffic Density from Large-Scale Web Camera Data
- Tell-and-Answer: Towards Explainable Visual Question Answering using Attributes and Captions
- Tails: Chasing Comets with the Zwicky Transient Facility and Deep Learning
- Learning to Extract a Video Sequence from a Single Motion-Blurred Image
- ML-LBM: Machine Learning Aided Flow Simulation in Porous Media
- Prototype-based Neural Network Layers: Incorporating Vector Quantization
- ScaleNet: Guiding Object Proposal Generation in Supermarkets and Beyond
- Dynamic backdoor attacks against federated learning
- NILMFormer: Non-Intrusive Load Monitoring that Accounts for Non-Stationarity
- Spectral Feature Transformation for Person Re-identification
- Noise2Void - Learning Denoising from Single Noisy Images
- Vision Xformers: Efficient Attention for Image Classification
- Learning Shape Priors for Single-View 3D Completion and Reconstruction
- UTRNet: High-Resolution Urdu Text Recognition In Printed Documents
- TAFE-Net: Task-Aware Feature Embeddings for Low Shot Learning
- A Multimodal Late Fusion Model for E-Commerce Product Classification
- Image-based localization using LSTMs for structured feature correlation
- Deep learning the astrometric signature of dark matter substructure
- LCNN: Lookup-based Convolutional Neural Network
- Semi-Supervised Multitask Learning on Multispectral Satellite Images Using Wasserstein Generative Adversarial Networks (GANs) for Predicting Poverty
- CROSSBOW: Scaling Deep Learning with Small Batch Sizes on Multi-GPU Servers
- Reconstruction of IACT events using deep learning techniques with CTLearn
- Multi-scale Location-aware Kernel Representation for Object Detection
- Artificial Intelligence Assisted Inversion (AIAI) of Synthetic Type Ia Supernova Spectra
- Learning to Navigate Using Mid-Level Visual Priors
- Skip-Clip: Self-Supervised Spatiotemporal Representation Learning by Future Clip Order Ranking
- Regressing Robust and Discriminative 3D Morphable Models with a very Deep Neural Network
- Modularized Morphing of Neural Networks
- Deep Heterogeneous Feature Fusion for Template-Based Face Recognition
- Attend and Interact: Higher-Order Object Interactions for Video Understanding
- Relation Networks for Optic Disc and Fovea Localization in Retinal Images
- CNN-based event classification for alpha-decay events in nuclear emulsion
- Fast, Exact and Multi-Scale Inference for Semantic Image Segmentation with Deep Gaussian CRFs
- Training with the Invisibles: Obfuscating Images to Share Safely for Learning Visual Recognition Models
- Underwater object detection using Invert Multi-Class Adaboost with deep learning
- Single-Shot Bidirectional Pyramid Networks for High-Quality Object Detection
- OffRoadTranSeg: Semi-Supervised Segmentation using Transformers on OffRoad environments
- VIPriors 1: Visual Inductive Priors for Data-Efficient Deep Learning Challenges
- InverseFaceNet: Deep Monocular Inverse Face Rendering
- Towards Robust RGB-D Human Mesh Recovery
- Deep learning for detection of bird vocalisations
- cGANs with Multi-Hinge Loss
- Deep Restricted Boltzmann Networks
- Spatial-Temporal Self-Attention Network for Flow Prediction
- Combining Image Features and Patient Metadata to Enhance Transfer Learning
- Eformer: Edge Enhancement based Transformer for Medical Image Denoising
- Pointwise Convolutional Neural Networks
- DSAC - Differentiable RANSAC for Camera Localization
- Weakly Supervised Attention Model for RV StrainClassification from volumetric CTPA Scans
- SRN: Side-output Residual Network for Object Symmetry Detection in the Wild
- DA-GAN: Instance-level Image Translation by Deep Attention Generative Adversarial Networks (with Supplementary Materials)
- Detection of Einstein Telescope gravitational wave signals from binary black holes using deep learning
- LightTrack: A Generic Framework for Online Top-Down Human Pose Tracking
- Iterative Deep Learning for Network Topology Extraction
- AdvGAN++ : Harnessing latent layers for adversary generation
- Real-Time High-Resolution Background Matting
- Graph neural network for 3D classification of ambiguities and optical crosstalk in scintillator-based neutrino detectors
- Coordinating Filters for Faster Deep Neural Networks
- Generative Partition Networks for Multi-Person Pose Estimation
- Label-Driven Reconstruction for Domain Adaptation in Semantic Segmentation
- An End-to-End Approach to Natural Language Object Retrieval via Context-Aware Deep Reinforcement Learning
- Weakly-Supervised 3D Pose Estimation from a Single Image using Multi-View Consistency
- Improved Stereo Matching with Constant Highway Networks and Reflective Confidence Learning
- Signal Combination for Language Identification
- Scaling GRPC Tensorflow on 512 nodes of Cori Supercomputer
- Deep Texture Manifold for Ground Terrain Recognition
- NLP-CUET@DravidianLangTech-EACL2021: Investigating Visual and Textual Features to Identify Trolls from Multimodal Social Media Memes
- An Efficient Transformer Decoder with Compressed Sub-layers
- Recurrent Localization Networks applied to the Lippmann-Schwinger Equation
- Compiling Deep Learning Models for Custom Hardware Accelerators
- Neural networks with differentiable structure
- Joint Pruning & Quantization for Extremely Sparse Neural Networks
- Weak-lensing Mass Reconstruction of Galaxy Clusters with Convolutional Neural Network
- PhishGAN: Data Augmentation and Identification of Homoglpyh Attacks
- Turning a Blind Eye: Explicit Removal of Biases and Variation from Deep Neural Network Embeddings
- Domain Alignment with Triplets
- Towards recognizing the light facet of the Higgs Boson
- How To Extract Fashion Trends From Social Media? A Robust Object Detector With Support For Unsupervised Learning
- Reconstruction of 3-D Atomic Distortions from Electron Microscopy with Deep Learning
- Robust Processing-In-Memory Neural Networks via Noise-Aware Normalization
- Gradient Scheduling with Global Momentum for Non-IID Data Distributed Asynchronous Training
- TIRAMISU: A Polyhedral Compiler for Dense and Sparse Deep Learning
- A Generalised Signature Method for Multivariate Time Series Feature Extraction
- Occupancy Map Prediction Using Generative and Fully Convolutional Networks for Vehicle Navigation
- Dual Path Networks for Multi-Person Human Pose Estimation
- MHP-VOS: Multiple Hypotheses Propagation for Video Object Segmentation
- SAWNet: A Spatially Aware Deep Neural Network for 3D Point Cloud Processing
- Reducing Uncertainty in Undersampled MRI Reconstruction with Active Acquisition
- Pose Guided Human Video Generation
- Holistic Interstitial Lung Disease Detection using Deep Convolutional Neural Networks: Multi-label Learning and Unordered Pooling
- Autonomous Deep Learning: A Genetic DCNN Designer for Image Classification
- Recurrent Filter Learning for Visual Tracking
- OrigamiNet: Weakly-Supervised, Segmentation-Free, One-Step, Full Page Text Recognition by learning to unfold
- FairyTailor: A Multimodal Generative Framework for Storytelling
- RarePlanes: Synthetic Data Takes Flight
- Fetal Gender Identification using Machine and Deep Learning Algorithms on Phonocardiogram Signals
- DocVQA: A Dataset for VQA on Document Images
- Shape-from-Mask: A Deep Learning Based Human Body Shape Reconstruction from Binary Mask Images
- Deep Feature Flow for Video Recognition
- Self-Supervised Feature Learning by Learning to Spot Artifacts
- Geometric robustness of deep networks: analysis and improvement
- Context-Aware Visual Compatibility Prediction
- Image segmentation via Cellular Automata
- DeepDeblur: Fast one-step blurry face images restoration
- Exploring Corruption Robustness: Inductive Biases in Vision Transformers and MLP-Mixers
- 3D Reconstruction in Canonical Co-ordinate Space from Arbitrarily Oriented 2D Images
- Channel-wise Hessian Aware trace-Weighted Quantization of Neural Networks
- OCoR: An Overlapping-Aware Code Retriever
- Semi-supervised Domain Adaptation based on Dual-level Domain Mixing for Semantic Segmentation
- Optimization Algorithm Inspired Deep Neural Network Structure Design
- Comprehensive Evaluation of OpenCL-based Convolutional Neural Network Accelerators in Xilinx and Altera FPGAs
- An Empirical Exploration of Skip Connections for Sequential Tagging
- Incremental Sequence Learning
- An LSTM-Based Dynamic Customer Model for Fashion Recommendation
- Adaptive Feeding: Achieving Fast and Accurate Detections by Adaptively Combining Object Detectors
- ActionFlowNet: Learning Motion Representation for Action Recognition
- EC-GAN: Low-Sample Classification using Semi-Supervised Algorithms and GANs
- Initialization Matters: Regularizing Manifold-informed Initialization for Neural Recommendation Systems
- 2D Image Relighting with Image-to-Image Translation
- Evaluating Transfer Learning for Simplifying GitHub READMEs
- Semantic Segmentation for Partially Occluded Apple Trees Based on Deep Learning
- A Continuous Convolutional Trainable Filter for Modelling Unstructured Data
- Optimization of Artificial Neural Networks models applied to the identification of images of asteroids' resonant arguments
- Learning a Discriminative Filter Bank within a CNN for Fine-grained Recognition
- Deep Learning applied to Road Traffic Speed forecasting
- Learning Visual Question Answering by Bootstrapping Hard Attention
- A Simple Loss Function for Improving the Convergence and Accuracy of Visual Question Answering Models
- FireNet: Real-time Segmentation of Fire Perimeter from Aerial Video
- Dual ResGCN for Balanced Scene GraphGeneration
- Detecting Cyberattacks in Industrial Control Systems Using Convolutional Neural Networks
- A deep learning theory for neural networks grounded in physics
- Orders-of-magnitude speedup in atmospheric chemistry modeling through neural network-based emulation
- Benanza: Automatic Benchmark Generation to Compute "Lower-bound" Latency and Inform Optimizations of Deep Learning Models on GPUs
- Self-Supervised Relative Depth Learning for Urban Scene Understanding
- Efficient Palm-Line Segmentation with U-Net Context Fusion Module
- Gated Context Model with Embedded Priors for Deep Image Compression
- Conditional Extreme Value Theory for Open Set Video Domain Adaptation
- Efficient Coarse-to-Fine Non-Local Module for the Detection of Small Objects
- Timage -- A Robust Time Series Classification Pipeline
- Aesthetic-Driven Image Enhancement by Adversarial Learning
- Super-Resolution with Deep Adaptive Image Resampling
- Transformable Bottleneck Networks
- Scalable, End-to-End, Deep-Learning-Based Data Reconstruction Chain for Particle Imaging Detectors
- SCREENet: A Multi-view Deep Convolutional Neural Network for Classification of High-resolution Synthetic Mammographic Screening Scans
- Evaluating Soccer Player: from Live Camera to Deep Reinforcement Learning
- Learning Representations of Sets through Optimized Permutations
- Weaving Multi-scale Context for Single Shot Detector
- Federated Noisy Client Learning
- COVID-19 Detection in Chest X-ray Images Using Swin-Transformer and Transformer in Transformer
- Knowledge-based Radiation Treatment Planning: A Data-driven Method Survey
- Deep learning for semantic segmentation of remote sensing images with rich spectral content
- A Simple Cache Model for Image Recognition
- Building Emotional Machines: Recognizing Image Emotions through Deep Neural Networks
- Foreground Removal of CO Intensity Mapping Using Deep Learning
- Transform and Tell: Entity-Aware News Image Captioning
- Re-identification = Retrieval + Verification: Back to Essence and Forward with a New Metric
- TOM-Net: Learning Transparent Object Matting from a Single Image
- Unsupervised Single Image Deraining with Self-supervised Constraints
- Training Neural Networks by Using Power Linear Units (PoLUs)
- Character-based NMT with Transformer
- Advances in Asynchronous Parallel and Distributed Optimization
- Question Type Guided Attention in Visual Question Answering
- Wise-SrNet: A Novel Architecture for Enhancing Image Classification by Learning Spatial Resolution of Feature Maps
- Lightweight Convolutional Representations for On-Device Natural Language Processing
- Multimodal Memory Modelling for Video Captioning
- FOTS: Fast Oriented Text Spotting with a Unified Network
- SketchParse : Towards Rich Descriptions for Poorly Drawn Sketches using Multi-Task Hierarchical Deep Networks
- Soft Calibration Objectives for Neural Networks
- A(DP)SGD: Asynchronous Decentralized Parallel Stochastic Gradient Descent with Differential Privacy
- Learning to Learn from Noisy Web Videos
- A Generalized Network for MRI Intensity Normalization
- Deep Class Aware Denoising
- Deep Quantization: Encoding Convolutional Activations with Deep Generative Model
- Convolutional Regression for Visual Tracking
- Dense Recurrent Neural Networks for Scene Labeling
- Deep Blind Image Inpainting
- Dual-Glance Model for Deciphering Social Relationships
- Transfer entropy-based feedback improves performance in artificial neural networks
- LaSO: Label-Set Operations networks for multi-label few-shot learning
- Training Keyword Spotters with Limited and Synthesized Speech Data
- Neither Private Nor Fair: Impact of Data Imbalance on Utility and Fairness in Differential Privacy
- Can we cover navigational perception needs of the visually impaired by panoptic segmentation?
- ResFPN: Residual Skip Connections in Multi-Resolution Feature Pyramid Networks for Accurate Dense Pixel Matching
- Railway Anomaly detection model using synthetic defect images generated by CycleGAN
- Automatic Liver Segmentation from CT Images Using Deep Learning Algorithms: A Comparative Study
- DAF:re: A Challenging, Crowd-Sourced, Large-Scale, Long-Tailed Dataset For Anime Character Recognition
- Privacy-preserving medical image analysis
- Cosmic Background Removal with Deep Neural Networks in SBND
- HateProof: Are Hateful Meme Detection Systems really Robust?
- Estimating Photometric Redshifts for Galaxies from the DESI Legacy Imaging Surveys with Bayesian Neural Networks Trained by DESI EDR
- Towards Understanding the Data Dependency of Mixup-style Training
- Language-Driven Image Style Transfer
- AVA: Adversarial Vignetting Attack against Visual Recognition
- Unmanned Aerial Vehicle Visual Detection and Tracking using Deep Neural Networks: A Performance Benchmark
- DeepGalaxy: Deducing the Properties of Galaxy Mergers from Images Using Deep Neural Networks
- Rock Classification in Petrographic Thin Section Images Based on Concatenated Convolutional Neural Networks
- Truth or Backpropaganda? An Empirical Investigation of Deep Learning Theory
- ToyArchitecture: Unsupervised Learning of Interpretable Models of the World
- Robust Face Detection via Learning Small Faces on Hard Images
- On transfer learning using a MAC model variant
- To Compress, or Not to Compress: Characterizing Deep Learning Model Compression for Embedded Inference
- Inferring Cosmic String Tension through the Neural Network Prediction of String Locations in CMB Maps
- Deep neural network ensemble by data augmentation and bagging for skin lesion classification
- Weakly and Semi Supervised Human Body Part Parsing via Pose-Guided Knowledge Transfer
- Fast Neural Architecture Construction using EnvelopeNets
- Statistically Motivated Second Order Pooling
- A 3D Coarse-to-Fine Framework for Volumetric Medical Image Segmentation
- Between-class Learning for Image Classification
- UC Merced Submission to the ActivityNet Challenge 2016
- Blending LSTMs into CNNs
- Stochastic Downsampling for Cost-Adjustable Inference and Improved Regularization in Convolutional Networks
- Learning Frequency-aware Dynamic Network for Efficient Super-Resolution
- Zero-Resource Neural Machine Translation with Multi-Agent Communication Game
- Do Normalization Layers in a Deep ConvNet Really Need to Be Distinct?
- FaceSpoof Buster: a Presentation Attack Detector Based on Intrinsic Image Properties and Deep Learning
- YOLOStereo3D: A Step Back to 2D for Efficient Stereo 3D Detection
- Phonology Recognition in American Sign Language
- Nonuniform-to-Uniform Quantization: Towards Accurate Quantization via Generalized Straight-Through Estimation
- Anomalous Sound Detection as a Simple Binary Classification Problem with Careful Selection of Proxy Outlier Examples
- A Machine Learning Approach to Correcting Atmospheric Seeing in Solar Flare Observations
- ModuleNet: Knowledge-inherited Neural Architecture Search
- COLD: Concurrent Loads Disaggregator for Non-Intrusive Load Monitoring
- Trade-offs in Top-k Classification Accuracies on Losses for Deep Learning
- A Theory of Multiple-Source Adaptation with Limited Target Labeled Data
- Tearing Down the Memory Wall
- Imprinto: Enhancing Infrared Inkjet Watermarking for Human and Machine Perception
- Self-labeled Conditional GANs
- Imitating Targets from all sides: An Unsupervised Transfer Learning method for Person Re-identification
- Rethinking Training from Scratch for Object Detection
- Echo: Compiler-based GPU Memory Footprint Reduction for LSTM RNN Training
- DenseImage Network: Video Spatial-Temporal Evolution Encoding and Understanding
- End-to-End Deep Kronecker-Product Matching for Person Re-identification
- An Empirical Evaluation of Adversarial Robustness under Transfer Learning
- Deep driven fMRI decoding of visual categories
- Visual Forecasting by Imitating Dynamics in Natural Sequences
- Deep Dose Plugin Towards Real-time Monte Carlo Dose Calculation Through a Deep Learning based Denoising Algorithm
- Deep Stacked Networks with Residual Polishing for Image Inpainting
- Do Vision Models Encode Object-Level Semantic Relatedness? A Cognitive Psychology-Inspired Benchmark
- Deep Learning for Metagenomic Data: using 2D Embeddings and Convolutional Neural Networks
- Towards Structured Analysis of Broadcast Badminton Videos
- RILOD: Near Real-Time Incremental Learning for Object Detection at the Edge
- Neural Network Training as an Optimal Control Problem: An Augmented Lagrangian Approach
- Convolution Aware Initialization
- Towards large-scale, automated, accurate detection of CCTV camera objects using computer vision. Applications and implications for privacy, safety, and cybersecurity. (Preprint)
- Depth-Based 3D Hand Pose Estimation: From Current Achievements to Future Goals
- Demystifying the MLPerf Benchmark Suite
- Faster Convergence in Deep-Predictive-Coding Networks to Learn Deeper Representations
- The Phonexia VoxCeleb Speaker Recognition Challenge 2021 System Description
- Predicting bulge to total luminosity ratio of galaxies using deep learning
- DeepSkeleton: Skeleton Map for 3D Human Pose Regression
- Joint Discovery of Object States and Manipulation Actions
- Crowd Transformer Network
- SegStereo: Exploiting Semantic Information for Disparity Estimation
- Learning 3D Shapes as Multi-Layered Height-maps using 2D Convolutional Networks
- Towards High Performance Video Object Detection
- GradSign: Model Performance Inference with Theoretical Insights
- Domain-Specific Priors and Meta Learning for Few-Shot First-Person Action Recognition
- CNN Acceleration by Low-rank Approximation with Quantized Factors
- Semi-supervised Skin Detection by Network with Mutual Guidance
- HyPar-Flow: Exploiting MPI and Keras for Scalable Hybrid-Parallel DNN Training using TensorFlow
- toon2real: Translating Cartoon Images to Realistic Images
- Diagnosing Error in Temporal Action Detectors
- Deep neural network for solving differential equations motivated by Legendre-Galerkin approximation
- Simulating Personal Food Consumption Patterns using a Modified Markov Chain
- Biased Bytes: On the Validity of Estimating Food Consumption from Digital Traces
- One-Shot Speaker Identification for a Service Robot using a CNN-based Generic Verifier
- Scene Understanding Networks for Autonomous Driving based on Around View Monitoring System
- SPATL: Salient Parameter Aggregation and Transfer Learning for Heterogeneous Clients in Federated Learning
- 3D Object Detection From LiDAR Data Using Distance Dependent Feature Extraction
- Fast Spectral Ranking for Similarity Search
- Inter-Patient ECG Classification with Convolutional and Recurrent Neural Networks
- Food Ingredients Recognition through Multi-label Learning
- Assessing Intelligence in Artificial Neural Networks
- Video Frame Interpolation by Plug-and-Play Deep Locally Linear Embedding
- Video Object Segmentation with Joint Re-identification and Attention-Aware Mask Propagation
- Beyond Forward Shortcuts: Fully Convolutional Master-Slave Networks (MSNets) with Backward Skip Connections for Semantic Segmentation
- Irregular Convolutional Neural Networks
- Non-Negative Bregman Divergence Minimization for Deep Direct Density Ratio Estimation
- Deep Residual Network for Joint Demosaicing and Super-Resolution
- A flexible FPGA accelerator for convolutional neural networks
- A morphological segmentation approach to determining bar lengths
- How to Make a BLT Sandwich? Learning to Reason towards Understanding Web Instructional Videos
- BusyHands: A Hand-Tool Interaction Database for Assembly Tasks Semantic Segmentation
- Learning Normalized Inputs for Iterative Estimation in Medical Image Segmentation
- ADF & TransApp: A Transformer-Based Framework for Appliance Detection Using Smart Meter Consumption Series
- Local Deep Implicit Functions for 3D Shape
- Extension of Direct Feedback Alignment to Convolutional and Recurrent Neural Network for Bio-plausible Deep Learning
- Noisy Computations during Inference: Harmful or Helpful?
- Training Deep Neural Networks Without Batch Normalization
- Pano2CAD: Room Layout From A Single Panorama Image
- Learning Inertial Odometry for Dynamic Legged Robot State Estimation
- Theano-MPI: a Theano-based Distributed Training Framework
- MotionSqueeze: Neural Motion Feature Learning for Video Understanding
- EvoGrad: Efficient Gradient-Based Meta-Learning and Hyperparameter Optimization
- UV-GAN: Adversarial Facial UV Map Completion for Pose-invariant Face Recognition
- Towards Zero-shot Cross-lingual Image Retrieval and Tagging
- The Evolution of Neural Network-Based Chart Patterns: A Preliminary Study
- Measuring Fairness in Generative Models
- Identity Preserving Generative Adversarial Network for Cross-Domain Person Re-identification
- Darker than Black-Box: Face Reconstruction from Similarity Queries
- Deep Network Interpolation for Continuous Imagery Effect Transition
- MHAttnSurv: Multi-Head Attention for Survival Prediction Using Whole-Slide Pathology Images
- Predicting Localized Primordial Star Formation with Deep Convolutional Neural Networks
- OkwuGbé: End-to-End Speech Recognition for Fon and Igbo
- Unified Generator-Classifier for Efficient Zero-Shot Learning
- SeGAN: Segmenting and Generating the Invisible
- EdgeSegNet: A Compact Network for Semantic Segmentation
- Deep Flow-Guided Video Inpainting
- EfficientHRNet: Efficient Scaling for Lightweight High-Resolution Multi-Person Pose Estimation
- Hardware Acceleration of Explainable Machine Learning using Tensor Processing Units
- Evolving Deep Neural Networks by Multi-objective Particle Swarm Optimization for Image Classification
- FrameNet: Learning Local Canonical Frames of 3D Surfaces from a Single RGB Image
- Structure Learning of Deep Networks via DNA Computing Algorithm
- A Winning Hand: Compressing Deep Networks Can Improve Out-Of-Distribution Robustness
- Visualizing the decision-making process in deep neural decision forest
- MedSelect: Selective Labeling for Medical Image Classification Combining Meta-Learning with Deep Reinforcement Learning
- Matrix and tensor decompositions for training binary neural networks
- CNN aided Weighted Interpolation for Channel Estimation in Vehicular Communications
- Doubly Nested Network for Resource-Efficient Inference
- Unconstrained optimisation on Riemannian manifolds
- Neural Language Priors
- An Effective Pipeline for a Real-world Clothes Retrieval System
- A Cascaded Residual UNET for Fully Automated Segmentation of Prostate and Peripheral Zone in T2-weighted 3D Fast Spin Echo Images
- Ultrasound-Guided Robotic Navigation with Deep Reinforcement Learning
- Gradient Information Guided Deraining with A Novel Network and Adversarial Training
- Classifying CMB time-ordered data through deep neural networks
- Constraint Solving with Deep Learning for Symbolic Execution
- Towards Human-Machine Cooperation: Self-supervised Sample Mining for Object Detection
- Facilitating Access to Multilingual COVID-19 Information via Neural Machine Translation
- Opening the Blackbox: Accelerating Neural Differential Equations by Regularizing Internal Solver Heuristics
- 3D-DETNet: a Single Stage Video-Based Vehicle Detector
- Unsupervised Video Depth Estimation Based on Ego-motion and Disparity Consensus
- Application-Driven Near-Data Processing for Similarity Search
- Identifying Most Walkable Direction for Navigation in an Outdoor Environment
- HySTER: A Hybrid Spatio-Temporal Event Reasoner
- Active Perception for Ambiguous Objects Classification
- Residual Frames with Efficient Pseudo-3D CNN for Human Action Recognition
- DelugeNets: Deep Networks with Efficient and Flexible Cross-layer Information Inflows
- LDMNet: Low Dimensional Manifold Regularized Neural Networks
- Convolutional Neural Network Interpretability with General Pattern Theory
- TACo: Token-aware Cascade Contrastive Learning for Video-Text Alignment
- Spontaneous Symmetry Breaking in Neural Networks
- Energy-efficient Amortized Inference with Cascaded Deep Classifiers
- A polarization analyzer from Deep Neural Networks
- Diagnostic Image Quality Assessment and Classification in Medical Imaging: Opportunities and Challenges
- Flexible and Scalable Deep Learning with MMLSpark
- Why Do Deep Neural Networks Still Not Recognize These Images?: A Qualitative Analysis on Failure Cases of ImageNet Classification
- Dual Encoder Fusion U-Net (DEFU-Net) for Cross-manufacturer Chest X-ray Segmentation
- Extreme 3D Face Reconstruction: Seeing Through Occlusions
- Low-Cost Parameterizations of Deep Convolutional Neural Networks
- A Multi-view RGB-D Approach for Human Pose Estimation in Operating Rooms
- Learning to Support: Exploiting Structure Information in Support Sets for One-Shot Learning
- How to train accurate BNNs for embedded systems?
- Towards Label-Free 3D Segmentation of Optical Coherence Tomography Images of the Optic Nerve Head Using Deep Learning
- Deep-learning-based identification of odontogenic keratocysts in hematoxylin- and eosin-stained jaw cyst specimens
- Semi-Supervised Noisy Student Pre-training on EfficientNet Architectures for Plant Pathology Classification
- Unsupervised Domain Adaptation for Spatio-Temporal Action Localization
- Elastic Gossip: Distributing Neural Network Training Using Gossip-like Protocols
- DF-Net: Unsupervised Joint Learning of Depth and Flow using Cross-Task Consistency
- Multi-domain semantic segmentation with pyramidal fusion
- Multi-Expert Gender Classification on Age Group by Integrating Deep Neural Networks
- Measuring the Substructure Mass Power Spectrum of 23 SLACS Strong Galaxy-Galaxy Lenses with Convolutional Neural Networks
- fruit-SALAD: A Style Aligned Artwork Dataset to reveal similarity perception in image embeddings
- Beyond Trade-off: Accelerate FCN-based Face Detector with Higher Accuracy
- Compression of Deep Neural Networks for Image Instance Retrieval
- OAH-Net: A Deep Neural Network for Hologram Reconstruction of Off-axis Digital Holographic Microscope
- Real-time regression analysis with deep convolutional neural networks
- A Singular Value Perspective on Model Robustness
- Benchmarking Inference Performance of Deep Learning Models on Analog Devices
- AttendSeg: A Tiny Attention Condenser Neural Network for Semantic Segmentation on the Edge
- Exponential Moving Average Model in Parallel Speech Recognition Training
- Search to Distill: Pearls are Everywhere but not the Eyes
- Frustum VoxNet for 3D object detection from RGB-D or Depth images
- Low-Latency Video Semantic Segmentation
- Face Aging with Contextual Generative Adversarial Nets
- Cost-Effective Training of Deep CNNs with Active Model Adaptation
- Multi-Miner: Object-Adaptive Region Mining for Weakly-Supervised Semantic Segmentation
- TensorFlow with user friendly Graphical Framework for object detection API
- Classification of simulated radio signals using Wide Residual Networks for use in the search for extra-terrestrial intelligence
- A Self-supervised Approach for Adversarial Robustness
- AI4AI: Quantitative Methods for Classifying Host Species from Avian Influenza DNA Sequence
- StarMap for Category-Agnostic Keypoint and Viewpoint Estimation
- A model for interpreting social interactions in local image regions
- Butterfly Effect: Bidirectional Control of Classification Performance by Small Additive Perturbation
- Grounding inductive biases in natural images:invariance stems from variations in data
- Face Recognition in Unconstrained Conditions: A Systematic Review
- Three-Stream Convolutional Networks for Video-based Person Re-Identification
- Efficient Training of Convolutional Neural Nets on Large Distributed Systems
- Generating Nontrivial Melodies for Music as a Service
- Weight Map Layer for Noise and Adversarial Attack Robustness
- Neural Style Representations and the Large-Scale Classification of Artistic Style
- Modular Learning Component Attacks: Today's Reality, Tomorrow's Challenge
- Synthetic Unknown Class Learning for Learning Unknowns
- Learnable Adaptive Cosine Estimator (LACE) for Image Classification
- Giving Commands to a Self-driving Car: A Multimodal Reasoner for Visual Grounding
- Fast Marching Energy CNN
- SurfConv: Bridging 3D and 2D Convolution for RGBD Images
- Pedestrian Detection with Autoregressive Network Phases
- Malaria detection from RBC images using shallow Convolutional Neural Networks
- A Deep Multi-task Learning Approach to Skin Lesion Classification
- Table-Based Neural Units: Fully Quantizing Networks for Multiply-Free Inference
- Type-Driven Automated Learning with Lale
- Design Environment of Quantization-Aware Edge AI Hardware for Few-Shot Learning
- A study on using image based machine learning methods to develop the surrogate models of stamp forming simulations
- Estimating Atmospheric Parameters of DA White Dwarf Stars with Deep Learning
- VommaNet: an End-to-End Network for Disparity Estimation from Reflective and Texture-less Light Field Images
- FaceShapeGene: A Disentangled Shape Representation for Flexible Face Image Editing
- Learning Visual Representations for Transfer Learning by Suppressing Texture
- Tracking Without Re-recognition in Humans and Machines
- Representation Transfer by Optimal Transport
- Detecting Pulsars with Neural Networks: A Proof of Concept
- Guided Proofreading of Automatic Segmentations for Connectomics
- Learning Disentangled Representations of Satellite Image Time Series
- Loss Barcode: A Topological Measure of Escapability in Loss Landscapes
- DeepGeo: Photo Localization with Deep Neural Network
- Knowledge Distillation via Instance-level Sequence Learning
- Widget Captioning: Generating Natural Language Description for Mobile User Interface Elements
- Improving Sentence Representations with Consensus Maximisation
- A Deep Learning Approach to the Inversion of Borehole Resistivity Measurements
- Spatial Memory for Context Reasoning in Object Detection
- Efficient Realistic Data Generation Framework leveraging Deep Learning-based Human Digitization
- Recognizing bird species in diverse soundscapes under weak supervision
- In Defense of the Classification Loss for Person Re-Identification
- Weighted Empirical Risk Minimization: Sample Selection Bias Correction based on Importance Sampling
- Lossless Compression of Mosaic Images with Convolutional Neural Network Prediction
- CSMCNet: Scalable Video Compressive Sensing Reconstruction with Interpretable Motion Estimation
- Gradually Updated Neural Networks for Large-Scale Image Recognition
- 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
- iShape: A First Step Towards Irregular Shape Instance Segmentation
- Cluster Analysis with Deep Embeddings and Contrastive Learning
- Predicting the dynamics of 2d objects with a deep residual network
- AON: Towards Arbitrarily-Oriented Text Recognition
- Ignition: An End-to-End Supervised Model for Training Simulated Self-Driving Vehicles
- Investigating Transfer Learning Capabilities of Vision Transformers and CNNs by Fine-Tuning a Single Trainable Block
- MLPerf HPC: A Holistic Benchmark Suite for Scientific Machine Learning on HPC Systems
- Enhanced Object Detection via Fusion With Prior Beliefs from Image Classification
- Cube Padding for Weakly-Supervised Saliency Prediction in 360° Videos
- An Audio-Video Deep and Transfer Learning Framework for Multimodal Emotion Recognition in the wild
- Towards Trainable Saliency Maps in Medical Imaging
- Ultrasound Diagnosis of COVID-19: Robustness and Explainability
- Dense xUnit Networks
- SuperNet -- An efficient method of neural networks ensembling
- Towards Collaborative Intelligence Friendly Architectures for Deep Learning
- One-class Steel Detector Using Patch GAN Discriminator for Visualising Anomalous Feature Map
- Optimizing Deep Neural Networks with Multiple Search Neuroevolution
- WaveletNet: Logarithmic Scale Efficient Convolutional Neural Networks for Edge Devices
- Physical Primitive Decomposition
- Dendron: Enhancing Human Activity Recognition with On-Device TinyML Learning
- Real-Time Cell Sorting with Scalable In Situ FPGA-Accelerated Deep Learning
- Grounded Video Description
- Click Here: Human-Localized Keypoints as Guidance for Viewpoint Estimation
- Evaluating Text-to-Image Matching using Binary Image Selection (BISON)
- Multivariate-Information Adversarial Ensemble for Scalable Joint Distribution Matching
- Vehicle Re-identification Method Based on Vehicle Attribute and Mutual Exclusion Between Cameras
- Deep unsupervised domain adaptation applied to the Cherenkov Telescope Array Large-Sized Telescope
- Learning On-Road Visual Control for Self-Driving Vehicles with Auxiliary Tasks
- Aug3D-RPN: Improving Monocular 3D Object Detection by Synthetic Images with Virtual Depth
- Deep Frame Interpolation
- Learning image from projection: a full-automatic reconstruction (FAR) net for sparse-views computed tomography
- Understanding Catastrophic Forgetting and Remembering in Continual Learning with Optimal Relevance Mapping
- Investigation of a Machine learning methodology for the SKA pulsar search pipeline
- El-CID: A filter for Gravitational-wave Electromagnetic Counterpart Identification
- PoseGAN: A Pose-to-Image Translation Framework for Camera Localization
- Sparsity in Deep Neural Networks - An Empirical Investigation with TensorQuant
- NavigationNet: A Large-scale Interactive Indoor Navigation Dataset
- Multimodal AI in Healthcare: Review of Vision-Language Foundation Models for Real-World Medical Applications
- Scalable Metric Learning via Weighted Approximate Rank Component Analysis
- Single Image Depth Estimation Trained via Depth from Defocus Cues
- Federated Learning over Wireless Networks: A Band-limited Coordinated Descent Approach
- Generative-Discriminative Complementary Learning
- Functional Error Correction for Robust Neural Networks
- cuConv: A CUDA Implementation of Convolution for CNN Inference
- End-to-end learning potentials for structured attribute prediction
- Experimental Demonstration of Learned Time-Domain Digital Back-Propagation
- Incremental Learning in Person Re-Identification
- Meta-Learning Bidirectional Update Rules
- CrescendoNet: A Simple Deep Convolutional Neural Network with Ensemble Behavior
- Go with the Flow: Adaptive Control for Neural ODEs
- Clothing Retrieval with Visual Attention Model
- Single Sample Feature Importance: An Interpretable Algorithm for Low-Level Feature Analysis
- An Artificial Intelligence-Driven Agent for Real-Time Head-and-Neck IMRT Plan Generation using Conditional Generative Adversarial Network (cGAN)
- An Overview on Data Representation Learning: From Traditional Feature Learning to Recent Deep Learning
- MinMaxCAM: Improving object coverage for CAM-basedWeakly Supervised Object Localization
- Looking for change? Roll the Dice and demand Attention
- Deep Imbalanced Attribute Classification using Visual Attention Aggregation
- BENCHIP: Benchmarking Intelligence Processors
- Adaptive Leader-Follower Formation Control and Obstacle Avoidance via Deep Reinforcement Learning
- High-speed Railway Fastener Detection and Localization Method based on convolutional neural network
- Instance Scale Normalization for image understanding
- Multi-Plateau Ensemble for Endoscopic Artefact Segmentation and Detection
- Spatially-Adaptive Filter Units for Deep Neural Networks
- Learning Spatial-Semantic Context with Fully Convolutional Recurrent Network for Online Handwritten Chinese Text Recognition
- Is a Picture Worth Ten Thousand Words in a Review Dataset?
- Explain Me the Painting: Multi-Topic Knowledgeable Art Description Generation
- MULE: Multimodal Universal Language Embedding
- NASIB: Neural Architecture Search withIn Budget
- Probabilistic Oriented Object Detection in Automotive Radar
- MPDCompress - Matrix Permutation Decomposition Algorithm for Deep Neural Network Compression
- First-Order Preconditioning via Hypergradient Descent
- Ensemble Transfer Learning for Emergency Landing Field Identification on Moderate Resource Heterogeneous Kubernetes Cluster
- Defective samples simulation through Neural Style Transfer for automatic surface defect segment
- Real-time Burst Photo Selection Using a Light-Head Adversarial Network
- Propagated Perturbation of Adversarial Attack for well-known CNNs: Empirical Study and its Explanation
- Class-Wise Difficulty-Balanced Loss for Solving Class-Imbalance
- On Improving Temporal Consistency for Online Face Liveness Detection
- Classifying Tweet Sentiment Using the Hidden State and Attention Matrix of a Fine-tuned BERTweet Model
- Towards DeepSentinel: An extensible corpus of labelled Sentinel-1 and -2 imagery and a general-purpose sensor-fusion semantic embedding model
- Key Frame Proposal Network for Efficient Pose Estimation in Videos
- Bespoke vs. Prêt-à-Porter Lottery Tickets: Exploiting Mask Similarity for Trainable Sub-Network Finding
- Geometrically Enriched Latent Spaces
- Model Optimization for Deep Space Exploration via Simulators and Deep Learning
- Trying Bilinear Pooling in Video-QA
- Hunt for dark subhalos in the galactic stellar field using computer vision
- Imaginative Walks: Generative Random Walk Deviation Loss for Improved Unseen Learning Representation
- MLPerf Mobile Inference Benchmark
- NWT: Towards natural audio-to-video generation with representation learning
- Energy Propagation in Deep Convolutional Neural Networks
- The VQA-Machine: Learning How to Use Existing Vision Algorithms to Answer New Questions
- YUVMultiNet: Real-time YUV multi-task CNN for autonomous driving
- Learning View Priors for Single-view 3D Reconstruction
- A 3D CNN Network with BERT For Automatic COVID-19 Diagnosis From CT-Scan Images
- ArchNet: Data Hiding Model in Distributed Machine Learning System
- DeMeshNet: Blind Face Inpainting for Deep MeshFace Verification
- Difficulty Translation in Histopathology Images
- SAM-GCNN: A Gated Convolutional Neural Network with Segment-Level Attention Mechanism for Home Activity Monitoring
- Deep Transfer Learning with Ridge Regression
- Hybrid graph convolutional neural networks for landmark-based anatomical segmentation
- Proxy Synthesis: Learning with Synthetic Classes for Deep Metric Learning
- Deep Consensus Learning
- From Deep to Shallow: Transformations of Deep Rectifier Networks
- Recommending Outfits from Personal Closet
- "What happens if..." Learning to Predict the Effect of Forces in Images
- Class Subset Selection for Transfer Learning using Submodularity
- Meta-Cal: Well-controlled Post-hoc Calibration by Ranking
- Where Should We Begin? A Low-Level Exploration of Weight Initialization Impact on Quantized Behaviour of Deep Neural Networks
- Quality-Aware Network for Human Parsing
- Empirical Analysis of Image Caption Generation using Deep Learning
- Exploring Vision Transformers for Fine-grained Classification
- Few-Shot Object Recognition from Machine-Labeled Web Images
- Dynamic Video Segmentation Network
- Deconfusing intensity maps with neural networks
- Fast and Accurate Online Video Object Segmentation via Tracking Parts
- Deep CSI Learning for Gait Biometric Sensing and Recognition
- Comparing the costs of abstraction for DL frameworks
- Large, fast and accurate HI intensity maps with latent overlap diffusion
- Gear Training: A new way to implement high-performance model-parallel training
- DEPARA: Deep Attribution Graph for Deep Knowledge Transferability
- Improving Convolutional Neural Networks Via Conservative Field Regularisation and Integration
- TLGAN: document Text Localization using Generative Adversarial Nets
- Positional Artefacts Propagate Through Masked Language Model Embeddings
- Multimodal Data Fusion based on the Global Workspace Theory
- Stochastic Gradient Variance Reduction by Solving a Filtering Problem
- C-DLinkNet: considering multi-level semantic features for human parsing
- Augmentation Inside the Network
- A Machine-Learning Method for Time-Dependent Wave Equations over Unbounded Domains
- Fine-grained Image-to-Image Transformation towards Visual Recognition
- Adversarially Robust Kernel Smoothing
- Unsupervised Continual Learning Via Pseudo Labels
- D-OccNet: Detailed 3D Reconstruction Using Cross-Domain Learning
- Deep Learning At Scale and At Ease
- Cross-Channel Intragroup Sparsity Neural Network
- Lenses In VoicE (LIVE): Searching for strong gravitational lenses in the VOICE@VST survey using Convolutional Neural Networks
- BPPSA: Scaling Back-propagation by Parallel Scan Algorithm
- Filter Bank Regularization of Convolutional Neural Networks
- ADNet: Leveraging Error-Bias Towards Normal Direction in Face Alignment
- What augmentations are sensitive to hyper-parameters and why?
- Structured 2D Representation of 3D Data for Shape Processing
- Lift-the-flap: what, where and when for context reasoning
- Regularized Ensembles and Transferability in Adversarial Learning
- Neural Rejuvenation: Improving Deep Network Training by Enhancing Computational Resource Utilization
- Kilonova Light Curve Parameter Estimation Using Likelihood-Free Inference
- Convolution in Convolution for Network in Network
- Latent Sensor Fusion: Multimedia Learning of Physiological Signals for Resource-Constrained Devices
- On Spectral Properties of Gradient-based Explanation Methods
- Whole Slide Multiple Instance Learning for Predicting Axillary Lymph Node Metastasis
- ChainGAN: A sequential approach to GANs
- Sex Detection in the Early Stage of Fertilized Chicken Eggs via Image Recognition
- Scene Parsing via Dense Recurrent Neural Networks with Attentional Selection
- Using Early-Learning Regularization to Classify Real-World Noisy Data
- Reducing the feature divergence of RGB and near-infrared images using Switchable Normalization
- The Method of Multimodal MRI Brain Image Segmentation Based on Differential Geometric Features
- Machine Translation between Vietnamese and English: an Empirical Study
- D2C: Diffusion-Denoising Models for Few-shot Conditional Generation
- Orthogonal-Padé Activation Functions: Trainable Activation functions for smooth and faster convergence in deep networks
- Augmented KRnet for density estimation and approximation
- Learnable Pooling Methods for Video Classification
- Dense neural networks as sparse graphs and the lightning initialization
- Semantic Image Cropping
- Will Multi-modal Data Improves Few-shot Learning?
- Evaluation of Neural Networks for Image Recognition Applications: Designing a 0-1 MILP Model of a CNN to create adversarials
- Retinal Microvasculature as Biomarker for Diabetes and Cardiovascular Diseases
- Semantic Segmentation and Object Detection Towards Instance Segmentation: Breast Tumor Identification
- Smart Device based Initial Movement Detection of Cyclists using Convolutional Neuronal Networks
- Auto-Classification of Retinal Diseases in the Limit of Sparse Data Using a Two-Streams Machine Learning Model
- Effectiveness of Deep Networks in NLP using BiDAF as an example architecture
- Semantic Segmentation on VSPW Dataset through Aggregation of Transformer Models
- Multiple Myeloma Cancer Cell Instance Segmentation
- VTAMIQ: Transformers for Attention Modulated Image Quality Assessment
- Disturbing Target Values for Neural Network Regularization
- Protecting Anonymous Speech: A Generative Adversarial Network Methodology for Removing Stylistic Indicators in Text
- Exploiting Inter-pixel Correlations in Unsupervised Domain Adaptation for Semantic Segmentation
- Unifying Identification and Context Learning for Person Recognition
- LogAvgExp Provides a Principled and Performant Global Pooling Operator
- Fully convolutional Siamese neural networks for buildings damage assessment from satellite images
- Foresee: Attentive Future Projections of Chaotic Road Environments with Online Training
- Deep Collaborative Learning for Visual Recognition
- A Neural Embeddings Approach for Detecting Mobile Counterfeit Apps
- Doping: A technique for efficient compression of LSTM models using sparse structured additive matrices
- The Effects of Image Distribution and Task on Adversarial Robustness
- Automatic Latent Fingerprint Segmentation
- A Sketch-Based Neural Model for Generating Commit Messages from Diffs
- Writing in The Air: Unconstrained Text Recognition from Finger Movement Using Spatio-Temporal Convolution
- Decoupled Gradient Harmonized Detector for Partial Annotation: Application to Signet Ring Cell Detection
- Joint Spatial-Temporal Optimization for Stereo 3D Object Tracking
- Learning scale-variant and scale-invariant features for deep image classification
- Intensity Non-uniformity Correction in MR Imaging Using Residual Cycle Generative Adversarial Network
- In-Vehicle Object Detection in the Wild for Driverless Vehicles
- Deep Learning with Apache SystemML
- Model Agnostic Combination for Ensemble Learning
- Detecting abnormal events in video using Narrowed Normality Clusters
- Amended Cross Entropy Cost: Framework For Explicit Diversity Encouragement
- Non-Markov Policies to Reduce Sequential Failures in Robot Bin Picking
- Unsupervised Learning of Solutions to Differential Equations with Generative Adversarial Networks
- A general approach to bridge the reality-gap
- Enforcing Reasoning in Visual Commonsense Reasoning
- Towards thinner convolutional neural networks through Gradually Global Pruning
- TraffickCam: Explainable Image Matching For Sex Trafficking Investigations
- Incorporating Textual Evidence in Visual Storytelling
- Privacy for Rescue: A New Testimony Why Privacy is Vulnerable In Deep Models
- Deep Shape Matching
- Adaptive Loss Function for Super Resolution Neural Networks Using Convex Optimization Techniques
- Scalable and Effective Deep CCA via Soft Decorrelation
- NeuroFabric: Identifying Ideal Topologies for Training A Priori Sparse Networks
- Adversarial training applied to Convolutional Neural Network for photometric redshift predictions
- FA-RPN: Floating Region Proposals for Face Detection
- Studying the Plasticity in Deep Convolutional Neural Networks using Random Pruning
- Skeleton Transformer Networks: 3D Human Pose and Skinned Mesh from Single RGB Image
- A Push-Pull Layer Improves Robustness of Convolutional Neural Networks
- A Generative Map for Image-based Camera Localization
- Exploring epoch-dependent stochastic residual networks
- Deep Contextual Recurrent Residual Networks for Scene Labeling
- Manifestation of Image Contrast in Deep Networks
- Human Activity Recognition for Edge Devices
- Boosted Attention: Leveraging Human Attention for Image Captioning
- Perceive Where to Focus: Learning Visibility-aware Part-level Features for Partial Person Re-identification
- ClusterNet: Detecting Small Objects in Large Scenes by Exploiting Spatio-Temporal Information
- Position-Aware Convolutional Networks for Traffic Prediction
- Beyond Planar Symmetry: Modeling human perception of reflection and rotation symmetries in the wild
- Unsupervised Open Domain Recognition by Semantic Discrepancy Minimization
- Compression Fractures Detection on CT
- YouTube-8M Video Understanding Challenge Approach and Applications
- Recurrent 3D Pose Sequence Machines
- High Efficient Reconstruction of Single-shot T2 Mapping from OverLapping-Echo Detachment Planar Imaging Based on Deep Residual Network
- BPGrad: Towards Global Optimality in Deep Learning via Branch and Pruning
- Feature Selective Networks for Object Detection
- Multi-Mode Inference Engine for Convolutional Neural Networks
- Visual Data Augmentation through Learning
- Deep, Dense, and Low-Rank Gaussian Conditional Random Fields
- Feudal Steering: Hierarchical Learning for Steering Angle Prediction
- Reliable Label Bootstrapping for Semi-Supervised Learning
- Improving compute efficacy frontiers with SliceOut
- Deep Learning: Our Miraculous Year 1990-1991
- A Simple and Interpretable Predictive Model for Healthcare
- A comparison of deep machine learning algorithms in COVID-19 disease diagnosis
- Phantom: A High-Performance Computational Core for Sparse Convolutional Neural Networks
- Automated Segmentation of Brain Gray Matter Nuclei on Quantitative Susceptibility Mapping Using Deep Convolutional Neural Network
- Recent Advancements in Self-Supervised Paradigms for Visual Feature Representation
- Efficient resource management in UAVs for Visual Assistance
- Rethinking Radiology: An Analysis of Different Approaches to BraTS
- Graph Neural Networks for UnsupervisedDomain Adaptation of Histopathological ImageAnalytics
- A Multi-Task Learning Approach for Meal Assessment
- Exploiting Temporal Attention Features for Effective Denoising in Videos
- Learning Compact Physics-Aware Delayed Photocurrent Models Using Dynamic Mode Decomposition
- 3D-MOV: Audio-Visual LSTM Autoencoder for 3D Reconstruction of Multiple Objects from Video
- Selective Deep Convolutional Neural Network for Low Cost Distorted Image Classification
- FHEDN: A based on context modeling Feature Hierarchy Encoder-Decoder Network for face detection
- LR-to-HR Face Hallucination with an Adversarial Progressive Attribute-Induced Network
- Classification of COVID-19 from CXR Images in a 15-class Scenario: an Attempt to Avoid Bias in the System
- ReflectNet -- A Generative Adversarial Method for Single Image Reflection Suppression
- Animal inspired Application of a Variant of Mel Spectrogram for Seismic Data Processing
- Video Surveillance for Road Traffic Monitoring
- Barrier-Free Large-Scale Sparse Tensor Accelerator (BARISTA) For Convolutional Neural Networks
- Vehicle Image Generation Going Well with The Surroundings
- Introduce the Result Into Self-Attention
- Training Dynamic based data filtering may not work for NLP datasets
- Medusa: A Scalable Interconnect for Many-Port DNN Accelerators and Wide DRAM Controller Interfaces
- Diagnosis of Pediatric Obstructive Sleep Apnea via Face Classification with Persistent Homology and Convolutional Neural Networks
- Bounding Box Embedding for Single Shot Person Instance Segmentation
- Text Classification based on Multiple Block Convolutional Highways
- On the Flip Side: Identifying Counterexamples in Visual Question Answering
- Leveraging Model Interpretability and Stability to increase Model Robustness
- Investigations of the Influences of a CNN's Receptive Field on Segmentation of Subnuclei of Bilateral Amygdalae
- Person re-identification across different datasets with multi-task learning
- Person Search in Videos with One Portrait Through Visual and Temporal Links
- Dense Fusion Classmate Network for Land Cover Classification
- Accent Recognition with Hybrid Phonetic Features
- FusionStitching: Boosting Execution Efficiency of Memory Intensive Computations for DL Workloads
- StackGAN: Facial Image Generation Optimizations
- TrUMAn: Trope Understanding in Movies and Animations
- Granular Motor State Monitoring of Free Living Parkinson's Disease Patients via Deep Learning
- Relational Mimic for Visual Adversarial Imitation Learning
- Backtracking gradient descent method for general functions, with applications to Deep Learning
- Logit Attenuating Weight Normalization
- Perceptual Gradient Networks
- Convergence Analysis of Gradient Descent Algorithms with Proportional Updates
- Temporally Folded Convolutional Neural Networks for Sequence Forecasting
- Copy and Paste method based on Pose for Re-identification
- A simple model for detection of rare sound events
- Towards More Efficient and Effective Inference: The Joint Decision of Multi-Participants
- Instance Map based Image Synthesis with a Denoising Generative Adversarial Network
- Mitigating large adversarial perturbations on X-MAS (X minus Moving Averaged Samples)
- Deep Boosted Regression for MR to CT Synthesis
- A Survey On 3D Inner Structure Prediction from its Outer Shape
- Recognition of Russian traffic signs in winter conditions. Solutions of the "Ice Vision" competition winners
- GANs for Urban Design
- Attentive Sequence to Sequence Translation for Localizing Clips of Interest by Natural Language Descriptions
- Development and evaluation of intraoperative ultrasound segmentation with negative image frames and multiple observer labels
- Dual Pattern Learning Networks by Empirical Dual Prediction Risk Minimization
- FMT:Fusing Multi-task Convolutional Neural Network for Person Search
- Style-Restricted GAN: Multi-Modal Translation with Style Restriction Using Generative Adversarial Networks
- Improve Unsupervised Pretraining for Few-label Transfer
- Does Face Recognition Error Echo Gender Classification Error?
- Mapping the Internet: Modelling Entity Interactions in Complex Heterogeneous Networks
- Unsupervised monocular stereo matching
- Image Manipulation with Perceptual Discriminators
- Exploration on Grounded Word Embedding: Matching Words and Images with Image-Enhanced Skip-Gram Model
- Batch Inverse-Variance Weighting: Deep Heteroscedastic Regression
- Hotels-50K: A Global Hotel Recognition Dataset
- Open Source Face Recognition Performance Evaluation Package
- TUNet: Incorporating segmentation maps to improve classification
- DDNet: Dual-path Decoder Network for Occlusion Relationship Reasoning
- Analysing object detectors from the perspective of co-occurring object categories
- Learning Chebyshev Basis in Graph Convolutional Networks for Skeleton-based Action Recognition
- Consistent Accelerated Inference via Confident Adaptive Transformers
- Reconciling Feature-Reuse and Overfitting in DenseNet with Specialized Dropout
- Benchmarks of ResNet Architecture for Atrial Fibrillation Classification
- A Free Lunch in Generating Datasets: Building a VQG and VQA System with Attention and Humans in the Loop
- Mix and Mask Actor-Critic Methods
- Bidirectional Multirate Reconstruction for Temporal Modeling in Videos
- Finding Correspondences for Optical Flow and Disparity Estimations using a Sub-pixel Convolution-based Encoder-Decoder Network
- Training Convolutional Neural Networks and Compressed Sensing End-to-End for Microscopy Cell Detection
- Deep Active Localization
- Natural Disaster Classification using Aerial Photography Explainable for Typhoon Damaged Feature
- Improving the Performance of Neural Networks in Regression Tasks Using Drawering
- Penetrating the Fog: the Path to Efficient CNN Models
- Automated pulmonary nodule detection using 3D deep convolutional neural networks
- The Focus-Aspect-Polarity Model for Predicting Subjective Noun Attributes in Images
- Who Will Win Practical Artificial Intelligence? AI Engineerings in China
- Asynchronous Stochastic Gradient MCMC with Elastic Coupling
- Real-time Action Recognition with Dissimilarity-based Training of Specialized Module Networks
- On the Equivalence of Convolutional and Hadamard Networks using DFT
- Structure Learning of Deep Neural Networks with Q-Learning
- Autoencoding Undirected Molecular Graphs With Neural Networks
- A Self-supervised Learning System for Object Detection in Videos Using Random Walks on Graphs
- DeepAtrophy: Teaching a Neural Network to Differentiate Progressive Changes from Noise on Longitudinal MRI in Alzheimer's Disease
- Vanishing Curvature and the Power of Adaptive Methods in Randomly Initialized Deep Networks
- Population Gradients improve performance across data-sets and architectures in object classification
- DeepCompress: Efficient Point Cloud Geometry Compression
- Know Your Surroundings: Panoramic Multi-Object Tracking by Multimodality Collaboration
- Towards Diverse Paragraph Captioning for Untrimmed Videos
- Neural Options Pricing
- Efficient Transfer Learning via Joint Adaptation of Network Architecture and Weight
- Domain-Agnostic Clustering with Self-Distillation
- Towards Robust and Automatic Hyper-Parameter Tunning
- Learning Robust 3D Face Reconstruction and Discriminative Identity Representation
- A Compositional Textual Model for Recognition of Imperfect Word Images
- Large Language Models -- the Future of Fundamental Physics?
- Automatic Liver Segmentation with Adversarial Loss and Convolutional Neural Network
- Y-GAN: A Generative Adversarial Network for Depthmap Estimation from Multi-camera Stereo Images
- Tensorization of neural networks for improved privacy and interpretability
- Semi-Supervised Learning for Face Sketch Synthesis in the Wild
- Pay Attention to Convolution Filters: Towards Fast and Accurate Fine-Grained Transfer Learning
- Binary Stochastic Representations for Large Multi-class Classification
- Playing Go without Game Tree Search Using Convolutional Neural Networks
- Searches for Compact Binary Coalescence Events Using Neural Networks in LIGO/Virgo Third Observation Period
- Neural Image Captioning
- MURAUER: Mapping Unlabeled Real Data for Label AUstERity
- Montage based 3D Medical Image Retrieval from Traumatic Brain Injury Cohort using Deep Convolutional Neural Network
- 2nd Place Solution to Instance Segmentation of IJCAI 3D AI Challenge 2020
- Diagnostic Visualization for Deep Neural Networks Using Stochastic Gradient Langevin Dynamics
- Non-local RoIs for Instance Segmentation
- MCMC Guided CNN Training and Segmentation for Pancreas Extraction
- Neural Machine Translation between Herbal Prescriptions and Diseases
- Real-time Human Detection Model for Edge Devices
- A deep ensemble approach to X-ray polarimetry
- Using mixup as regularization and tuning hyper-parameters for ResNets
- A Content Transformation Block For Image Style Transfer
- Depth Without the Magic: Inductive Bias of Natural Gradient Descent
- An Improved Neural Segmentation Method Based on U-NET
- Predicting Clinical Outcomes in COVID-19 using Radiomics and Deep Learning on Chest Radiographs: A Multi-Institutional Study
- Hybrid BYOL-ViT: Efficient approach to deal with small datasets
- Evaluating Contrastive Learning on Wearable Timeseries for Downstream Clinical Outcomes
- Learning by Cheating : An End-to-End Zero Shot Framework for Autonomous Drone Navigation
- Graph Relation Transformer: Incorporating pairwise object features into the Transformer architecture
- Complementary Ensemble Learning
- DeepWheat: Estimating Phenotypic Traits from Crop Images with Deep Learning
- Game Theory for Adversarial Attacks and Defenses
- Knowledge-driven Active Learning
- Learning Atomic Multipoles: Prediction of the Electrostatic Potential with Equivariant Graph Neural Networks
- InsectUp: Crowdsourcing Insect Observations to Assess Demographic Shifts and Improve Classification
- Rethinking Lightweight Convolutional Neural Networks for Efficient and High-quality Pavement Crack Detection
- ISyNet: Convolutional Neural Networks design for AI accelerator
- Impact of Channel Variation on One-Class Learning for Spoof Detection
- Deep Generative Variational Autoencoding for Replay Spoof Detection in Automatic Speaker Verification
- Block-Cyclic Stochastic Coordinate Descent for Deep Neural Networks
- Audiomer: A Convolutional Transformer For Keyword Spotting
- Train, Diagnose and Fix: Interpretable Approach for Fine-grained Action Recognition
- From Artificial Intelligence to Brain Intelligence: The basis learning and memory algorithm for brain-like intelligence
- Fast and Explicit Neural View Synthesis
- Exploiting Nontrivial Connectivity for Automatic Speech Recognition
- Caramel: Accelerating Decentralized Distributed Deep Learning with Computation Scheduling
- Compact retail shelf segmentation for mobile deployment
- How to Train your DNN: The Network Operator Edition
- Identify Speakers in Cocktail Parties with End-to-End Attention
- Broadband vectorial ultra-flat optics with experimental efficiency up to 99% in the visible via universal approximators
- Recurrent Residual Module for Fast Inference in Videos
- RootPainter3D: Interactive-machine-learning enables rapid and accurate contouring for radiotherapy
- Exponential Discriminative Metric Embedding in Deep Learning
- Train and Deploy an Image Classifier for Disaster Response
- Cross-filter compression for CNN inference acceleration
- On Intrinsic Dataset Properties for Adversarial Machine Learning
- VeriMedi: Pill Identification using Proxy-based Deep Metric Learning and Exact Solution
- Efficient Embedding of MPI Collectives in MXNET DAGs for scaling Deep Learning
- Error Control and Loss Functions for the Deep Learning Inversion of Borehole Resistivity Measurements
- OmniLayout: Room Layout Reconstruction from Indoor Spherical Panoramas
- A Multi-Modal Approach to Infer Image Affect
- Holistic Image Manipulation Detection using Pixel Co-occurrence Matrices
- Domain Adaptive Monocular Depth Estimation With Semantic Information
- Sparsifying and Down-scaling Networks to Increase Robustness to Distortions
- Searching Learning Strategy with Reinforcement Learning for 3D Medical Image Segmentation
- Local Contrast Learning
- Reinforced Attention for Few-Shot Learning and Beyond
- Representation range needs for 16-bit neural network training
- Image to Video Domain Adaptation Using Web Supervision
- Beyond Categorical Label Representations for Image Classification
- Analysis on Image Set Visual Question Answering
- Split-Merge Pooling
- AET-EFN: A Versatile Design for Static and Dynamic Event-Based Vision
- Dynamic Metric Learning: Towards a Scalable Metric Space to Accommodate Multiple Semantic Scales
- Learning Identity-Preserving Transformations on Data Manifolds
- A Quadratic Actor Network for Model-Free Reinforcement Learning
- Deep Gradient Projection Networks for Pan-sharpening
- LiDAR-based Recurrent 3D Semantic Segmentation with Temporal Memory Alignment
- Variational Autoencoded Regression: High Dimensional Regression of Visual Data on Complex Manifold
- BEDS: Bagging ensemble deep segmentation for nucleus segmentation with testing stage stain augmentation
- PrototypeML: A Neural Network Integrated Design and Development Environment
- Hardware-efficient Residual Networks for FPGAs
- VideoClick: Video Object Segmentation with a Single Click
- OpTorch: Optimized deep learning architectures for resource limited environments
- Survey on Deep Learning-based Kuzushiji Recognition
- RethNet: Object-by-Object Learning for Detecting Facial Skin Problems
- A one-armed CNN for exoplanet detection from light curves
- Minimizing Labeling Effort for Tree Skeleton Segmentation using an Automated Iterative Training Methodology
- Bayesian neural network with pretrained protein embedding enhances prediction accuracy of drug-protein interaction
- A Simple Riemannian Manifold Network for Image Set Classification
- MyFood: A Food Segmentation and Classification System to Aid Nutritional Monitoring
- 3D attention mechanism for fine-grained classification of table tennis strokes using a Twin Spatio-Temporal Convolutional Neural Networks
- Learning to Predict the 3D Layout of a Scene