MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
arXiv:1704.04861
Abstract
We present a class of efficient models called MobileNets for mobile and embedded vision applications. MobileNets are based on a streamlined architecture that uses depth-wise separable convolutions to build light weight deep neural networks. We introduce two simple global hyper-parameters that efficiently trade off between latency and accuracy. These hyper-parameters allow the model builder to choose the right sized model for their application based on the constraints of the problem. We present extensive experiments on resource and accuracy tradeoffs and show strong performance compared to other popular models on ImageNet classification. We then demonstrate the effectiveness of MobileNets across a wide range of applications and use cases including object detection, finegrain classification, face attributes and large scale geo-localization.
References in corpus (19)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Distilling the Knowledge in a Neural Network
- SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
- Caffe: Convolutional Architecture for Fast Feature Embedding
- Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding
- YFCC100M: The New Data in Multimedia Research
- Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations
- Going Deeper with Convolutions
- Compressing Neural Networks with the Hashing Trick
- Speeding up Convolutional Neural Networks with Low Rank Expansions
- PlaNet - Photo Geolocation with Convolutional Neural Networks
- Xception: Deep Learning with Depthwise Separable Convolutions
- Speeding-up Convolutional Neural Networks Using Fine-tuned CP-Decomposition
- XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks
- Flattened Convolutional Neural Networks for Feedforward Acceleration
- Speed/accuracy trade-offs for modern convolutional object detectors
- Quantized Convolutional Neural Networks for Mobile Devices
- The Unreasonable Effectiveness of Noisy Data for Fine-Grained Recognition
- Deep Fried Convnets
Cited by in corpus (2118)
- YOLOv4: Optimal Speed and Accuracy of Object Detection
- EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
- Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
- Knowledge Distillation: A Survey
- Covid-19: Automatic detection from X-Ray images utilizing Transfer Learning with Convolutional Neural Networks
- PVT v2: Improved Baselines with Pyramid Vision Transformer
- MobileNetV2: Inverted Residuals and Linear Bottlenecks
- Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation
- NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding
- Convergence of Edge Computing and Deep Learning: A Comprehensive Survey
- Deep Joint Source-Channel Coding for Wireless Image Transmission
- MLP-Mixer: An all-MLP Architecture for Vision
- Deep Multi-modal Object Detection and Semantic Segmentation for Autonomous Driving: Datasets, Methods, and Challenges
- A Survey of Deep Learning-based Object Detection
- The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks
- AMC: AutoML for Model Compression and Acceleration on Mobile Devices
- Activation Functions: Comparison of trends in Practice and Research for Deep Learning
- Deep Face Recognition: A Survey
- ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices
- Road Damage Detection Using Deep Neural Networks with Images Captured Through a Smartphone
- A Survey of Model Compression and Acceleration for Deep Neural Networks
- Benchmark Analysis of Representative Deep Neural Network Architectures
- Medical Image Segmentation Using Deep Learning: A Survey
- Deep neural network models for computational histopathology: A survey
- Searching for Activation Functions
- PlantDoc: A Dataset for Visual Plant Disease Detection
- Regularized Deep Networks in Intelligent Transportation Systems: A Taxonomy and a Case Study
- A survey on modern trainable activation functions
- Object Detection in 20 Years: A Survey
- Binary Neural Networks: A Survey
- Gather-Excite: Exploiting Feature Context in Convolutional Neural Networks
- A Review on Deep Learning in UAV Remote Sensing
- Monocular Human Pose Estimation: A Survey of Deep Learning-based Methods
- Asynchronous Federated Optimization
- RetinaFace: Single-stage Dense Face Localisation in the Wild
- PC-DARTS: Partial Channel Connections for Memory-Efficient Architecture Search
- Avoiding Overfitting: A Survey on Regularization Methods for Convolutional Neural Networks
- Do ImageNet Classifiers Generalize to ImageNet?
- Advancements in Image Classification using Convolutional Neural Network
- Visual Transformers: Token-based Image Representation and Processing for Computer Vision
- A Survey: Deep Learning for Hyperspectral Image Classification with Few Labeled Samples
- Deep Learning for UAV-based Object Detection and Tracking: A Survey
- Fast-SCNN: Fast Semantic Segmentation Network
- CSPNet: A New Backbone that can Enhance Learning Capability of CNN
- Extracting possibly representative COVID-19 Biomarkers from X-Ray images with Deep Learning approach and image data related to Pulmonary Diseases
- Xception: Deep Learning with Depthwise Separable Convolutions
- Hello Edge: Keyword Spotting on Microcontrollers
- Bayesian Compression for Deep Learning
- Coordinate Attention for Efficient Mobile Network Design
- Point-Voxel CNN for Efficient 3D Deep Learning
- Training and Inference with Integers in Deep Neural Networks
- Wide Activation for Efficient and Accurate Image Super-Resolution
- MixConv: Mixed Depthwise Convolutional Kernels
- Rice Diseases Detection and Classification Using Attention Based Neural Network and Bayesian Optimization
- Split Computing and Early Exiting for Deep Learning Applications: Survey and Research Challenges
- LocalViT: Analyzing Locality in Vision Transformers
- ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware
- Deep learning-based survival prediction for multiple cancer types using histopathology images
- SNAS: Stochastic Neural Architecture Search
- NAS-FAS: Static-Dynamic Central Difference Network Search for Face Anti-Spoofing
- MCUNet: Tiny Deep Learning on IoT Devices
- Pruning by Explaining: A Novel Criterion for Deep Neural Network Pruning
- A Survey of Convolutional Neural Networks: Analysis, Applications, and Prospects
- DARTS+: Improved Differentiable Architecture Search with Early Stopping
- Face Mask Detection using Transfer Learning of InceptionV3
- Deep Dual-resolution Networks for Real-time and Accurate Semantic Segmentation of Road Scenes
- BlazeFace: Sub-millisecond Neural Face Detection on Mobile GPUs
- Depthwise Separable Convolutions for Neural Machine Translation
- Modality specific U-Net variants for biomedical image segmentation: A survey
- Slalom: Fast, Verifiable and Private Execution of Neural Networks in Trusted Hardware
- The impact of patient clinical information on automated skin cancer detection
- ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design
- Single Path One-Shot Neural Architecture Search with Uniform Sampling
- Deep Learning for Generic Object Detection: A Survey
- Slimmable Neural Networks
- Benchmarking TPU, GPU, and CPU Platforms for Deep Learning
- Interpretable Survival Prediction for Colorectal Cancer using Deep Learning
- SimpleShot: Revisiting Nearest-Neighbor Classification for Few-Shot Learning
- Hyperspectral Classification Based on Lightweight 3-D-CNN With Transfer Learning
- Cloudburst: Stateful Functions-as-a-Service
- Federated Learning in the Sky: Aerial-Ground Air Quality Sensing Framework with UAV Swarms
- FastFCN: Rethinking Dilated Convolution in the Backbone for Semantic Segmentation
- EmergencyNet: Efficient Aerial Image Classification for Drone-Based Emergency Monitoring Using Atrous Convolutional Feature Fusion
- Interstellar: Using Halide's Scheduling Language to Analyze DNN Accelerators
- HAT: Hardware-Aware Transformers for Efficient Natural Language Processing
- Stand-Alone Self-Attention in Vision Models
- Integer Quantization for Deep Learning Inference: Principles and Empirical Evaluation
- Hardware and Software Optimizations for Accelerating Deep Neural Networks: Survey of Current Trends, Challenges, and the Road Ahead
- GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond
- Revisiting ResNets: Improved Training and Scaling Strategies
- Demystifying Parallel and Distributed Deep Learning: An In-Depth Concurrency Analysis
- GluonCV and GluonNLP: Deep Learning in Computer Vision and Natural Language Processing
- Skin Lesion Analyser: An Efficient Seven-Way Multi-Class Skin Cancer Classification Using MobileNet
- A Survey on Neural Architecture Search
- Quantization and Deployment of Deep Neural Networks on Microcontrollers
- A Comprehensive Survey of Neural Architecture Search: Challenges and Solutions
- ContextNet: Exploring Context and Detail for Semantic Segmentation in Real-time
- Benchmarking TinyML Systems: Challenges and Direction
- GhostNets on Heterogeneous Devices via Cheap Operations
- Automatic heterogeneous quantization of deep neural networks for low-latency inference on the edge for particle detectors
- You Only Look at One Sequence: Rethinking Transformer in Vision through Object Detection
- Group Knowledge Transfer: Federated Learning of Large CNNs at the Edge
- DarkneTZ: Towards Model Privacy at the Edge using Trusted Execution Environments
- DABNet: Depth-wise Asymmetric Bottleneck for Real-time Semantic Segmentation
- Learning to Optimize Tensor Programs
- Empowering Edge Intelligence: A Comprehensive Survey on On-Device AI Models
- Music Source Separation in the Waveform Domain
- Tensor Methods in Computer Vision and Deep Learning
- Adversarial Example Detection for DNN Models: A Review and Experimental Comparison
- Neural Architecture Transfer
- Spatial Group-wise Enhance: Improving Semantic Feature Learning in Convolutional Networks
- EEG-based Cross-Subject Driver Drowsiness Recognition with an Interpretable Convolutional Neural Network
- MobileSal: Extremely Efficient RGB-D Salient Object Detection
- L1-Norm Batch Normalization for Efficient Training of Deep Neural Networks
- Real-time object detection method based on improved YOLOv4-tiny
- Towards the Systematic Reporting of the Energy and Carbon Footprints of Machine Learning
- Deep-learning-based surrogate flow modeling and geological parameterization for data assimilation in 3D subsurface flow
- Real-time Pose and Shape Reconstruction of Two Interacting Hands With a Single Depth Camera
- Bringing AI To Edge: From Deep Learning's Perspective
- CvT: Introducing Convolutions to Vision Transformers
- TSM: Temporal Shift Module for Efficient Video Understanding
- Accelerating COVID-19 Differential Diagnosis with Explainable Ultrasound Image Analysis
- Progressive Neural Architecture Search
- CornerNet-Lite: Efficient Keypoint Based Object Detection
- DeeperLab: Single-Shot Image Parser
- Discrimination-aware Channel Pruning for Deep Neural Networks
- Evaluating the Robustness of Neural Networks: An Extreme Value Theory Approach
- Speed/accuracy trade-offs for modern convolutional object detectors
- ViTAE: Vision Transformer Advanced by Exploring Intrinsic Inductive Bias
- Discrimination-aware Network Pruning for Deep Model Compression
- Label Refinery: Improving ImageNet Classification through Label Progression
- MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer
- A Comprehensive Overview and Comparative Analysis on Deep Learning Models: CNN, RNN, LSTM, GRU
- Path-Level Network Transformation for Efficient Architecture Search
- Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation
- Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks with Octave Convolution
- Bag of Freebies for Training Object Detection Neural Networks
- AutoSlim: Towards One-Shot Architecture Search for Channel Numbers
- FETCH: A deep-learning based classifier for fast transient classification
- Bag of Tricks for Image Classification with Convolutional Neural Networks
- How to Prove Your Model Belongs to You: A Blind-Watermark based Framework to Protect Intellectual Property of DNN
- Layer-wise training convolutional neural networks with smaller filters for human activity recognition using wearable sensors
- A Survey of FPGA-Based Neural Network Accelerator
- SiamRPN++: Evolution of Siamese Visual Tracking with Very Deep Networks
- Deep Learning for Automatic Pneumonia Detection
- Enable Deep Learning on Mobile Devices: Methods, Systems, and Applications
- High-Throughput CNN Inference on Embedded ARM big.LITTLE Multi-Core Processors
- TVM: An Automated End-to-End Optimizing Compiler for Deep Learning
- Automatic classification between COVID-19 pneumonia, non-COVID-19 pneumonia, and the healthy on chest X-ray image: combination of data augmentation methods
- AI Challenger : A Large-scale Dataset for Going Deeper in Image Understanding
- Progressive Differentiable Architecture Search: Bridging the Depth Gap between Search and Evaluation
- Backdoor Attacks and Countermeasures on Deep Learning: A Comprehensive Review
- TensorFlow.js: Machine Learning for the Web and Beyond
- Exploring Spatial Significance via Hybrid Pyramidal Graph Network for Vehicle Re-identification
- Compact Generalized Non-local Network
- FastDeepIoT: Towards Understanding and Optimizing Neural Network Execution Time on Mobile and Embedded Devices
- Incremental Learning in Deep Convolutional Neural Networks Using Partial Network Sharing
- Deep Learning in Mobile and Wireless Networking: A Survey
- Tip-Adapter: Training-free CLIP-Adapter for Better Vision-Language Modeling
- Towards Learning a Universal Non-Semantic Representation of Speech
- Edge Intelligence: Architectures, Challenges, and Applications
- TPH-YOLOv5: Improved YOLOv5 Based on Transformer Prediction Head for Object Detection on Drone-captured Scenarios
- Interventional Few-Shot Learning
- Compressing Neural Networks using the Variational Information Bottleneck
- Receptive Field Block Net for Accurate and Fast Object Detection
- RetinaMask: Learning to predict masks improves state-of-the-art single-shot detection for free
- Rigging the Lottery: Making All Tickets Winners
- XNOR-Net++: Improved Binary Neural Networks
- Streaming keyword spotting on mobile devices
- Omni-Scale Feature Learning for Person Re-Identification
- BiSeNet V2: Bilateral Network with Guided Aggregation for Real-time Semantic Segmentation
- CorrDetector: A Framework for Structural Corrosion Detection from Drone Images using Ensemble Deep Learning
- GhostNet: More Features from Cheap Operations
- Combining a Convolutional Neural Network with Autoencoders to Predict the Survival Chance of COVID-19 Patients
- DeepCABAC: A Universal Compression Algorithm for Deep Neural Networks
- Recent Advances in Deep Learning: An Overview
- Recent Advances in Object Detection in the Age of Deep Convolutional Neural Networks
- CLIP-Adapter: Better Vision-Language Models with Feature Adapters
- Machine learning and AI-based approaches for bioactive ligand discovery and GPCR-ligand recognition
- Light-Weight RefineNet for Real-Time Semantic Segmentation
- Hardware Acceleration of Sparse and Irregular Tensor Computations of ML Models: A Survey and Insights
- Rethinking on Multi-Stage Networks for Human Pose Estimation
- Dynamic Fusion Module Evolves Drivable Area and Road Anomaly Detection: A Benchmark and Algorithms
- Deep Learning-based Spacecraft Relative Navigation Methods: A Survey
- Review: Deep Learning in Electron Microscopy
- Adaptive Inference through Early-Exit Networks: Design, Challenges and Directions
- RF-Based Human Activity Recognition Using Signal Adapted Convolutional Neural Network
- PointSeg: Real-Time Semantic Segmentation Based on 3D LiDAR Point Cloud
- Siamese Attentional Keypoint Network for High Performance Visual Tracking
- An Empirical Study of Spatial Attention Mechanisms in Deep Networks
- Face Recognition: From Traditional to Deep Learning Methods
- Data-Free Adversarial Distillation
- CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windows
- Tiny-DSOD: Lightweight Object Detection for Resource-Restricted Usages
- Joint Device-Edge Inference over Wireless Links with Pruning
- Pruning Deep Convolutional Neural Networks Architectures with Evolution Strategy
- Pelee: A Real-Time Object Detection System on Mobile Devices
- Soft Threshold Weight Reparameterization for Learnable Sparsity
- Balanced Semi-Supervised Generative Adversarial Network for Damage Assessment from Low-Data Imbalanced-Class Regime
- Edge Intelligence: Paving the Last Mile of Artificial Intelligence with Edge Computing
- Once-for-All: Train One Network and Specialize it for Efficient Deployment
- CycleMLP: A MLP-like Architecture for Dense Prediction
- ATRW: A Benchmark for Amur Tiger Re-identification in the Wild
- Shallow-Deep Networks: Understanding and Mitigating Network Overthinking
- Efficient Two-Stream Network for Violence Detection Using Separable Convolutional LSTM
- PP-LCNet: A Lightweight CPU Convolutional Neural Network
- MetaPruning: Meta Learning for Automatic Neural Network Channel Pruning
- Selective Kernel Networks
- CondenseNet: An Efficient DenseNet using Learned Group Convolutions
- Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networks
- MobileBERT: a Compact Task-Agnostic BERT for Resource-Limited Devices
- The Power of Sparsity in Convolutional Neural Networks
- Accelerator-Aware Pruning for Convolutional Neural Networks
- Real-time monitoring of driver drowsiness on mobile platforms using 3D neural networks
- Loss-aware Weight Quantization of Deep Networks
- Deep -Means: Re-Training and Parameter Sharing with Harder Cluster Assignments for Compressing Deep Convolutions
- Revisiting Shadow Detection: A New Benchmark Dataset for Complex World
- FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search
- Non-Vacuous Generalization Bounds at the ImageNet Scale: A PAC-Bayesian Compression Approach
- Double Similarity Distillation for Semantic Image Segmentation
- What Do Compressed Deep Neural Networks Forget?
- Efficient Facial Representations for Age, Gender and Identity Recognition in Organizing Photo Albums using Multi-output CNN
- Prediction of lung and colon cancer through analysis of histopathological images by utilizing Pre-trained CNN models with visualization of class activation and saliency maps
- Automated interpretation of congenital heart disease from multi-view echocardiograms
- Dynamic Sampling Networks for Efficient Action Recognition in Videos
- Closing the Generalization Gap of Adaptive Gradient Methods in Training Deep Neural Networks
- Measuring the Algorithmic Efficiency of Neural Networks
- MEDIC: A Multi-Task Learning Dataset for Disaster Image Classification
- Paraphrasing Complex Network: Network Compression via Factor Transfer
- Video Classification with Channel-Separated Convolutional Networks
- Visual Wake Words Dataset
- Be Your Own Teacher: Improve the Performance of Convolutional Neural Networks via Self Distillation
- CGNet: A Light-weight Context Guided Network for Semantic Segmentation
- SkyNet: a Hardware-Efficient Method for Object Detection and Tracking on Embedded Systems
- SpArSe: Sparse Architecture Search for CNNs on Resource-Constrained Microcontrollers
- Learning to Decode the Surface Code with a Recurrent, Transformer-Based Neural Network
- Ansor: Generating High-Performance Tensor Programs for Deep Learning
- Exploring Randomly Wired Neural Networks for Image Recognition
- Stabilizing Differentiable Architecture Search via Perturbation-based Regularization
- Deep Learning of Quasar Spectra to Discover and Characterize Damped Lya Systems
- Deep Learning Methods for Solving Linear Inverse Problems: Research Directions and Paradigms
- Spatiotemporal Contrastive Video Representation Learning
- Deep Learning Inference in Facebook Data Centers: Characterization, Performance Optimizations and Hardware Implications
- Heterogeneous Multilayer Generalized Operational Perceptron
- MobiSR: Efficient On-Device Super-Resolution through Heterogeneous Mobile Processors
- Local Motion Planner for Autonomous Navigation in Vineyards with a RGB-D Camera-Based Algorithm and Deep Learning Synergy
- Network Decoupling: From Regular to Depthwise Separable Convolutions
- Net2Vis -- A Visual Grammar for Automatically Generating Publication-Tailored CNN Architecture Visualizations
- Applications and Techniques for Fast Machine Learning in Science
- Deep Neural Network Approximation for Custom Hardware: Where We've Been, Where We're Going
- A Low Effort Approach to Structured CNN Design Using PCA
- Exploiting temporal and depth information for multi-frame face anti-spoofing
- Analyzing Human-Human Interactions: A Survey
- Secure Evaluation of Quantized Neural Networks
- Robust Adversarial Perturbation on Deep Proposal-based Models
- Efficient Deep Learning on Multi-Source Private Data
- Optimizing CNN Model Inference on CPUs
- Efficient and Accurate Arbitrary-Shaped Text Detection with Pixel Aggregation Network
- Pruning neural networks without any data by iteratively conserving synaptic flow
- ViNG: Learning Open-World Navigation with Visual Goals
- MeliusNet: Can Binary Neural Networks Achieve MobileNet-level Accuracy?
- Improving Universal Sound Separation Using Sound Classification
- Learning N:M Fine-grained Structured Sparse Neural Networks From Scratch
- SEED: Self-supervised Distillation For Visual Representation
- Deep Learning for Image Super-resolution: A Survey
- UnsuperPoint: End-to-end Unsupervised Interest Point Detector and Descriptor
- Convolutional Neural Networks with Intermediate Loss for 3D Super-Resolution of CT and MRI Scans
- Learning regression and verification networks for long-term visual tracking
- PANNs: Large-Scale Pretrained Audio Neural Networks for Audio Pattern Recognition
- LEEP: A New Measure to Evaluate Transferability of Learned Representations
- Using Computer Vision to enhance Safety of Workforce in Manufacturing in a Post COVID World
- On the Accuracy of Analog Neural Network Inference Accelerators
- Dynamic Convolution: Attention over Convolution Kernels
- NSGA-Net: Neural Architecture Search using Multi-Objective Genetic Algorithm
- LaneNet: Real-Time Lane Detection Networks for Autonomous Driving
- NetAdapt: Platform-Aware Neural Network Adaptation for Mobile Applications
- Deep Learning Framework to Detect Face Masks from Video Footage
- Sample and Computation Redistribution for Efficient Face Detection
- Towards Practical Verification of Machine Learning: The Case of Computer Vision Systems
- OpenEDS: Open Eye Dataset
- Probabilistic Neural Architecture Search
- Transfer Learning-based Road Damage Detection for Multiple Countries
- DyNet: Dynamic Convolution for Accelerating Convolutional Neural Networks
- BNAS:An Efficient Neural Architecture Search Approach Using Broad Scalable Architecture
- Blockchain-Federated-Learning and Deep Learning Models for COVID-19 detection using CT Imaging
- AddNet: Deep Neural Networks Using FPGA-Optimized Multipliers
- How much real data do we actually need: Analyzing object detection performance using synthetic and real data
- A novel channel pruning method for deep neural network compression
- Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation
- Zero-Cost Proxies for Lightweight NAS
- A Study of Face Obfuscation in ImageNet
- Efficient Multi-objective Neural Architecture Search via Lamarckian Evolution
- And the Bit Goes Down: Revisiting the Quantization of Neural Networks
- EEEA-Net: An Early Exit Evolutionary Neural Architecture Search
- Advanced Dropout: A Model-free Methodology for Bayesian Dropout Optimization
- SLSNet: Skin lesion segmentation using a lightweight generative adversarial network
- ASAP: Architecture Search, Anneal and Prune
- Bridging the Gap Between Computational Photography and Visual Recognition
- RFBNet: Deep Multimodal Networks with Residual Fusion Blocks for RGB-D Semantic Segmentation
- Rethinking the Hyperparameters for Fine-tuning
- ResKD: Residual-Guided Knowledge Distillation
- ConTNet: Why not use convolution and transformer at the same time?
- A Survey on Deep Neural Network Compression: Challenges, Overview, and Solutions
- Discovering Neural Wirings
- PaddleSeg: A High-Efficient Development Toolkit for Image Segmentation
- Empowering Things with Intelligence: A Survey of the Progress, Challenges, and Opportunities in Artificial Intelligence of Things
- Real-time Convolutional Neural Networks for Emotion and Gender Classification
- Classification of Histopathological Biopsy Images Using Ensemble of Deep Learning Networks
- On Deep Learning Techniques to Boost Monocular Depth Estimation for Autonomous Navigation
- Violence detection in videos using deep recurrent and convolutional neural networks
- Acoustic Anomaly Detection for Machine Sounds based on Image Transfer Learning
- Cluster Pruning: An Efficient Filter Pruning Method for Edge AI Vision Applications
- Towards Better Surgical Instrument Segmentation in Endoscopic Vision: Multi-Angle Feature Aggregation and Contour Supervision
- Structured Probabilistic Pruning for Convolutional Neural Network Acceleration
- A Battle of Network Structures: An Empirical Study of CNN, Transformer, and MLP
- Improving Fast Segmentation With Teacher-student Learning
- On-Device Neural Net Inference with Mobile GPUs
- Knowledge Transfer via Distillation of Activation Boundaries Formed by Hidden Neurons
- Behavioral Use Licensing for Responsible AI
- FermiNets: Learning generative machines to generate efficient neural networks via generative synthesis
- Trained Quantization Thresholds for Accurate and Efficient Fixed-Point Inference of Deep Neural Networks
- Modeling Uncertainty with Hedged Instance Embedding
- Lightweight Modules for Efficient Deep Learning based Image Restoration
- AlphaX: eXploring Neural Architectures with Deep Neural Networks and Monte Carlo Tree Search
- Effective and Efficient Dropout for Deep Convolutional Neural Networks
- You Only Hear Once: A YOLO-like Algorithm for Audio Segmentation and Sound Event Detection
- Efficient Convolutional Neural Networks for Depth-Based Multi-Person Pose Estimation
- Compacting Deep Neural Networks for Internet of Things: Methods and Applications
- Driving Scene Perception Network: Real-time Joint Detection, Depth Estimation and Semantic Segmentation
- Security Analysis of Deep Neural Networks Operating in the Presence of Cache Side-Channel Attacks
- ViKiNG: Vision-Based Kilometer-Scale Navigation with Geographic Hints
- Q-BERT: Hessian Based Ultra Low Precision Quantization of BERT
- Driver Behavior Recognition via Interwoven Deep Convolutional Neural Nets with Multi-stream Inputs
- Restructuring Batch Normalization to Accelerate CNN Training
- Introduction to Camera Pose Estimation with Deep Learning
- Gait recognition via deep learning of the center-of-pressure trajectory
- TBC-Net: A real-time detector for infrared small target detection using semantic constraint
- MiniNet: An extremely lightweight convolutional neural network for real-time unsupervised monocular depth estimation
- Effects of Degradations on Deep Neural Network Architectures
- pCAMP: Performance Comparison of Machine Learning Packages on the Edges
- Augment your batch: better training with larger batches
- A Constructive Prediction of the Generalization Error Across Scales
- MCUNetV2: Memory-Efficient Patch-based Inference for Tiny Deep Learning
- FedBABU: Towards Enhanced Representation for Federated Image Classification
- Building Efficient ConvNets using Redundant Feature Pruning
- Learning Generalisable Omni-Scale Representations for Person Re-Identification
- Accelerator-aware Neural Network Design using AutoML
- MEAL V2: Boosting Vanilla ResNet-50 to 80%+ Top-1 Accuracy on ImageNet without Tricks
- HAQ: Hardware-Aware Automated Quantization with Mixed Precision
- Scalable Distributed DNN Training using TensorFlow and CUDA-Aware MPI: Characterization, Designs, and Performance Evaluation
- Decision and Feature Level Fusion of Deep Features Extracted from Public COVID-19 Data-sets
- MobileFaceNets: Efficient CNNs for Accurate Real-Time Face Verification on Mobile Devices
- s-LWSR: Super Lightweight Super-Resolution Network
- LambdaNetworks: Modeling Long-Range Interactions Without Attention
- Unsupervised Domain Adaptation for Mobile Semantic Segmentation based on Cycle Consistency and Feature Alignment
- Tensorized Embedding Layers for Efficient Model Compression
- On-Device Machine Learning: An Algorithms and Learning Theory Perspective
- Deep Mutual Learning
- Compute and memory efficient universal sound source separation
- Model Rubik's Cube: Twisting Resolution, Depth and Width for TinyNets
- Efficient Processing of Deep Neural Networks: A Tutorial and Survey
- ShuffleSeg: Real-time Semantic Segmentation Network
- RepVGG: Making VGG-style ConvNets Great Again
- SUNRISE: A Simple Unified Framework for Ensemble Learning in Deep Reinforcement Learning
- Reweighted Proximal Pruning for Large-Scale Language Representation
- BERT Loses Patience: Fast and Robust Inference with Early Exit
- Chart-Text: A Fully Automated Chart Image Descriptor
- DAIS: Automatic Channel Pruning via Differentiable Annealing Indicator Search
- Adversarial Examples - A Complete Characterisation of the Phenomenon
- Depthwise Separable Convolutional ResNet with Squeeze-and-Excitation Blocks for Small-footprint Keyword Spotting
- K for the Price of 1: Parameter-efficient Multi-task and Transfer Learning
- Back to Simplicity: How to Train Accurate BNNs from Scratch?
- Stabilizing DARTS with Amended Gradient Estimation on Architectural Parameters
- DermGAN: Synthetic Generation of Clinical Skin Images with Pathology
- Towards Unconstrained Palmprint Recognition on Consumer Devices: a Literature Review
- VWA: Hardware Efficient Vectorwise Accelerator for Convolutional Neural Network
- MiniSeg: An Extremely Minimum Network for Efficient COVID-19 Segmentation
- Detecting solar system objects with convolutional neural networks
- Four Things Everyone Should Know to Improve Batch Normalization
- ThunderNet: Towards Real-time Generic Object Detection
- AtomNAS: Fine-Grained End-to-End Neural Architecture Search
- Panoptic-DeepLab: A Simple, Strong, and Fast Baseline for Bottom-Up Panoptic Segmentation
- Attention-guided Chained Context Aggregation for Semantic Segmentation
- CeyMo: See More on Roads -- A Novel Benchmark Dataset for Road Marking Detection
- ClearBuds: Wireless Binaural Earbuds for Learning-Based Speech Enhancement
- Mobile Video Object Detection with Temporally-Aware Feature Maps
- Recent Advances of Continual Learning in Computer Vision: An Overview
- Pruning Algorithms to Accelerate Convolutional Neural Networks for Edge Applications: A Survey
- Refiner: Refining Self-attention for Vision Transformers
- Absolute distance prediction based on deep learning object detection and monocular depth estimation models
- MobileDets: Searching for Object Detection Architectures for Mobile Accelerators
- Shift: A Zero FLOP, Zero Parameter Alternative to Spatial Convolutions
- ExpandNets: Linear Over-parameterization to Train Compact Convolutional Networks
- Fingerprint Presentation Attack Detection by Channel-wise Feature Denoising
- Bounding Box Regression with Uncertainty for Accurate Object Detection
- Comparison and Benchmarking of AI Models and Frameworks on Mobile Devices
- YOLO-LITE: A Real-Time Object Detection Algorithm Optimized for Non-GPU Computers
- Container: Context Aggregation Network
- ASSANet: An Anisotropic Separable Set Abstraction for Efficient Point Cloud Representation Learning
- Dynamic Neural Networks: A Survey
- Rethinking Classification and Localization for Object Detection
- Transfer learning for radio galaxy classification
- BlockDrop: Dynamic Inference Paths in Residual Networks
- You Only Search Once: Single Shot Neural Architecture Search via Direct Sparse Optimization
- Efficiently utilizing complex-valued PolSAR image data via a multi-task deep learning framework
- PocketNet: A Smaller Neural Network for Medical Image Analysis
- Suppress and Balance: A Simple Gated Network for Salient Object Detection
- Convolution with even-sized kernels and symmetric padding
- Improving Electron Micrograph Signal-to-Noise with an Atrous Convolutional Encoder-Decoder
- RWF-2000: An Open Large Scale Video Database for Violence Detection
- Understanding the Disharmony between Dropout and Batch Normalization by Variance Shift
- End-to-End Evaluation of Federated Learning and Split Learning for Internet of Things
- BigNAS: Scaling Up Neural Architecture Search with Big Single-Stage Models
- ShiftAddNet: A Hardware-Inspired Deep Network
- Multimodal and multicontrast image fusion via deep generative models
- EasyQuant: Post-training Quantization via Scale Optimization
- Distilling Policy Distillation
- Rethinking BiSeNet For Real-time Semantic Segmentation
- Improving Efficiency in Convolutional Neural Network with Multilinear Filters
- Temporal Convolution for Real-time Keyword Spotting on Mobile Devices
- Trading-off Accuracy and Energy of Deep Inference on Embedded Systems: A Co-Design Approach
- WoodFisher: Efficient Second-Order Approximation for Neural Network Compression
- Generalizability vs. Robustness: Adversarial Examples for Medical Imaging
- Faasm: Lightweight Isolation for Efficient Stateful Serverless Computing
- FixyNN: Efficient Hardware for Mobile Computer Vision via Transfer Learning
- Adversarial Generation of Training Examples: Applications to Moving Vehicle License Plate Recognition
- Contrastive Self-supervised Neural Architecture Search
- Dual-stream Network for Visual Recognition
- EXTD: Extremely Tiny Face Detector via Iterative Filter Reuse
- Exploiting Robust Unsupervised Video Person Re-identification
- Fast object detection in compressed JPEG Images
- Searching Efficient 3D Architectures with Sparse Point-Voxel Convolution
- On-device Training: A First Overview on Existing Systems
- End-to-end Neural Diarization: From Transformer to Conformer
- Parameter Efficient Multimodal Transformers for Video Representation Learning
- Into the Wild with AudioScope: Unsupervised Audio-Visual Separation of On-Screen Sounds
- Compounding the Performance Improvements of Assembled Techniques in a Convolutional Neural Network
- Knowledge Distillation via Route Constrained Optimization
- Medical Image Classification Using Transfer Learning and Chaos Game Optimization on the Internet of Medical Things
- Low-Memory Neural Network Training: A Technical Report
- ISTA-NAS: Efficient and Consistent Neural Architecture Search by Sparse Coding
- Towards High Performance Video Object Detection for Mobiles
- Applying Domain Randomization to Synthetic Data for Object Category Detection
- When Deep Learning Meets Data Alignment: A Review on Deep Registration Networks (DRNs)
- HAWQ: Hessian AWare Quantization of Neural Networks with Mixed-Precision
- GFD-SSD: Gated Fusion Double SSD for Multispectral Pedestrian Detection
- Kronecker Attention Networks
- Principled Weight Initialization for Hypernetworks
- Deformable Kernels: Adapting Effective Receptive Fields for Object Deformation
- PFLD: A Practical Facial Landmark Detector
- Defensive Quantization: When Efficiency Meets Robustness
- 'Skimming-Perusal' Tracking: A Framework for Real-Time and Robust Long-term Tracking
- A Comprehensive Survey of Machine Learning Applied to Radar Signal Processing
- Autonomous Driving with Deep Learning: A Survey of State-of-Art Technologies
- A Comprehensive and Modularized Statistical Framework for Gradient Norm Equality in Deep Neural Networks
- Attributes Guided Feature Learning for Vehicle Re-identification
- Machine Learning for MU-MIMO Receive Processing in OFDM Systems
- DeepLab2: A TensorFlow Library for Deep Labeling
- Fuzzy Pooling
- f-CNN: A Toolflow for Mapping Multi-CNN Applications on FPGAs
- Searching for Low-Bit Weights in Quantized Neural Networks
- Training Binary Neural Networks through Learning with Noisy Supervision
- ResNet strikes back: An improved training procedure in timm
- Deep Layer Aggregation
- InversionNet3D: Efficient and Scalable Learning for 3D Full Waveform Inversion
- Workpiece Image-based Tool Wear Classification in Blanking Processes Using Deep Convolutional Neural Networks
- TinyML for Ubiquitous Edge AI
- Reinforced Evolutionary Neural Architecture Search
- TinyTL: Reduce Activations, Not Trainable Parameters for Efficient On-Device Learning
- Edge AI: On-Demand Accelerating Deep Neural Network Inference via Edge Computing
- StressNAS: Affect State and Stress Detection Using Neural Architecture Search
- Depthwise Convolution is All You Need for Learning Multiple Visual Domains
- Mind the Pad -- CNNs can Develop Blind Spots
- Understanding Knowledge Distillation in Non-autoregressive Machine Translation
- Smartphone Sensing for the Well-being of Young Adults: A Review
- torchgpipe: On-the-fly Pipeline Parallelism for Training Giant Models
- A Non-Technical Survey on Deep Convolutional Neural Network Architectures
- Towards Optimal Structured CNN Pruning via Generative Adversarial Learning
- Stacked U-Nets: A No-Frills Approach to Natural Image Segmentation
- An Analysis of SVD for Deep Rotation Estimation
- Feature Fusion for Online Mutual Knowledge Distillation
- BinaryDuo: Reducing Gradient Mismatch in Binary Activation Network by Coupling Binary Activations
- QuartzNet: Deep Automatic Speech Recognition with 1D Time-Channel Separable Convolutions
- Training Competitive Binary Neural Networks from Scratch
- OmniPose: A Multi-Scale Framework for Multi-Person Pose Estimation
- DSConv: Efficient Convolution Operator
- Defending Against Machine Learning Model Stealing Attacks Using Deceptive Perturbations
- Accurate and Compact Convolutional Neural Networks with Trained Binarization
- ROMANet: Fine-Grained Reuse-Driven Off-Chip Memory Access Management and Data Organization for Deep Neural Network Accelerators
- TAda! Temporally-Adaptive Convolutions for Video Understanding
- Looking Fast and Slow: Memory-Guided Mobile Video Object Detection
- AM-MobileNet1D: A Portable Model for Speaker Recognition
- EdgeSpeechNets: Highly Efficient Deep Neural Networks for Speech Recognition on the Edge
- Fixed-Point Convolutional Neural Network for Real-Time Video Processing in FPGA
- DenseBody: Directly Regressing Dense 3D Human Pose and Shape From a Single Color Image
- Zero Time Waste: Recycling Predictions in Early Exit Neural Networks
- Data-Driven Sparse Structure Selection for Deep Neural Networks
- Glance and Focus: a Dynamic Approach to Reducing Spatial Redundancy in Image Classification
- Fast, nonlocal and neural: a lightweight high quality solution to image denoising
- ReActNet: Towards Precise Binary Neural Network with Generalized Activation Functions
- Is it enough to optimize CNN architectures on ImageNet?
- Musical Chair: Efficient Real-Time Recognition Using Collaborative IoT Devices
- Dynamic Spatio-temporal Graph-based CNNs for Traffic Prediction
- FBNetV2: Differentiable Neural Architecture Search for Spatial and Channel Dimensions
- SqueezeSegV3: Spatially-Adaptive Convolution for Efficient Point-Cloud Segmentation
- S-MLP: Spatial-Shift MLP Architecture for Vision
- GOLD-NAS: Gradual, One-Level, Differentiable
- Scaling Wide Residual Networks for Panoptic Segmentation
- WIDER Face and Pedestrian Challenge 2018: Methods and Results
- FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation
- RefineDetLite: A Lightweight One-stage Object Detection Framework for CPU-only Devices
- Weight-Sharing Neural Architecture Search: A Battle to Shrink the Optimization Gap
- A Survey of Modern Object Detection Literature using Deep Learning
- Using Videos to Evaluate Image Model Robustness
- Large-Scale Generative Data-Free Distillation
- Reveal of Domain Effect: How Visual Restoration Contributes to Object Detection in Aquatic Scenes
- FedBE: Making Bayesian Model Ensemble Applicable to Federated Learning
- Light-Weight RetinaNet for Object Detection
- Deep Association Learning for Unsupervised Video Person Re-identification
- Dynamic Sparse Training: Find Efficient Sparse Network From Scratch With Trainable Masked Layers
- MobilePose: Real-Time Pose Estimation for Unseen Objects with Weak Shape Supervision
- Memory-Driven Mixed Low Precision Quantization For Enabling Deep Network Inference On Microcontrollers
- Learning Sparse Low-Precision Neural Networks With Learnable Regularization
- IGCV3: Interleaved Low-Rank Group Convolutions for Efficient Deep Neural Networks
- FabricNet: A Fiber Recognition Architecture Using Ensemble ConvNets
- RNNPool: Efficient Non-linear Pooling for RAM Constrained Inference
- COVID-19 Screening Using Residual Attention Network an Artificial Intelligence Approach
- RESA: Recurrent Feature-Shift Aggregator for Lane Detection
- Improving Object Detection from Scratch via Gated Feature Reuse
- CVR-Net: A deep convolutional neural network for coronavirus recognition from chest radiography images
- Channel Compression: Rethinking Information Redundancy among Channels in CNN Architecture
- Scaling Video Analytics on Constrained Edge Nodes
- ShrinkTeaNet: Million-scale Lightweight Face Recognition via Shrinking Teacher-Student Networks
- IamNN: Iterative and Adaptive Mobile Neural Network for Efficient Image Classification
- How Does Batch Normalization Help Binary Training?
- DSNAS: Direct Neural Architecture Search without Parameter Retraining
- Pareto-Optimal Quantized ResNet Is Mostly 4-bit
- Latency-Aware Differentiable Neural Architecture Search
- PP-OCRv2: Bag of Tricks for Ultra Lightweight OCR System
- Scaling Laws for Deep Learning
- VID-WIN: Fast Video Event Matching with Query-Aware Windowing at the Edge for the Internet of Multimedia Things
- Preferences Prediction using a Gallery of Mobile Device based on Scene Recognition and Object Detection
- Learning Guided Convolutional Network for Depth Completion
- AI Benchmark: Running Deep Neural Networks on Android Smartphones
- Multi-frame Feature Aggregation for Real-time Instrument Segmentation in Endoscopic Video
- Training Shallow and Thin Networks for Acceleration via Knowledge Distillation with Conditional Adversarial Networks
- Diagnosis of Autism in Children using Facial Analysis and Deep Learning
- A Performance Comparison of Loss Functions for Deep Face Recognition
- Theory-Inspired Path-Regularized Differential Network Architecture Search
- Nimble: Efficiently Compiling Dynamic Neural Networks for Model Inference
- iQIYI-VID: A Large Dataset for Multi-modal Person Identification
- CEREALS - Cost-Effective REgion-based Active Learning for Semantic Segmentation
- Computing Systems for Autonomous Driving: State-of-the-Art and Challenges
- MARS: Multi-macro Architecture SRAM CIM-Based Accelerator with Co-designed Compressed Neural Networks
- Towards Real-World Blind Face Restoration with Generative Facial Prior
- FedGEMS: Federated Learning of Larger Server Models via Selective Knowledge Fusion
- Task dependent Deep LDA pruning of neural networks
- RC-DARTS: Resource Constrained Differentiable Architecture Search
- AGDC: Automatic Garbage Detection and Collection
- Recent Advances in Deep Learning for Object Detection
- Prototype Guided Federated Learning of Visual Feature Representations
- CSL-YOLO: A New Lightweight Object Detection System for Edge Computing
- ConvMLP: Hierarchical Convolutional MLPs for Vision
- RP2K: A Large-Scale Retail Product Dataset for Fine-Grained Image Classification
- PCONV: The Missing but Desirable Sparsity in DNN Weight Pruning for Real-time Execution on Mobile Devices
- PAN++: Towards Efficient and Accurate End-to-End Spotting of Arbitrarily-Shaped Text
- Quantization for Rapid Deployment of Deep Neural Networks
- NeurObfuscator: A Full-stack Obfuscation Tool to Mitigate Neural Architecture Stealing
- VarGNet: Variable Group Convolutional Neural Network for Efficient Embedded Computing
- AclNet: efficient end-to-end audio classification CNN
- Joint Multi-Dimension Pruning via Numerical Gradient Update
- DeepReDuce: ReLU Reduction for Fast Private Inference
- Auto-Icon+: An Automated End-to-End Code Generation Tool for Icon Designs in UI Development
- Identification of Pediatric Respiratory Diseases Using Fine-grained Diagnosis System
- SquishedNets: Squishing SqueezeNet further for edge device scenarios via deep evolutionary synthesis
- WebFace260M: A Benchmark Unveiling the Power of Million-Scale Deep Face Recognition
- Constructing Fast Network through Deconstruction of Convolution
- Addressing Missing Labels in Large-Scale Sound Event Recognition Using a Teacher-Student Framework With Loss Masking
- Duckiefloat: a Collision-Tolerant Resource-Constrained Blimp for Long-Term Autonomy in Subterranean Environments
- Image Classification with Classic and Deep Learning Techniques
- An efficient solution for semantic segmentation: ShuffleNet V2 with atrous separable convolutions
- Automatic Identification of MHD Modes in Magnetic Fluctuations Spectrograms using Deep Learning Techniques
- DiPair: Fast and Accurate Distillation for Trillion-Scale Text Matching and Pair Modeling
- Towards Robust Learning-Based Pose Estimation of Noncooperative Spacecraft
- Diverse Branch Block: Building a Convolution as an Inception-like Unit
- Similarity of Neural Network Models: A Survey of Functional and Representational Measures
- Self-Binarizing Networks
- End-to-End Supermask Pruning: Learning to Prune Image Captioning Models
- Federated Neural Architecture Search
- A Classification Supervised Auto-Encoder Based on Predefined Evenly-Distributed Class Centroids
- Identity-Driven DeepFake Detection
- Local-to-Global Self-Attention in Vision Transformers
- Towards Effective Low-bitwidth Convolutional Neural Networks
- Sequential Image-based Attention Network for Inferring Force Estimation without Haptic Sensor
- What does it mean to understand a neural network?
- Towards Palmprint Verification On Smartphones
- Packing Sparse Convolutional Neural Networks for Efficient Systolic Array Implementations: Column Combining Under Joint Optimization
- FBNetV3: Joint Architecture-Recipe Search using Predictor Pretraining
- AdderNet and its Minimalist Hardware Design for Energy-Efficient Artificial Intelligence
- Dataset Distillation
- Vehicle Re-Identification: an Efficient Baseline Using Triplet Embedding
- AdaSpring: Context-adaptive and Runtime-evolutionary Deep Model Compression for Mobile Applications
- APQ: Joint Search for Network Architecture, Pruning and Quantization Policy
- Wisdom of Committees: An Overlooked Approach To Faster and More Accurate Models
- Model Slicing for Supporting Complex Analytics with Elastic Inference Cost and Resource Constraints
- GhostSR: Learning Ghost Features for Efficient Image Super-Resolution
- Lightweight Residual Densely Connected Convolutional Neural Network
- LEDNet: A Lightweight Encoder-Decoder Network for Real-Time Semantic Segmentation
- Attention-based Dropout Layer for Weakly Supervised Object Localization
- SqueezeWave: Extremely Lightweight Vocoders for On-device Speech Synthesis
- Probabilistic Dual Network Architecture Search on Graphs
- Characterizing signal propagation to close the performance gap in unnormalized ResNets
- Accelerate CNNs from Three Dimensions: A Comprehensive Pruning Framework
- Randomness In Neural Network Training: Characterizing The Impact of Tooling
- Private Model Compression via Knowledge Distillation
- SkyNet: A Champion Model for DAC-SDC on Low Power Object Detection
- Fighting Quantization Bias With Bias
- Characterizing the Deep Neural Networks Inference Performance of Mobile Applications
- Efficient, high-performance pancreatic segmentation using multi-scale feature extraction
- Quantizing Convolutional Neural Networks for Low-Power High-Throughput Inference Engines
- MAMNet: Multi-path Adaptive Modulation Network for Image Super-Resolution
- Dog Identification using Soft Biometrics and Neural Networks
- Mitigating Edge Machine Learning Inference Bottlenecks: An Empirical Study on Accelerating Google Edge Models
- Resource-Efficient Neural Networks for Embedded Systems
- Improved Techniques for Training Adaptive Deep Networks
- STEERAGE: Synthesis of Neural Networks Using Architecture Search and Grow-and-Prune Methods
- Utilizing Smartphone-Based Machine Learning in Medical Monitor Data Collection: Seven Segment Digit Recognition
- YOLoC: DeploY Large-Scale Neural Network by ROM-based Computing-in-Memory using ResiduaL Branch on a Chip
- Not All Ops Are Created Equal!
- Progressive DARTS: Bridging the Optimization Gap for NAS in the Wild
- Advanced Capsule Networks via Context Awareness
- IPGuard: Protecting Intellectual Property of Deep Neural Networks via Fingerprinting the Classification Boundary
- Feature Pyramid Encoding Network for Real-time Semantic Segmentation
- Marvel: A Data-centric Compiler for DNN Operators on Spatial Accelerators
- MicroNet: Towards Image Recognition with Extremely Low FLOPs
- Rethinking Text Line Recognition Models
- Splitting Steepest Descent for Growing Neural Architectures
- Towards Practical 2D Grapevine Bud Detection with Fully Convolutional Networks
- Deep Learning for Semantic Segmentation on Minimal Hardware
- Accuracy-Efficiency Trade-Offs and Accountability in Distributed ML Systems
- Feature Distillation: DNN-Oriented JPEG Compression Against Adversarial Examples
- CityFlow: A City-Scale Benchmark for Multi-Target Multi-Camera Vehicle Tracking and Re-Identification
- Sparse Transfer Learning via Winning Lottery Tickets
- Joint Neural Architecture Search and Quantization
- Industrial Scale Privacy Preserving Deep Neural Network
- Not All Images are Worth 16x16 Words: Dynamic Transformers for Efficient Image Recognition
- ExtremeC3Net: Extreme Lightweight Portrait Segmentation Networks using Advanced C3-modules
- ZeroQ: A Novel Zero Shot Quantization Framework
- Rate Distortion For Model Compression: From Theory To Practice
- Differentiable Model Compression via Pseudo Quantization Noise
- FRILL: A Non-Semantic Speech Embedding for Mobile Devices
- MANAS: Multi-Agent Neural Architecture Search
- Optimizing speed/accuracy trade-off for person re-identification via knowledge distillation
- Mixed-precision Neural Networks on RISC-V Cores: ISA extensions for Multi-Pumped Soft SIMD Operations
- Deep Learning based approach to detect Customer Age, Gender and Expression in Surveillance Video
- DPP-Net: Device-aware Progressive Search for Pareto-optimal Neural Architectures
- Finite size corrections for neural network Gaussian processes
- Towards Privacy-Preserving Visual Recognition via Adversarial Training: A Pilot Study
- A Panda? No, It's a Sloth: Slowdown Attacks on Adaptive Multi-Exit Neural Network Inference
- ANTNets: Mobile Convolutional Neural Networks for Resource Efficient Image Classification
- Efficient Visual Recognition with Deep Neural Networks: A Survey on Recent Advances and New Directions
- Deep4Air: A Novel Deep Learning Framework for Airport Airside Surveillance
- FoodTracker: A Real-time Food Detection Mobile Application by Deep Convolutional Neural Networks
- A Dataset and Benchmark Towards Multi-Modal Face Anti-Spoofing Under Surveillance Scenarios
- Weight-dependent Gates for Network Pruning
- Projection Convolutional Neural Networks for 1-bit CNNs via Discrete Back Propagation
- Comparison of State-of-the-Art Deep Learning APIs for Image Multi-Label Classification using Semantic Metrics
- Personalized Federated Deep Learning for Pain Estimation From Face Images
- Efficient Accelerator for Dilated and Transposed Convolution with Decomposition
- Dynamic Instance Normalization for Arbitrary Style Transfer
- A Delay Metric for Video Object Detection: What Average Precision Fails to Tell
- End-to-End Entity Classification on Multimodal Knowledge Graphs
- Universally Slimmable Networks and Improved Training Techniques
- ChamNet: Towards Efficient Network Design through Platform-Aware Model Adaptation
- Optimizing the Trade-off between Single-Stage and Two-Stage Object Detectors using Image Difficulty Prediction
- Siamese Box Adaptive Network for Visual Tracking
- HardCoRe-NAS: Hard Constrained diffeRentiable Neural Architecture Search
- Auto-Panoptic: Cooperative Multi-Component Architecture Search for Panoptic Segmentation
- ReNAS:Relativistic Evaluation of Neural Architecture Search
- Adversarial Infidelity Learning for Model Interpretation
- MultiScene: A Large-scale Dataset and Benchmark for Multi-scene Recognition in Single Aerial Images
- Chameleon: Adaptive Code Optimization for Expedited Deep Neural Network Compilation
- Metamorphic Testing for Object Detection Systems
- Design Automation for Efficient Deep Learning Computing
- AdaBits: Neural Network Quantization with Adaptive Bit-Widths
- Learned Low Precision Graph Neural Networks
- Switchable Precision Neural Networks
- Real-time Federated Evolutionary Neural Architecture Search
- Soft-Root-Sign Activation Function
- Breaking Batch Normalization for better explainability of Deep Neural Networks through Layer-wise Relevance Propagation
- Cross-dataset Training for Class Increasing Object Detection
- FQ-Conv: Fully Quantized Convolution for Efficient and Accurate Inference
- Hardware-Centric AutoML for Mixed-Precision Quantization
- Imperceptible Adversarial Examples by Spatial Chroma-Shift
- CFPNet-M: A Light-Weight Encoder-Decoder Based Network for Multimodal Biomedical Image Real-Time Segmentation
- Intersection focused Situation Coverage-based Verification and Validation Framework for Autonomous Vehicles Implemented in CARLA
- Pruning Self-attentions into Convolutional Layers in Single Path
- DSPoint: Dual-scale Point Cloud Recognition with High-frequency Fusion
- Fast and Flexible Human Pose Estimation with HyperPose
- I-BERT: Integer-only BERT Quantization
- How Much Can We Really Trust You? Towards Simple, Interpretable Trust Quantification Metrics for Deep Neural Networks
- Post-Training Piecewise Linear Quantization for Deep Neural Networks
- Knowledge distillation via adaptive instance normalization
- Adapted Center and Scale Prediction: More Stable and More Accurate
- Percival: Making In-Browser Perceptual Ad Blocking Practical With Deep Learning
- Structured Knowledge Distillation for Dense Prediction
- Kernel Transformer Networks for Compact Spherical Convolution
- Graph-Based Global Reasoning Networks
- Structured Binary Neural Networks for Accurate Image Classification and Semantic Segmentation
- Relaxed Quantization for Discretized Neural Networks
- Learning to Train a Binary Neural Network
- Segmentation of Liver Lesions with Reduced Complexity Deep Models
- Target Driven Instance Detection
- The iNaturalist Species Classification and Detection Dataset
- PyHealth: A Python Library for Health Predictive Models
- Multi-Objective Automatic Machine Learning with AutoxgboostMC
- SuPer Deep: A Surgical Perception Framework for Robotic Tissue Manipulation using Deep Learning for Feature Extraction
- MoBiNet: A Mobile Binary Network for Image Classification
- Exchangeable deep neural networks for set-to-set matching and learning
- Taxonomy and Evaluation of Structured Compression of Convolutional Neural Networks
- Addressing the Cold-Start Problem in Outfit Recommendation Using Visual Preference Modelling
- Privacy Aware Offloading of Deep Neural Networks
- Rafiki: Machine Learning as an Analytics Service System
- Transfer Learning for Oral Cancer Detection using Microscopic Images
- Exploiting Errors for Efficiency: A Survey from Circuits to Algorithms
- Efficient Neural Network Training via Forward and Backward Propagation Sparsification
- Biased Mixtures Of Experts: Enabling Computer Vision Inference Under Data Transfer Limitations
- Pooling Pyramid Network for Object Detection
- EdgeNet: Balancing Accuracy and Performance for Edge-based Convolutional Neural Network Object Detectors
- Deep Learning Assessment of galaxy morphology in S-PLUS DataRelease 1
- Hierarchical Dynamic Filtering Network for RGB-D Salient Object Detection
- LeanConvNets: Low-cost Yet Effective Convolutional Neural Networks
- KTAN: Knowledge Transfer Adversarial Network
- AdaViT: Adaptive Vision Transformers for Efficient Image Recognition
- A deep learning based solution for construction equipment detection: from development to deployment
- Deep Mangoes: from fruit detection to cultivar identification in colour images of mango trees
- C3: Concentrated-Comprehensive Convolution and its application to semantic segmentation
- Single-Label Multi-Class Image Classification by Deep Logistic Regression
- Understanding Reuse, Performance, and Hardware Cost of DNN Dataflows: A Data-Centric Approach Using MAESTRO
- Improving Prostate Cancer Detection with Breast Histopathology Images
- Multinomial Distribution Learning for Effective Neural Architecture Search
- Skin disease identification from dermoscopy images using deep convolutional neural network
- Funnel Activation for Visual Recognition
- Evolutionary-Neural Hybrid Agents for Architecture Search
- Continual 3D Convolutional Neural Networks for Real-time Processing of Videos
- ZigZag: A Memory-Centric Rapid DNN Accelerator Design Space Exploration Framework
- FD-MobileNet: Improved MobileNet with a Fast Downsampling Strategy
- An Experimental Study of the Impact of Pre-training on the Pruning of a Convolutional Neural Network
- Efficient Differentiable Neural Architecture Search with Meta Kernels
- DarKnight: A Data Privacy Scheme for Training and Inference of Deep Neural Networks
- The Architectural Implications of Facebook's DNN-based Personalized Recommendation
- To Ensemble or Not Ensemble: When does End-To-End Training Fail?
- ASFD: Automatic and Scalable Face Detector
- MEAL: Multi-Model Ensemble via Adversarial Learning
- CondenseNeXt: An Ultra-Efficient Deep Neural Network for Embedded Systems
- Dynamic Mini-batch SGD for Elastic Distributed Training: Learning in the Limbo of Resources
- EffNet: An Efficient Structure for Convolutional Neural Networks
- AdderNet: Do We Really Need Multiplications in Deep Learning?
- MirBot: A collaborative object recognition system for smartphones using convolutional neural networks
- Zero-Shot Knowledge Distillation from a Decision-Based Black-Box Model
- Learning Efficient Detector with Semi-supervised Adaptive Distillation
- Mobile Video Action Recognition
- SCAN: A Scalable Neural Networks Framework Towards Compact and Efficient Models
- Layer Pruning via Fusible Residual Convolutional Block for Deep Neural Networks
- Searching for Winograd-aware Quantized Networks
- HPLFlowNet: Hierarchical Permutohedral Lattice FlowNet for Scene Flow Estimation on Large-scale Point Clouds
- AReLU: Attention-based Rectified Linear Unit
- DeepObfuscation: Securing the Structure of Convolutional Neural Networks via Knowledge Distillation
- STONNE: A Detailed Architectural Simulator for Flexible Neural Network Accelerators
- Densely Guided Knowledge Distillation using Multiple Teacher Assistants
- AirSim Drone Racing Lab
- Generalization Bounds for Convolutional Neural Networks
- Rethinking Channel Dimensions for Efficient Model Design
- Tracking-by-Trackers with a Distilled and Reinforced Model
- Rethinking Bottleneck Structure for Efficient Mobile Network Design
- One-Shot Pruning of Recurrent Neural Networks by Jacobian Spectrum Evaluation
- Efficient Object Detection Model for Real-Time UAV Applications
- DeepAtom: A Framework for Protein-Ligand Binding Affinity Prediction
- Pixel Difference Networks for Efficient Edge Detection
- CNN-based Facial Affect Analysis on Mobile Devices
- Improving Device-Edge Cooperative Inference of Deep Learning via 2-Step Pruning
- Efficient 3D Fully Convolutional Networks for Pulmonary Lobe Segmentation in CT Images
- Knowledge Squeezed Adversarial Network Compression
- Efficient Segmentation: Learning Downsampling Near Semantic Boundaries
- BlockSwap: Fisher-guided Block Substitution for Network Compression on a Budget
- Multi-Fiber Networks for Video Recognition
- Learnable Embedding Space for Efficient Neural Architecture Compression
- Dense Crowds Detection and Counting with a Lightweight Architecture
- Optimal checkpointing for heterogeneous chains: how to train deep neural networks with limited memory
- Advanced Deep Learning Methodologies for Skin Cancer Classification in Prodromal Stages
- Group Ensemble: Learning an Ensemble of ConvNets in a single ConvNet
- Restricted Recurrent Neural Networks
- A CNN-Based Blind Denoising Method for Endoscopic Images
- Comparing Computing Platforms for Deep Learning on a Humanoid Robot
- WQT and DG-YOLO: towards domain generalization in underwater object detection
- Learning to play the Chess Variant Crazyhouse above World Champion Level with Deep Neural Networks and Human Data
- EagleEye: Fast Sub-net Evaluation for Efficient Neural Network Pruning
- Densely Connected Search Space for More Flexible Neural Architecture Search
- Fine-Grained Neural Architecture Search
- MobileStyleGAN: A Lightweight Convolutional Neural Network for High-Fidelity Image Synthesis
- Shift-based Primitives for Efficient Convolutional Neural Networks
- CoCoPIE: Making Mobile AI Sweet As PIE --Compression-Compilation Co-Design Goes a Long Way
- A White Paper on Neural Network Quantization
- Continual Learning on the Edge with TensorFlow Lite
- Reinforcement Learning and Adaptive Sampling for Optimized DNN Compilation
- Byzantine-Robust and Privacy-Preserving Framework for FedML
- OpenEI: An Open Framework for Edge Intelligence
- Orchestrating the Development Lifecycle of Machine Learning-Based IoT Applications: A Taxonomy and Survey
- Neural networks on microcontrollers: saving memory at inference via operator reordering
- Fix your classifier: the marginal value of training the last weight layer
- Control Distance IoU and Control Distance IoU Loss Function for Better Bounding Box Regression
- RotDCF: Decomposition of Convolutional Filters for Rotation-Equivariant Deep Networks
- Revisiting Dynamic Convolution via Matrix Decomposition
- Deep Reasoning with Multi-Scale Context for Salient Object Detection
- An Embarrassingly Simple Approach for Knowledge Distillation
- Pose Neural Fabrics Search
- SGAS: Sequential Greedy Architecture Search
- A Framework of Transfer Learning in Object Detection for Embedded Systems
- DHP: Differentiable Meta Pruning via HyperNetworks
- Highly Efficient Salient Object Detection with 100K Parameters
- Indices Matter: Learning to Index for Deep Image Matting
- Multi-Scale RCNN Model for Financial Time-series Classification
- Pruning artificial neural networks: a way to find well-generalizing, high-entropy sharp minima
- Generalization bounds for deep learning
- SSFL: Tackling Label Deficiency in Federated Learning via Personalized Self-Supervision
- A Comprehensive Overhaul of Feature Distillation
- LIT: Block-wise Intermediate Representation Training for Model Compression
- Optimization of Quantum-dot Qubit Fabrication via Machine Learning
- DAC-SDC Low Power Object Detection Challenge for UAV Applications
- Road Segmentation Using CNN with GRU
- BoolNet: Minimizing The Energy Consumption of Binary Neural Networks
- Feature Pyramid Grids
- Adaptive Fractional Dilated Convolution Network for Image Aesthetics Assessment
- Real-Time High-Performance Semantic Image Segmentation of Urban Street Scenes
- SIGAN: A Novel Image Generation Method for Solar Cell Defect Segmentation and Augmentation
- Deep Multi-Resolution Dictionary Learning for Histopathology Image Analysis
- RGBD Based Dimensional Decomposition Residual Network for 3D Semantic Scene Completion
- LF-YOLO: A Lighter and Faster YOLO for Weld Defect Detection of X-ray Image
- AttentiveNAS: Improving Neural Architecture Search via Attentive Sampling
- BLK-REW: A Unified Block-based DNN Pruning Framework using Reweighted Regularization Method
- Towards Creating a Deployable Grasp Type Probability Estimator for a Prosthetic Hand
- Neural Architecture Design for GPU-Efficient Networks
- Equivalent and Approximate Transformations of Deep Neural Networks
- An Analysis of Deep Object Detectors For Diver Detection
- Constrained Deep Learning using Conditional Gradient and Applications in Computer Vision
- All You Need is a Few Shifts: Designing Efficient Convolutional Neural Networks for Image Classification
- Long Short-Term Transformer for Online Action Detection
- Distilling Knowledge via Knowledge Review
- Adversarial Alignment of Class Prediction Uncertainties for Domain Adaptation
- Enabling Large Neural Networks on Tiny Microcontrollers with Swapping
- Explicit Shape Encoding for Real-Time Instance Segmentation
- EdgeCNN: Convolutional Neural Network Classification Model with small inputs for Edge Computing
- Automated Design Space Exploration for optimised Deployment of DNN on Arm Cortex-A CPUs
- C3AE: Exploring the Limits of Compact Model for Age Estimation
- AC/DC: Alternating Compressed/DeCompressed Training of Deep Neural Networks
- Towards Compact ConvNets via Structure-Sparsity Regularized Filter Pruning
- LAFFNet: A Lightweight Adaptive Feature Fusion Network for Underwater Image Enhancement
- Differentiable Architecture Search with Ensemble Gumbel-Softmax
- Generalization through Simulation: Integrating Simulated and Real Data into Deep Reinforcement Learning for Vision-Based Autonomous Flight
- Understanding Generalization in Deep Learning via Tensor Methods
- Ternary Hybrid Neural-Tree Networks for Highly Constrained IoT Applications
- Eyeriss v2: A Flexible Accelerator for Emerging Deep Neural Networks on Mobile Devices
- Faa$T: A Transparent Auto-Scaling Cache for Serverless Applications
- Differentiable Fine-grained Quantization for Deep Neural Network Compression
- An Information Theory-inspired Strategy for Automatic Network Pruning
- Rethinking Differentiable Search for Mixed-Precision Neural Networks
- Building Computationally Efficient and Well-Generalizing Person Re-Identification Models with Metric Learning
- Optimizing Video Object Detection via a Scale-Time Lattice
- MicroRec: Efficient Recommendation Inference by Hardware and Data Structure Solutions
- Lite-HRNet: A Lightweight High-Resolution Network
- ACTION-Net: Multipath Excitation for Action Recognition
- GeneCAI: Genetic Evolution for Acquiring Compact AI
- Embedded Real-Time Fall Detection Using Deep Learning For Elderly Care
- NASGEM: Neural Architecture Search via Graph Embedding Method
- AR-Net: Adaptive Frame Resolution for Efficient Action Recognition
- Efficient Neural Architecture Search via Proximal Iterations
- Joint Deep Cross-Domain Transfer Learning for Emotion Recognition
- XSepConv: Extremely Separated Convolution
- AI Blue Book: Vehicle Price Prediction using Visual Features
- Activate or Not: Learning Customized Activation
- Deep Density-aware Count Regressor
- PIRM Challenge on Perceptual Image Enhancement on Smartphones: Report
- A3D: Adaptive 3D Networks for Video Action Recognition
- Deep Face Recognition Model Compression via Knowledge Transfer and Distillation
- Real-time Denoising and Dereverberation with Tiny Recurrent U-Net
- Hard-Attention for Scalable Image Classification
- Rethinking FUN: Frequency-Domain Utilization Networks
- How Do the Hearts of Deep Fakes Beat? Deep Fake Source Detection via Interpreting Residuals with Biological Signals
- Sanity Checks for Lottery Tickets: Does Your Winning Ticket Really Win the Jackpot?
- Highly Efficient Natural Image Matting
- Explaining in Style: Training a GAN to explain a classifier in StyleSpace
- Exploring the Applications of Faster R-CNN and Single-Shot Multi-box Detection in a Smart Nursery Domain
- Efficient Deep Neural Networks
- Weight Normalization based Quantization for Deep Neural Network Compression
- MSG-Transformer: Exchanging Local Spatial Information by Manipulating Messenger Tokens
- DeepLight: Robust & Unobtrusive Real-time Screen-Camera Communication for Real-World Displays
- Learning Deep Representations with Probabilistic Knowledge Transfer
- A Survey on Deep Learning Methods for Semantic Image Segmentation in Real-Time
- Neural Architecture Search using Deep Neural Networks and Monte Carlo Tree Search
- Traceability of Deep Neural Networks
- Ensemble Knowledge Distillation for Learning Improved and Efficient Networks
- Neural Architecture Search for Deep Face Recognition
- Fast and Efficient Zero-Learning Image Fusion
- ApproxNet: Content and Contention-Aware Video Analytics System for Embedded Clients
- SEFR: A Fast Linear-Time Classifier for Ultra-Low Power Devices
- Fingerprint Spoof Generalization
- Ego-Pose Estimation and Forecasting as Real-Time PD Control
- Minimum weight norm models do not always generalize well for over-parameterized problems
- Evolutionary Neural AutoML for Deep Learning
- Cyclic Differentiable Architecture Search
- Building an Integrated Mobile Robotic System for Real-Time Applications in Construction
- A Distributed Hierarchical SGD Algorithm with Sparse Global Reduction
- Depthwise Multiception Convolution for Reducing Network Parameters without Sacrificing Accuracy
- Assurance Monitoring of Cyber-Physical Systems with Machine Learning Components
- Training Compact Neural Networks with Binary Weights and Low Precision Activations
- Face Detection with Feature Pyramids and Landmarks
- Efficient Inference of CNNs via Channel Pruning
- Rethinking Machine Learning Development and Deployment for Edge Devices
- GazeGAN - Unpaired Adversarial Image Generation for Gaze Estimation
- DeepWaste: Applying Deep Learning to Waste Classification for a Sustainable Planet
- Deep Learning in Diabetic Foot Ulcers Detection: A Comprehensive Evaluation
- Rethinking Token-Mixing MLP for MLP-based Vision Backbone
- Fingerprints: Fixed Length Representation via Deep Networks and Domain Knowledge
- Effective Training of Convolutional Neural Networks with Low-bitwidth Weights and Activations
- Wildfire Smoke Detection System: Model Architecture, Training Mechanism, and Dataset
- Growing Efficient Deep Networks by Structured Continuous Sparsification
- Deep Learning Training on the Edge with Low-Precision Posits
- Intra-model Variability in COVID-19 Classification Using Chest X-ray Images
- Compact Global Descriptor for Neural Networks
- Deepfake Video Forensics based on Transfer Learning
- Partial Order Pruning: for Best Speed/Accuracy Trade-off in Neural Architecture Search
- MSCFNet: A Lightweight Network With Multi-Scale Context Fusion for Real-Time Semantic Segmentation
- HCMS: Hierarchical and Conditional Modality Selection for Efficient Video Recognition
- DNNVM : End-to-End Compiler Leveraging Heterogeneous Optimizations on FPGA-based CNN Accelerators
- MnasFPN: Learning Latency-aware Pyramid Architecture for Object Detection on Mobile Devices
- Balanced One-shot Neural Architecture Optimization
- LeYOLO, New Embedded Architecture for Object Detection
- Handwriting recognition and automatic scoring for descriptive answers in Japanese language tests
- FASTER Recurrent Networks for Efficient Video Classification
- SwishNet: A Fast Convolutional Neural Network for Speech, Music and Noise Classification and Segmentation
- Dynamic Region-Aware Convolution
- AttendNets: Tiny Deep Image Recognition Neural Networks for the Edge via Visual Attention Condensers
- MiLeNAS: Efficient Neural Architecture Search via Mixed-Level Reformulation
- Exploration of Quantum Neural Architecture by Mixing Quantum Neuron Designs
- NASI: Label- and Data-agnostic Neural Architecture Search at Initialization
- A(DP)SGD: Asynchronous Decentralized Parallel Stochastic Gradient Descent with Differential Privacy
- SmartExchange: Trading Higher-cost Memory Storage/Access for Lower-cost Computation
- Feature Pyramid Network for Multi-task Affective Analysis
- Towards Improving the Consistency, Efficiency, and Flexibility of Differentiable Neural Architecture Search
- LUTNet: Rethinking Inference in FPGA Soft Logic
- OMPQ: Orthogonal Mixed Precision Quantization
- Energy-Aware Neural Architecture Optimization with Fast Splitting Steepest Descent
- CodeX: Bit-Flexible Encoding for Streaming-based FPGA Acceleration of DNNs
- Benanza: Automatic Benchmark Generation to Compute "Lower-bound" Latency and Inform Optimizations of Deep Learning Models on GPUs
- Real-time Mask Detection on Google Edge TPU
- LiteDenseNet: A Lightweight Network for Hyperspectral Image Classification
- Anycost GANs for Interactive Image Synthesis and Editing
- SwiftNet: Using Graph Propagation as Meta-knowledge to Search Highly Representative Neural Architectures
- FSNet: Compression of Deep Convolutional Neural Networks by Filter Summary
- Real-time Person Re-identification at the Edge: A Mixed Precision Approach
- Bi-Real Net: Binarizing Deep Network Towards Real-Network Performance
- Depth-wise Decomposition for Accelerating Separable Convolutions in Efficient Convolutional Neural Networks
- SparseRT: Accelerating Unstructured Sparsity on GPUs for Deep Learning Inference
- Wise-SrNet: A Novel Architecture for Enhancing Image Classification by Learning Spatial Resolution of Feature Maps
- PhotoSafer: Content-Based and Context-Aware Private Photo Protection for Smartphones
- Learning Metrics from Teachers: Compact Networks for Image Embedding
- IRLAS: Inverse Reinforcement Learning for Architecture Search
- FDFtNet: Facing Off Fake Images using Fake Detection Fine-tuning Network
- AnalogNets: ML-HW Co-Design of Noise-robust TinyML Models and Always-On Analog Compute-in-Memory Accelerator
- Accelerating CNN Training by Pruning Activation Gradients
- Automated Model Design and Benchmarking of 3D Deep Learning Models for COVID-19 Detection with Chest CT Scans
- Low-Complexity Models for Acoustic Scene Classification Based on Receptive Field Regularization and Frequency Damping
- A strong baseline for image and video quality assessment
- TF-NAS: Rethinking Three Search Freedoms of Latency-Constrained Differentiable Neural Architecture Search
- Tango: A Deep Neural Network Benchmark Suite for Various Accelerators
- flexgrid2vec: Learning Efficient Visual Representations Vectors
- Structured Pruning for Efficient ConvNets via Incremental Regularization
- PENNI: Pruned Kernel Sharing for Efficient CNN Inference
- Assessing a mobile-based deep learning model for plant disease surveillance
- AirFace: Lightweight and Efficient Model for Face Recognition
- An Application-Specific VLIW Processor with Vector Instruction Set for CNN Acceleration
- Learning Versatile Convolution Filters for Efficient Visual Recognition
- S2DNAS:Transforming Static CNN Model for Dynamic Inference via Neural Architecture Search
- Making EfficientNet More Efficient: Exploring Batch-Independent Normalization, Group Convolutions and Reduced Resolution Training
- Structured Deep Neural Network Pruning via Matrix Pivoting
- Broadcasted Residual Learning for Efficient Keyword Spotting
- Organ Segmentation From Full-size CT Images Using Memory-Efficient FCN
- Audio Interval Retrieval using Convolutional Neural Networks
- Fully Point-wise Convolutional Neural Network for Modeling Statistical Regularities in Natural Images
- Who wants accurate models? Arguing for a different metrics to take classification models seriously
- Efficient Anytime CLF Reactive Planning System for a Bipedal Robot on Undulating Terrain
- Cascaded channel pruning using hierarchical self-distillation
- Domain-Aware Dynamic Networks
- A Novel Automation-Assisted Cervical Cancer Reading Method Based on Convolutional Neural Network
- Fully-Convolutional Intensive Feature Flow Neural Network for Text Recognition
- LE-HGR: A Lightweight and Efficient RGB-based Online Gesture Recognition Network for Embedded AR Devices
- MNN: A Universal and Efficient Inference Engine
- A Realtime Autonomous Robot Navigation Framework for Human like High-level Interaction and Task Planning in Global Dynamic Environment
- Rethinking Floating Point Overheads for Mixed Precision DNN Accelerators
- Progressive Neural Networks for Image Classification
- An Evaluation of Deep CNN Baselines for Scene-Independent Person Re-Identification
- The Shallow End: Empowering Shallower Deep-Convolutional Networks through Auxiliary Outputs
- Better the Devil you Know: An Analysis of Evasion Attacks using Out-of-Distribution Adversarial Examples
- MSplit LBI: Realizing Feature Selection and Dense Estimation Simultaneously in Few-shot and Zero-shot Learning
- InferBench: Understanding Deep Learning Inference Serving with an Automatic Benchmarking System
- Recurrent Neural Networks for video object detection
- FeatherNets: Convolutional Neural Networks as Light as Feather for Face Anti-spoofing
- Learning Whole-Image Descriptors for Real-time Loop Detection andKidnap Recovery under Large Viewpoint Difference
- A Near-Optimal Algorithm for Debiasing Trained Machine Learning Models
- MEAL: Manifold Embedding-based Active Learning
- Is Robustness the Cost of Accuracy? -- A Comprehensive Study on the Robustness of 18 Deep Image Classification Models
- Bring Your Own Codegen to Deep Learning Compiler
- A Facial Affect Analysis System for Autism Spectrum Disorder
- Manipulating SGD with Data Ordering Attacks
- Exploring Gradient Flow Based Saliency for DNN Model Compression
- Teachers Do More Than Teach: Compressing Image-to-Image Models
- An Features Extraction and Recognition Method for Underwater Acoustic Target Based on ATCNN
- Deep Learning Towards Mobile Applications
- Real Time System for Facial Analysis
- ApproxDet: Content and Contention-Aware Approximate Object Detection for Mobiles
- Characterising Across-Stack Optimisations for Deep Convolutional Neural Networks
- Perceptual Extreme Super Resolution Network with Receptive Field Block
- Accelerating Minibatch Stochastic Gradient Descent using Typicality Sampling
- Reconfigurable Cyber-Physical System for Lifestyle Video-Monitoring via Deep Learning
- Faces à la Carte: Text-to-Face Generation via Attribute Disentanglement
- LRNNet: A Light-Weighted Network with Efficient Reduced Non-Local Operation for Real-Time Semantic Segmentation
- Grafted network for person re-identification
- Deep Learning for Efficient Reconstruction of High-Resolution Turbulent DNS Data
- Learning from Higher-Layer Feature Visualizations
- Visual Localization for Autonomous Driving: Mapping the Accurate Location in the City Maze
- RobFR: Benchmarking Adversarial Robustness on Face Recognition
- PointIT: A Fast Tracking Framework Based on 3D Instance Segmentation
- DCANet: Learning Connected Attentions for Convolutional Neural Networks
- Frustrated with Replicating Claims of a Shared Model? A Solution
- DrNAS: Dirichlet Neural Architecture Search
- Fast Object Detection in Compressed Video
- Multi-Metric Evaluation of Thermal-to-Visual Face Recognition
- Fitting the Search Space of Weight-sharing NAS with Graph Convolutional Networks
- Learning Forward Reuse Distance
- Real-world Mapping of Gaze Fixations Using Instance Segmentation for Road Construction Safety Applications
- Collaborative Distillation for Ultra-Resolution Universal Style Transfer
- A Power-Efficient Binary-Weight Spiking Neural Network Architecture for Real-Time Object Classification
- Generalizable Pedestrian Detection: The Elephant In The Room
- HSD-CNN: Hierarchically self decomposing CNN architecture using class specific filter sensitivity analysis
- Towards Lossless Binary Convolutional Neural Networks Using Piecewise Approximation
- VATLD: A Visual Analytics System to Assess, Understand and Improve Traffic Light Detection
- Orthogonal Convolutional Neural Networks
- Constrained deep neural network architecture search for IoT devices accounting hardware calibration
- Towards High Performance Video Object Detection
- Echo: Compiler-based GPU Memory Footprint Reduction for LSTM RNN Training
- Hazard Detection in Supermarkets using Deep Learning on the Edge
- Multiwavelength classification of X-ray selected galaxy cluster candidates using convolutional neural networks
- Ternary Residual Networks
- AgileNet: Lightweight Dictionary-based Few-shot Learning
- Refactoring Neural Networks for Verification
- Differentiable Dynamic Quantization with Mixed Precision and Adaptive Resolution
- SPARK: Spatial-aware Online Incremental Attack Against Visual Tracking
- Learning Strict Identity Mappings in Deep Residual Networks
- Weight Pruning via Adaptive Sparsity Loss
- Towards Deep and Efficient: A Deep Siamese Self-Attention Fully Efficient Convolutional Network for Change Detection in VHR Images
- Computation-Efficient Knowledge Distillation via Uncertainty-Aware Mixup
- Horizontally Fused Training Array: An Effective Hardware Utilization Squeezer for Training Novel Deep Learning Models
- Validation of a deep learning mammography model in a population with low screening rates
- DRINet: A Dual-Representation Iterative Learning Network for Point Cloud Segmentation
- Multi-task Graph Convolutional Neural Network for Calcification Morphology and Distribution Analysis in Mammograms
- HourNAS: Extremely Fast Neural Architecture Search Through an Hourglass Lens
- Interactive Classification for Deep Learning Interpretation
- AOGNets: Compositional Grammatical Architectures for Deep Learning
- COVID-19 personal protective equipment detection using real-time deep learning methods
- Do Normalization Layers in a Deep ConvNet Really Need to Be Distinct?
- Towards Real-Time Monocular Depth Estimation for Robotics: A Survey
- Neural Epitome Search for Architecture-Agnostic Network Compression
- A Lightweight Neural Network for Monocular View Generation with Occlusion Handling
- Efficient Decoupled Neural Architecture Search by Structure and Operation Sampling
- Real-Time Index Authentication for Event-Oriented Surveillance Video Query using Blockchain
- Light-weight Document Image Cleanup using Perceptual Loss
- Multi Layer Neural Networks as Replacement for Pooling Operations
- Toward Efficient Transfer Learning in 6G
- Road User Detection in Videos
- Efficient Semantic Scene Completion Network with Spatial Group Convolution
- Hire-MLP: Vision MLP via Hierarchical Rearrangement
- Camera View Adjustment Prediction for Improving Image Composition
- Faraway-Frustum: Dealing with Lidar Sparsity for 3D Object Detection using Fusion
- Improved Detection of Adversarial Images Using Deep Neural Networks
- Real-time Memory Efficient Large-pose Face Alignment via Deep Evolutionary Network
- Auxiliary Learning for Deep Multi-task Learning
- Towards large-scale, automated, accurate detection of CCTV camera objects using computer vision. Applications and implications for privacy, safety, and cybersecurity. (Preprint)
- Improving Noise Robustness of an End-to-End Neural Model for Automatic Speech Recognition
- An Image Enhancing Pattern-based Sparsity for Real-time Inference on Mobile Devices
- Observer Dependent Lossy Image Compression
- How deep should be the depth of convolutional neural networks: a backyard dog case study
- Learning Student Networks via Feature Embedding
- Ordering Chaos: Memory-Aware Scheduling of Irregularly Wired Neural Networks for Edge Devices
- Condensation-Net: Memory-Efficient Network Architecture with Cross-Channel Pooling Layers and Virtual Feature Maps
- COP: Customized Deep Model Compression via Regularized Correlation-Based Filter-Level Pruning
- Seesaw-Net: Convolution Neural Network With Uneven Group Convolution
- Squeezed Convolutional Variational AutoEncoder for Unsupervised Anomaly Detection in Edge Device Industrial Internet of Things
- Embedded Large-Scale Handwritten Chinese Character Recognition
- A Semi-Automated Computational Approach for Infrared Dark Cloud Localization: A Catalog of Infrared Dark Clouds
- Real-time Detection, Tracking, and Classification of Moving and Stationary Objects using Multiple Fisheye Images
- VarGFaceNet: An Efficient Variable Group Convolutional Neural Network for Lightweight Face Recognition
- ModuleNet: Knowledge-inherited Neural Architecture Search
- Evolving Search Space for Neural Architecture Search
- Deep Dose Plugin Towards Real-time Monte Carlo Dose Calculation Through a Deep Learning based Denoising Algorithm
- A Highly Configurable Hardware/Software Stack for DNN Inference Acceleration
- Robust Real-time Pedestrian Detection in Aerial Imagery on Jetson TX2
- HM-NAS: Efficient Neural Architecture Search via Hierarchical Masking
- RILOD: Near Real-Time Incremental Learning for Object Detection at the Edge
- ESAI: Efficient Split Artificial Intelligence via Early Exiting Using Neural Architecture Search
- Post-training Quantization with Multiple Points: Mixed Precision without Mixed Precision
- AutoKWS: Keyword Spotting with Differentiable Architecture Search
- Nonuniform-to-Uniform Quantization: Towards Accurate Quantization via Generalized Straight-Through Estimation
- On the Privacy Risks of Cell-Based NAS Architectures
- PRGFlow: Benchmarking SWAP-Aware Unified Deep Visual Inertial Odometry
- Global Context for Convolutional Pose Machines
- Application-driven Privacy-preserving Data Publishing with Correlated Attributes
- KS(conf ): A Light-Weight Test if a ConvNet Operates Outside of Its Specifications
- Energy-Efficient Adaptive Machine Learning on IoT End-Nodes With Class-Dependent Confidence
- SGNet: A Super-class Guided Network for Image Classification and Object Detection
- Guidelines and Benchmarks for Deployment of Deep Learning Models on Smartphones as Real-Time Apps
- Depthwise Spatio-Temporal STFT Convolutional Neural Networks for Human Action Recognition
- Dilated Convolution with Dilated GRU for Music Source Separation
- Pufferfish: Communication-efficient Models At No Extra Cost
- A Convolutional Neural Network-Based Low Complexity Filter
- Learning low-precision neural networks without Straight-Through Estimator(STE)
- Efficient Memory Management for Deep Neural Net Inference
- DOTS: Decoupling Operation and Topology in Differentiable Architecture Search
- Robust Training of Social Media Image Classification Models for Rapid Disaster Response
- Differentiable Sparsification for Deep Neural Networks
- LP-3DCNN: Unveiling Local Phase in 3D Convolutional Neural Networks
- Towards Characterizing Adversarial Defects of Deep Learning Software from the Lens of Uncertainty
- Testing Deep Learning Models for Image Analysis Using Object-Relevant Metamorphic Relations
- Fire SSD: Wide Fire Modules based Single Shot Detector on Edge Device
- FlexSA: Flexible Systolic Array Architecture for Efficient Pruned DNN Model Training
- ZARTS: On Zero-order Optimization for Neural Architecture Search
- Task-Adaptive Neural Network Search with Meta-Contrastive Learning
- CALPA-NET: Channel-pruning-assisted Deep Residual Network for Steganalysis of Digital Images
- LightSAL: Lightweight Sign Agnostic Learning for Implicit Surface Representation
- Binarizing MobileNet via Evolution-based Searching
- 2D or not 2D? Adaptive 3D Convolution Selection for Efficient Video Recognition
- NPAS: A Compiler-aware Framework of Unified Network Pruning and Architecture Search for Beyond Real-Time Mobile Acceleration
- Contrastive Neural Architecture Search with Neural Architecture Comparators
- Hessian-Aware Pruning and Optimal Neural Implant
- Combinatorial Designs for Deep Learning
- A Pre-defined Sparse Kernel Based Convolution for Deep CNNs
- DPRed: Making Typical Activation and Weight Values Matter In Deep Learning Computing
- CFPNet: Channel-wise Feature Pyramid for Real-Time Semantic Segmentation
- Building Proactive Voice Assistants: When and How (not) to Interact
- Deep Scattering Network with Max-pooling
- VA-RED: Video Adaptive Redundancy Reduction
- A Lightweight Structure Aimed to Utilize Spatial Correlation for Sparse-View CT Reconstruction
- Learning Architectures for Binary Networks
- Enabling Socially Competent navigation through incorporating HRI
- RGB-D Based Action Recognition with Light-weight 3D Convolutional Networks
- Spatial-Separated Curve Rendering Network for Efficient and High-Resolution Image Harmonization
- Enhancing Model Assessment in Vision-based Interactive Machine Teaching through Real-time Saliency Map Visualization
- FreqNet: A Frequency-domain Image Super-Resolution Network with Dicrete Cosine Transform
- MixSearch: Searching for Domain Generalized Medical Image Segmentation Architectures
- GestARLite: An On-Device Pointing Finger Based Gestural Interface for Smartphones and Video See-Through Head-Mounts
- Adversarial Examples on Segmentation Models Can be Easy to Transfer
- DKM: Differentiable K-Means Clustering Layer for Neural Network Compression
- Exploiting Channel Similarity for Accelerating Deep Convolutional Neural Networks
- Hybrid Composition with IdleBlock: More Efficient Networks for Image Recognition
- Learning towards Minimum Hyperspherical Energy
- A Low-Cost Neural ODE with Depthwise Separable Convolution for Edge Domain Adaptation on FPGAs
- Integrating Large Circular Kernels into CNNs through Neural Architecture Search
- A Simple Method to Reduce Off-chip Memory Accesses on Convolutional Neural Networks
- Deep Attention Fusion Feature for Speech Separation with End-to-End Post-filter Method
- Automated Model Compression by Jointly Applied Pruning and Quantization
- Report on UG^2+ Challenge Track 1: Assessing Algorithms to Improve Video Object Detection and Classification from Unconstrained Mobility Platforms
- Low-Power Computer Vision: Status, Challenges, Opportunities
- Adaptive Selection of Deep Learning Models on Embedded Systems
- DeepPeep: Exploiting Design Ramifications to Decipher the Architecture of Compact DNNs
- Which *BERT? A Survey Organizing Contextualized Encoders
- Smart at what cost? Characterising Mobile Deep Neural Networks in the wild
- Learning Compact Neural Networks Using Ordinary Differential Equations as Activation Functions
- Do All MobileNets Quantize Poorly? Gaining Insights into the Effect of Quantization on Depthwise Separable Convolutional Networks Through the Eyes of Multi-scale Distributional Dynamics
- Achieving Real-Time LiDAR 3D Object Detection on a Mobile Device
- Geometry-Aware Gradient Algorithms for Neural Architecture Search
- Scene Understanding Networks for Autonomous Driving based on Around View Monitoring System
- DARC: Differentiable ARchitecture Compression
- Automatic Neural Network Compression by Sparsity-Quantization Joint Learning: A Constrained Optimization-based Approach
- Implicit 3D Orientation Learning for 6D Object Detection from RGB Images
- MotionSqueeze: Neural Motion Feature Learning for Video Understanding
- A Mean Field Theory of Quantized Deep Networks: The Quantization-Depth Trade-Off
- Improving Accuracy of Binary Neural Networks using Unbalanced Activation Distribution
- Mixed-Precision Quantized Neural Network with Progressively Decreasing Bitwidth For Image Classification and Object Detection
- Generalized Data Weighting via Class-level Gradient Manipulation
- AppealNet: An Efficient and Highly-Accurate Edge/Cloud Collaborative Architecture for DNN Inference
- FastFlowNet: A Lightweight Network for Fast Optical Flow Estimation
- MUXConv: Information Multiplexing in Convolutional Neural Networks
- Building Efficient Deep Neural Networks with Unitary Group Convolutions
- BusyHands: A Hand-Tool Interaction Database for Assembly Tasks Semantic Segmentation
- Towards Practical Lipreading with Distilled and Efficient Models
- LPRNet: Lightweight Deep Network by Low-rank Pointwise Residual Convolution
- Hyperspectral Classification Based on 3D Asymmetric Inception Network with Data Fusion Transfer Learning
- Open DNN Box by Power Side-Channel Attack
- Leveraging Human Selective Attention for Medical Image Analysis with Limited Training Data
- ML-EXray: Visibility into ML Deployment on the Edge
- Natural & Adversarial Bokeh Rendering via Circle-of-Confusion Predictive Network
- On Machine Learning and Structure for Mobile Robots
- GroupReduce: Block-Wise Low-Rank Approximation for Neural Language Model Shrinking
- IntraQ: Learning Synthetic Images with Intra-Class Heterogeneity for Zero-Shot Network Quantization
- Inference of Recyclable Objects with Convolutional Neural Networks
- On the Distributional Properties of Adaptive Gradients
- Block Convolution: Towards Memory-Efficient Inference of Large-Scale CNNs on FPGA
- DeepWear: Adaptive Local Offloading for On-Wearable Deep Learning
- A Unified Optimization Approach for CNN Model Inference on Integrated GPUs
- Matrix and tensor decompositions for training binary neural networks
- Training Certifiably Robust Neural Networks with Efficient Local Lipschitz Bounds
- Locally Enhanced Self-Attention: Combining Self-Attention and Convolution as Local and Context Terms
- M-FAC: Efficient Matrix-Free Approximations of Second-Order Information
- Energy-efficient Amortized Inference with Cascaded Deep Classifiers
- KVT: k-NN Attention for Boosting Vision Transformers
- Layer Folding: Neural Network Depth Reduction using Activation Linearization
- Skin disease diagnosis with deep learning: a review
- Towards Real-Time Automatic Portrait Matting on Mobile Devices
- Dynamic-OFA: Runtime DNN Architecture Switching for Performance Scaling on Heterogeneous Embedded Platforms
- Effective Sparsification of Neural Networks with Global Sparsity Constraint
- DeepOrganNet: On-the-Fly Reconstruction and Visualization of 3D / 4D Lung Models from Single-View Projections by Deep Deformation Network
- Neural Architecture Search for Lightweight Non-Local Networks
- MobileDepth: Efficient Monocular Depth Prediction on Mobile Devices
- 3D Depthwise Convolution: Reducing Model Parameters in 3D Vision Tasks
- Searching for Fast Model Families on Datacenter Accelerators
- Semi-Supervised Segmentation of Concrete Aggregate Using Consensus Regularisation and Prior Guidance
- CrossStack: A 3-D Reconfigurable RRAM Crossbar Inference Engine
- AVA-Speech: A Densely Labeled Dataset of Speech Activity in Movies
- Predictive Visual Tracking: A New Benchmark and Baseline Approach
- Slimmable Compressive Autoencoders for Practical Neural Image Compression
- Depth Quality-Inspired Feature Manipulation for Efficient RGB-D Salient Object Detection
- E-PixelHop: An Enhanced PixelHop Method for Object Classification
- ForgeryNet: A Versatile Benchmark for Comprehensive Forgery Analysis
- DeepLight: Learning Illumination for Unconstrained Mobile Mixed Reality
- Synthesis and Pruning as a Dynamic Compression Strategy for Efficient Deep Neural Networks
- AlphaNet: Improved Training of Supernets with Alpha-Divergence
- A New Clustering-Based Technique for the Acceleration of Deep Convolutional Networks
- SAIA: Split Artificial Intelligence Architecture for Mobile Healthcare System
- Parallel Residual Bi-Fusion Feature Pyramid Network for Accurate Single-Shot Object Detection
- Fully Learnable Group Convolution for Acceleration of Deep Neural Networks
- ESNet: An Efficient Symmetric Network for Real-time Semantic Segmentation
- Evaluating Off-the-Shelf Machine Listening and Natural Language Models for Automated Audio Captioning
- On Benchmarking Iris Recognition within a Head-mounted Display for AR/VR Application
- A Matrix-in-matrix Neural Network for Image Super Resolution
- Distilling with Performance Enhanced Students
- DC-NAS: Divide-and-Conquer Neural Architecture Search
- The Impact of Reinitialization on Generalization in Convolutional Neural Networks
- Anomaly Detection in Residential Video Surveillance on Edge Devices in IoT Framework
- Neural Machine Translation with Joint Representation
- Randomized Overdrive Neural Networks
- Block Annotation: Better Image Annotation for Semantic Segmentation with Sub-Image Decomposition
- Comprehensive Comparison of Deep Learning Models for Lung and COVID-19 Lesion Segmentation in CT scans
- Collage Inference: Using Coded Redundancy for Low Variance Distributed Image Classification
- Resource Constrained Neural Network Architecture Search: Will a Submodularity Assumption Help?
- Convolutional Neural Network Quantization using Generalized Gamma Distribution
- Fingerprinting Multi-exit Deep Neural Network Models via Inference Time
- Fine-Grained Stochastic Architecture Search
- Discovering Multi-Hardware Mobile Models via Architecture Search
- Self-Supervised Learning of a Biologically-Inspired Visual Texture Model
- SLSGD: Secure and Efficient Distributed On-device Machine Learning
- EfficientHRNet: Efficient Scaling for Lightweight High-Resolution Multi-Person Pose Estimation
- FTPipeHD: A Fault-Tolerant Pipeline-Parallel Distributed Training Framework for Heterogeneous Edge Devices
- Dynamic Group Convolution for Accelerating Convolutional Neural Networks
- Training Meta-Surrogate Model for Transferable Adversarial Attack
- FNA++: Fast Network Adaptation via Parameter Remapping and Architecture Search
- VACL: Variance-Aware Cross-Layer Regularization for Pruning Deep Residual Networks
- REPrune: Filter Pruning via Representative Election
- Jointly Optimizing Preprocessing and Inference for DNN-based Visual Analytics
- End-to-end Interpretable Neural Motion Planner
- Orthant Based Proximal Stochastic Gradient Method for -Regularized Optimization
- Dual-attention Focused Module for Weakly Supervised Object Localization
- Single-Path Mobile AutoML: Efficient ConvNet Design and NAS Hyperparameter Optimization
- Dataflow-based Joint Quantization of Weights and Activations for Deep Neural Networks
- BS-NAS: Broadening-and-Shrinking One-Shot NAS with Searchable Numbers of Channels
- STH: Spatio-Temporal Hybrid Convolution for Efficient Action Recognition
- Learning Efficient Video Representation with Video Shuffle Networks
- Mixup Regularization for Region Proposal based Object Detectors
- SeesawFaceNets: sparse and robust face verification model for mobile platform
- SplitSR: An End-to-End Approach to Super-Resolution on Mobile Devices
- MoGA: Searching Beyond MobileNetV3
- Steepest Descent Neural Architecture Optimization: Escaping Local Optimum with Signed Neural Splitting
- LCP: A Low-Communication Parallelization Method for Fast Neural Network Inference in Image Recognition
- PydMobileNet: Improved Version of MobileNets with Pyramid Depthwise Separable Convolution
- Knowledge Transfer via Dense Cross-Layer Mutual-Distillation
- Automated Rib Fracture Detection of Postmortem Computed Tomography Images Using Machine Learning Techniques
- Frame-To-Frame Consistent Semantic Segmentation
- Learning to discover and localize visual objects with open vocabulary
- Fingerprint Spoof Buster
- Dense Residual Network: Enhancing Global Dense Feature Flow for Character Recognition
- TanhSoft -- a family of activation functions combining Tanh and Softplus
- Binarized Neural Architecture Search for Efficient Object Recognition
- A Survey of Mobile Computing for the Visually Impaired
- FDDWNet: A Lightweight Convolutional Neural Network for Real-time Sementic Segmentation
- FlatteNet: A Simple Versatile Framework for Dense Pixelwise Prediction
- Enhancing a Neurocognitive Shared Visuomotor Model for Object Identification, Localization, and Grasping With Learning From Auxiliary Tasks
- MutualNet: Adaptive ConvNet via Mutual Learning from Network Width and Resolution
- Predicting Terrain Mechanical Properties in Sight for Planetary Rovers with Semantic Clues
- Learning to Fuse Asymmetric Feature Maps in Siamese Trackers
- Neural Pruning via Growing Regularization
- EdgeSegNet: A Compact Network for Semantic Segmentation
- AccelAT: A Framework for Accelerating the Adversarial Training of Deep Neural Networks through Accuracy Gradient
- Hidden-Fold Networks: Random Recurrent Residuals Using Sparse Supermasks
- PAM: Pose Attention Module for Pose-Invariant Face Recognition
- Understanding and Testing Generalization of Deep Networks on Out-of-Distribution Data
- Approximations in Deep Learning
- Low-Cost Parameterizations of Deep Convolutional Neural Networks
- Decentralized Smart Surveillance through Microservices Platform
- A Real-time Low-cost Artificial Intelligence System for Autonomous Spraying in Palm Plantations
- Full-attention based Neural Architecture Search using Context Auto-regression
- P3SGD: Patient Privacy Preserving SGD for Regularizing Deep CNNs in Pathological Image Classification
- MicroNet: Improving Image Recognition with Extremely Low FLOPs
- Deep Neural Models for color discrimination and color constancy
- AdaptCL: Efficient Collaborative Learning with Dynamic and Adaptive Pruning
- Binarized Neural Architecture Search
- AdaDeep: A Usage-Driven, Automated Deep Model Compression Framework for Enabling Ubiquitous Intelligent Mobiles
- 3D Dense Separated Convolution Module for Volumetric Image Analysis
- TensorFlow with user friendly Graphical Framework for object detection API
- Joint Architecture and Knowledge Distillation in CNN for Chinese Text Recognition
- Learning Depthwise Separable Graph Convolution from Data Manifold
- Automated flow for compressing convolution neural networks for efficient edge-computation with FPGA
- ECC: Platform-Independent Energy-Constrained Deep Neural Network Compression via a Bilinear Regression Model
- Salienteye: Maximizing Engagement While Maintaining Artistic Style on Instagram Using Deep Neural Networks
- Knowledge Distillation via Instance-level Sequence Learning
- Dataflow Aware Mapping of Convolutional Neural Networks Onto Many-Core Platforms With Network-on-Chip Interconnect
- ACP: Automatic Channel Pruning via Clustering and Swarm Intelligence Optimization for CNN
- Efficient Integer-Arithmetic-Only Convolutional Neural Networks
- Learning compact generalizable neural representations supporting perceptual grouping
- AnalogNet: Convolutional Neural Network Inference on Analog Focal Plane Sensor Processors
- Tracking e-cigarette warning label compliance on Instagram with deep learning
- Split to Be Slim: An Overlooked Redundancy in Vanilla Convolution
- HGC: Hierarchical Group Convolution for Highly Efficient Neural Network
- Parameter Prediction for Unseen Deep Architectures
- HENet:A Highly Efficient Convolutional Neural Networks Optimized for Accuracy, Speed and Storage
- Principal Component Networks: Parameter Reduction Early in Training
- Analyzing Machine Learning Workloads Using a Detailed GPU Simulator
- Pyramidal Dense Attention Networks for Lightweight Image Super-Resolution
- Fast-Tracker 2.0: Improving Autonomy of Aerial Tracking with Active Vision and Human Location Regression
- Parameter Efficient Deep Neural Networks with Bilinear Projections
- FurcaNeXt: End-to-end monaural speech separation with dynamic gated dilated temporal convolutional networks
- Improving Sickle Cell Disease Classification: A Fusion of Conventional Classifiers, Segmented Images, and Convolutional Neural Networks
- AttendSeg: A Tiny Attention Condenser Neural Network for Semantic Segmentation on the Edge
- Increasing Trustworthiness of Deep Neural Networks via Accuracy Monitoring
- Automated Quality Assessment of Hand Washing Using Deep Learning
- On Learning Semantic Representations for Million-Scale Free-Hand Sketches
- High Performance Depthwise and Pointwise Convolutions on Mobile Devices
- EPNAS: Efficient Progressive Neural Architecture Search
- Recent Advances in Efficient Computation of Deep Convolutional Neural Networks
- HASCO: Towards Agile HArdware and Software CO-design for Tensor Computation
- On the Learning Property of Logistic and Softmax Losses for Deep Neural Networks
- Distributed Low Precision Training Without Mixed Precision
- On-Device Document Classification using multimodal features
- FrostNet: Towards Quantization-Aware Network Architecture Search
- ResNetX: a more disordered and deeper network architecture
- DeepDive: An Integrative Algorithm/Architecture Co-Design for Deep Separable Convolutional Neural Networks
- TENET: A Framework for Modeling Tensor Dataflow Based on Relation-centric Notation
- MVStylizer: An Efficient Edge-Assisted Video Photorealistic Style Transfer System for Mobile Phones
- Learning Sparse & Ternary Neural Networks with Entropy-Constrained Trained Ternarization (EC2T)
- FRDet: Balanced and Lightweight Object Detector based on Fire-Residual Modules for Embedded Processor of Autonomous Driving
- Optimizing Neural Architecture Search using Limited GPU Time in a Dynamic Search Space: A Gene Expression Programming Approach
- Improving On-Screen Sound Separation for Open-Domain Videos with Audio-Visual Self-Attention
- WeightNet: Revisiting the Design Space of Weight Networks
- Capsule network with shortcut routing
- n-hot: Efficient bit-level sparsity for powers-of-two neural network quantization
- Efficient CNN-LSTM based Image Captioning using Neural Network Compression
- Binary Input Layer: Training of CNN models with binary input data
- MemNet: Memory-Efficiency Guided Neural Architecture Search with Augment-Trim learning
- Deep multi-modal networks for book genre classification based on its cover
- Multi-task Learning with Attention for End-to-end Autonomous Driving
- Separable Layers Enable Structured Efficient Linear Substitutions
- PointAR: Efficient Lighting Estimation for Mobile Augmented Reality
- NetAdaptV2: Efficient Neural Architecture Search with Fast Super-Network Training and Architecture Optimization
- LeanResNet: A Low-cost Yet Effective Convolutional Residual Networks
- Disturbance-immune Weight Sharing for Neural Architecture Search
- Proximu$: Efficiently Scaling DNN Inference in Multi-core CPUs through Near-Cache Compute
- Data-Driven Compression of Convolutional Neural Networks
- Face Recognition in Unconstrained Conditions: A Systematic Review
- Propose-and-Attend Single Shot Detector
- TYolov5: A Temporal Yolov5 Detector Based on Quasi-Recurrent Neural Networks for Real-Time Handgun Detection in Video
- DS-Net++: Dynamic Weight Slicing for Efficient Inference in CNNs and Transformers
- An Evolution of CNN Object Classifiers on Low-Resolution Images
- PatchFormer: An Efficient Point Transformer with Patch Attention
- A machine learning environment for evaluating autonomous driving software
- Stacked Temporal Attention: Improving First-person Action Recognition by Emphasizing Discriminative Clips
- ViPNAS: Efficient Video Pose Estimation via Neural Architecture Search
- ExplainFix: Explainable Spatially Fixed Deep Networks
- Improved Speech Separation with Time-and-Frequency Cross-domain Joint Embedding and Clustering
- Resource Rationing for Wireless Federated Learning: Concept, Benefits, and Challenges
- Train-by-Reconnect: Decoupling Locations of Weights from their Values
- Gated Multi-layer Convolutional Feature Extraction Network for Robust Pedestrian Detection
- Beyond Self-Supervision: A Simple Yet Effective Network Distillation Alternative to Improve Backbones
- A First Look at Deep Learning Apps on Smartphones
- Feature Products Yield Efficient Networks
- Refining the Structure of Neural Networks Using Matrix Conditioning
- Graph-Adaptive Pruning for Efficient Inference of Convolutional Neural Networks
- TE-YOLOF: Tiny and efficient YOLOF for blood cell detection
- Fine-grained Data Distribution Alignment for Post-Training Quantization
- Make (Nearly) Every Neural Network Better: Generating Neural Network Ensembles by Weight Parameter Resampling
- ASAP-NMS: Accelerating Non-Maximum Suppression Using Spatially Aware Priors
- Training convolutional neural networks with cheap convolutions and online distillation
- Dynamic Filtering with Large Sampling Field for ConvNets
- Distribution-sensitive Information Retention for Accurate Binary Neural Network
- Swift for TensorFlow: A portable, flexible platform for deep learning
- Differentiable Learning-to-Group Channels via Groupable Convolutional Neural Networks
- WSNet: Compact and Efficient Networks Through Weight Sampling
- Artificial Intelligence for COVID-19 Detection -- A state-of-the-art review
- A free web service for fast COVID-19 classification of chest X-Ray images
- Optimal Quantization for Batch Normalization in Neural Network Deployments and Beyond
- ACDC: Weight Sharing in Atom-Coefficient Decomposed Convolution
- Model-inspired Deep Learning for Light-Field Microscopy with Application to Neuron Localization
- Joint Estimation of Age and Gender from Unconstrained Face Images using Lightweight Multi-task CNN for Mobile Applications
- Efficient Integration of Multi-channel Information for Speaker-independent Speech Separation
- How Unique Is a Face: An Investigative Study
- GAN-Knowledge Distillation for one-stage Object Detection
- ConvNets for Counting: Object Detection of Transient Phenomena in Steelpan Drums
- S2-BNN: Bridging the Gap Between Self-Supervised Real and 1-bit Neural Networks via Guided Distribution Calibration
- Efficient CNN Building Blocks for Encrypted Data
- Correlation Congruence for Knowledge Distillation
- Brain-inspired reverse adversarial examples
- CAM-GAN: Continual Adaptation Modules for Generative Adversarial Networks
- SparseDNN: Fast Sparse Deep Learning Inference on CPUs
- Edge-Cloud Collaborated Object Detection via Difficult-Case Discriminator
- CodeVIO: Visual-Inertial Odometry with Learned Optimizable Dense Depth
- ECG-DelNet: Delineation of Ambulatory Electrocardiograms with Mixed Quality Labeling Using Neural Networks
- deepSELF: An Open Source Deep Self End-to-End Learning Framework
- Adversarial Attack across Datasets
- Embedded Knowledge Distillation in Depth-Level Dynamic Neural Network
- HALP: Hardware-Aware Latency Pruning
- Merging and Evolution: Improving Convolutional Neural Networks for Mobile Applications
- Towards Efficient Convolutional Neural Network for Domain-Specific Applications on FPGA
- SECS: Efficient Deep Stream Processing via Class Skew Dichotomy
- When to Prune? A Policy towards Early Structural Pruning
- FALCON: Lightweight and Accurate Convolution
- GANMEX: One-vs-One Attributions Guided by GAN-based Counterfactual Explanation Baselines
- InfantNet: A Deep Neural Network for Analyzing Infant Vocalizations
- Scheduled Differentiable Architecture Search for Visual Recognition
- Progressive Learning of Low-Precision Networks
- Dynamic Compression Ratio Selection for Edge Inference Systems with Hard Deadlines
- Live Target Detection with Deep Learning Neural Network and Unmanned Aerial Vehicle on Android Mobile Device
- Malware Classification Using Transfer Learning
- A Demonstration of Smart Doorbell Design Using Federated Deep Learning
- Improving Binary Neural Networks through Fully Utilizing Latent Weights
- Developing a Compressed Object Detection Model based on YOLOv4 for Deployment on Embedded GPU Platform of Autonomous System
- Table-Based Neural Units: Fully Quantizing Networks for Multiply-Free Inference
- Efficient Pig Counting in Crowds with Keypoints Tracking and Spatial-aware Temporal Response Filtering
- SlideNet: Fast and Accurate Slide Quality Assessment Based on Deep Neural Networks
- Learning Sparse Mixture of Experts for Visual Question Answering
- Sisyphus: A Cautionary Tale of Using Low-Degree Polynomial Activations in Privacy-Preserving Deep Learning
- Incomplete Dot Products for Dynamic Computation Scaling in Neural Network Inference
- Hand-Gesture-Recognition Based Text Input Method for AR/VR Wearable Devices
- MLPerf Tiny Benchmark
- Low Dimensional Landscape Hypothesis is True: DNNs can be Trained in Tiny Subspaces
- Efficient Uncertainty Estimation for Semantic Segmentation in Videos
- High Frequency Residual Learning for Multi-Scale Image Classification
- DA-NAS: Data Adapted Pruning for Efficient Neural Architecture Search
- Extending Label Smoothing Regularization with Self-Knowledge Distillation
- The 1st Challenge on Remote Physiological Signal Sensing (RePSS)
- SiMaN: Sign-to-Magnitude Network Binarization
- Real-Time Edge Classification: Optimal Offloading under Token Bucket Constraints
- BNAS v2: Learning Architectures for Binary Networks with Empirical Improvements
- Detecting Interlocutor Confusion in Situated Human-Avatar Dialogue: A Pilot Study
- ShadowNet: A Secure and Efficient On-device Model Inference System for Convolutional Neural Networks
- Performance Evaluation of Low-Cost Machine Vision Cameras for Image-Based Grasp Verification
- Balancing Specialization, Generalization, and Compression for Detection and Tracking
- Ranking Neural Checkpoints
- Cross-Model Image Annotation Platform with Active Learning
- Thanks for Nothing: Predicting Zero-Valued Activations with Lightweight Convolutional Neural Networks
- Pre-training without Natural Images
- Towards Efficient Convolutional Network Models with Filter Distribution Templates
- Linear Context Transform Block
- Video Frame Interpolation Transformer
- Tuning Algorithms and Generators for Efficient Edge Inference
- DotFAN: A Domain-transferred Face Augmentation Network for Pose and Illumination Invariant Face Recognition
- Towards Streaming Perception
- TinyGAN: Distilling BigGAN for Conditional Image Generation
- SPEC2: SPECtral SParsE CNN Accelerator on FPGAs
- Real-time Egocentric Gesture Recognition on Mobile Head Mounted Displays
- Doubly Sparse: Sparse Mixture of Sparse Experts for Efficient Softmax Inference
- Device-Cloud Collaborative Learning for Recommendation
- A Survey on Large-scale Machine Learning
- URNet : User-Resizable Residual Networks with Conditional Gating Module
- Universal Adder Neural Networks
- ENAS4D: Efficient Multi-stage CNN Architecture Search for Dynamic Inference
- ModiPick: SLA-aware Accuracy Optimization For Mobile Deep Inference
- VTLayout: Fusion of Visual and Text Features for Document Layout Analysis
- DASNet: Dynamic Activation Sparsity for Neural Network Efficiency Improvement
- Human Face Expressions from Images - 2D Face Geometry and 3D Face Local Motion versus Deep Neural Features
- Sparsity in Deep Neural Networks - An Empirical Investigation with TensorQuant
- Deep Neural Networks for Active Wave Breaking Classification
- Hardware-friendly Neural Network Architecture for Neuromorphic Computing
- Adversarial Robustness through Bias Variance Decomposition: A New Perspective for Federated Learning
- Investigating Emotion-Color Association in Deep Neural Networks
- Genetic Network Architecture Search
- Data Analytics Service Composition and Deployment on Edge Devices
- Convolutional Hough Matching Networks for Robust and Efficient Visual Correspondence
- LCS: Learning Compressible Subspaces for Adaptive Network Compression at Inference Time
- BinArray: A Scalable Hardware Accelerator for Binary Approximated CNNs
- Eye Semantic Segmentation with a Lightweight Model
- Multi-Task Multicriteria Hyperparameter Optimization
- Representative Graph Neural Network
- Accelerating Training of Deep Neural Networks with a Standardization Loss
- Less is More: Accelerating Faster Neural Networks Straight from JPEG
- Half-Space Proximal Stochastic Gradient Method for Group-Sparsity Regularized Problem
- Margin-Based Regularization and Selective Sampling in Deep Neural Networks
- The Pitfall of Evaluating Performance on Emerging AI Accelerators
- Neural Machine Translation: A Review and Survey
- SuperOCR: A Conversion from Optical Character Recognition to Image Captioning
- Robust Membership Encoding: Inference Attacks and Copyright Protection for Deep Learning
- Humans as Path-Finders for Safe Navigation
- Little Motion, Big Results: Using Motion Magnification to Reveal Subtle Tremors in Infants
- Explaining Image Classifiers using Statistical Fault Localization
- Training Sparse Neural Networks using Compressed Sensing
- Accelerating Multi-Model Inference by Merging DNNs of Different Weights
- Robustness of on-device Models: Adversarial Attack to Deep Learning Models on Android Apps
- Seismic Shot Gather Noise Localization Using a Multi-Scale Feature-Fusion-Based Neural Network
- SAFRON: Stitching Across the Frontier for Generating Colorectal Cancer Histology Images
- Understanding Chat Messages for Sticker Recommendation in Messaging Apps
- Matching Guided Distillation
- Practical Assessment of Generalization Performance Robustness for Deep Networks via Contrastive Examples
- Coupled Network for Robust Pedestrian Detection with Gated Multi-Layer Feature Extraction and Deformable Occlusion Handling
- A Light-Weighted Convolutional Neural Network for Bitemporal SAR Image Change Detection
- Weight Equalizing Shift Scaler-Coupled Post-training Quantization
- Self-supervised learning for audio-visual speaker diarization
- AQD: Towards Accurate Fully-Quantized Object Detection
- Improving Efficiency in Neural Network Accelerator Using Operands Hamming Distance optimization
- On the Orthogonality of Knowledge Distillation with Other Techniques: From an Ensemble Perspective
- iToF2dToF: A Robust and Flexible Representation for Data-Driven Time-of-Flight Imaging
- Channel Pruning via Optimal Thresholding
- Searching for Accurate Binary Neural Architectures
- Exploring Weight Symmetry in Deep Neural Networks
- Where Should We Begin? A Low-Level Exploration of Weight Initialization Impact on Quantized Behaviour of Deep Neural Networks
- Dynamic Spatial Verification for Large-Scale Object-Level Image Retrieval
- Sub-pixel face landmarks using heatmaps and a bag of tricks
- Joint Channel and Weight Pruning for Model Acceleration on Moblie Devices
- On the Demystification of Knowledge Distillation: A Residual Network Perspective
- Follow Your Path: a Progressive Method for Knowledge Distillation
- Exploiting Fully Convolutional Network and Visualization Techniques on Spontaneous Speech for Dementia Detection
- Small, Accurate, and Fast Vehicle Re-ID on the Edge: the SAFR Approach
- Advances and Challenges in Deep Lip Reading
- GroupBERT: Enhanced Transformer Architecture with Efficient Grouped Structures
- Active multi-fidelity Bayesian online changepoint detection
- Face mask detection using convolution neural network
- Efficient Semantic Segmentation using Gradual Grouping
- Representation Sharing for Fast Object Detector Search and Beyond
- Compression and Localization in Reinforcement Learning for ATARI Games
- Fast Object Classification and Meaningful Data Representation of Segmented Lidar Instances
- Developing efficient transfer learning strategies for robust scene recognition in mobile robotics using pre-trained convolutional neural networks
- Concurrent Neural Tree and Data Preprocessing AutoML for Image Classification
- Diagonalwise Refactorization: An Efficient Training Method for Depthwise Convolutions
- RecNets: Channel-wise Recurrent Convolutional Neural Networks
- Kerman: A Hybrid Lightweight Tracking Algorithm to Enable Smart Surveillance as an Edge Service
- Understanding the Effects of Pre-Training for Object Detectors via Eigenspectrum
- Client Adaptation improves Federated Learning with Simulated Non-IID Clients
- Parameter Transfer Unit for Deep Neural Networks
- Dense xUnit Networks
- Decentralized Reinforcement Learning for Multi-Target Search and Detection by a Team of Drones
- AIRCHITECT: Learning Custom Architecture Design and Mapping Space
- MODS -- A USV-oriented object detection and obstacle segmentation benchmark
- ISP4ML: Understanding the Role of Image Signal Processing in Efficient Deep Learning Vision Systems
- HBONet: Harmonious Bottleneck on Two Orthogonal Dimensions
- Real-time Keypoints Detection for Autonomous Recovery of the Unmanned Ground Vehicle
- Vehicle Re-Identification in Context
- Knowledge Distillation Meets Self-Supervision
- Fine-Grained Energy and Performance Profiling framework for Deep Convolutional Neural Networks
- Exploring Neural Networks Quantization via Layer-Wise Quantization Analysis
- S4Net: Single Stage Salient-Instance Segmentation
- Learning OFDM Waveforms with PAPR and ACLR Constraints
- A lightweight convolutional neural network for image denoising with fine details preservation capability
- Efficient Action Recognition Using Confidence Distillation
- MLPerf Mobile Inference Benchmark
- Performance Evaluation of Convolutional Neural Networks for Gait Recognition
- Object Detection with Mask-based Feature Encoding
- Fast Adjustable Threshold For Uniform Neural Network Quantization (Winning solution of LPIRC-II)
- Interleaving Learning, with Application to Neural Architecture Search
- ResiliNet: Failure-Resilient Inference in Distributed Neural Networks
- A Fast Knowledge Distillation Framework for Visual Recognition
- RTN: Reparameterized Ternary Network
- PatchNet -- Short-range Template Matching for Efficient Video Processing
- TEA-DNN: the Quest for Time-Energy-Accuracy Co-optimized Deep Neural Networks
- Differentiable Neural Architecture Learning for Efficient Neural Network Design
- IROS 2019 Lifelong Robotic Vision Challenge -- Lifelong Object Recognition Report
- Adversarial-Based Knowledge Distillation for Multi-Model Ensemble and Noisy Data Refinement
- An Attention Module for Convolutional Neural Networks
- A Simple Non-i.i.d. Sampling Approach for Efficient Training and Better Generalization
- MobiVSR: A Visual Speech Recognition Solution for Mobile Devices
- Deep Learning in the Era of Edge Computing: Challenges and Opportunities
- DPNET: Dual-Path Network for Efficient Object Detectioj with Lightweight Self-Attention
- TimeGate: Conditional Gating of Segments in Long-range Activities
- Towards a Generic Diver-Following Algorithm: Balancing Robustness and Efficiency in Deep Visual Detection
- Ultra Power-Efficient CNN Domain Specific Accelerator with 9.3TOPS/Watt for Mobile and Embedded Applications
- ReCU: Reviving the Dead Weights in Binary Neural Networks
- MITAS: A Compressed Time-Domain Audio Separation Network with Parameter Sharing
- Exploiting Activation based Gradient Output Sparsity to Accelerate Backpropagation in CNNs
- SADet: Learning An Efficient and Accurate Pedestrian Detector
- The VVAD-LRS3 Dataset for Visual Voice Activity Detection
- WaveletNet: Logarithmic Scale Efficient Convolutional Neural Networks for Edge Devices
- SwiftSRGAN -- Rethinking Super-Resolution for Efficient and Real-time Inference
- Model Optimization for Deep Space Exploration via Simulators and Deep Learning
- The Unreasonable Effectiveness of Encoder-Decoder Networks for Retinal Vessel Segmentation
- Fast DCTTS: Efficient Deep Convolutional Text-to-Speech
- A Survey on Edge Performance Benchmarking
- Non-Blocking Simultaneous Multithreading: Embracing the Resiliency of Deep Neural Networks
- Post-Training BatchNorm Recalibration
- MDInference: Balancing Inference Accuracy and Latency for Mobile Applications
- Temporally Identity-Aware SSD with Attentional LSTM
- Evaluation of Model Selection for Kernel Fragment Recognition in Corn Silage
- MPDCompress - Matrix Permutation Decomposition Algorithm for Deep Neural Network Compression
- Massively Parallel Video Networks
- Live Reconstruction of Large-Scale Dynamic Outdoor Worlds
- TP-TIO: A Robust Thermal-Inertial Odometry with Deep ThermalPoint
- Efficient Human Pose Estimation with Depthwise Separable Convolution and Person Centroid Guided Joint Grouping
- Learning Universal Shape Dictionary for Realtime Instance Segmentation
- Learning by Self-Explanation, with Application to Neural Architecture Search
- FactorizeNet: Progressive Depth Factorization for Efficient Network Architecture Exploration Under Quantization Constraints
- Multi-objective Neural Architecture Search with Almost No Training
- Energy Drain of the Object Detection Processing Pipeline for Mobile Devices: Analysis and Implications
- An Artificial Intelligence System for Combined Fruit Detection and Georeferencing, Using RTK-Based Perspective Projection in Drone Imagery
- FDNAS: Improving Data Privacy and Model Diversity in AutoML
- Analytical aspects of non-differentiable neural networks
- Fully Quantized Image Super-Resolution Networks
- Channel Pruning via Multi-Criteria based on Weight Dependency
- Dirichlet Pruning for Neural Network Compression
- LogAvgExp Provides a Principled and Performant Global Pooling Operator
- Evaluating robustness of You Only Hear Once(YOHO) Algorithm on noisy audios in the VOICe Dataset
- MOS: A Low Latency and Lightweight Framework for Face Detection, Landmark Localization, and Head Pose Estimation
- ADDS: Adaptive Differentiable Sampling for Robust Multi-Party Learning
- Privacy Aware Person Detection in Surveillance Data
- Scalable Smartphone Cluster for Deep Learning
- Signature-Graph Networks
- Dynamic Slimmable Denoising Network
- Receptive Field Broadening and Boosting for Salient Object Detection
- Scheduling Optimization Techniques for Neural Network Training
- Semi-tensor Product-based TensorDecomposition for Neural Network Compression
- Chaotic-to-Fine Clustering for Unlabeled Plant Disease Images
- Dense Pruning of Pointwise Convolutions in the Frequency Domain
- Complexity-aware Adaptive Training and Inference for Edge-Cloud Distributed AI Systems
- A Separable Temporal Convolution Neural Network with Attention for Small-Footprint Keyword Spotting
- Learning degraded image classification with restoration data fidelity
- StarEnhancer: Learning Real-Time and Style-Aware Image Enhancement
- Training for temporal sparsity in deep neural networks, application in video processing
- A Visual Domain Transfer Learning Approach for Heartbeat Sound Classification
- IC Networks: Remodeling the Basic Unit for Convolutional Neural Networks
- BFTrainer: Low-Cost Training of Neural Networks on Unfillable Supercomputer Nodes
- Self-Reorganizing and Rejuvenating CNNs for Increasing Model Capacity Utilization
- Personalizing Pre-trained Models
- Dynamic Resolution Network
- Towards Accurate and Compact Architectures via Neural Architecture Transformer
- Multi-Scale Temporal Convolution Network for Classroom Voice Detection
- Estimating the Robustness of Classification Models by the Structure of the Learned Feature-Space
- cofga: A Dataset for Fine Grained Classification of Objects from Aerial Imagery
- PAL: Intelligence Augmentation using Egocentric Visual Context Detection
- A multimodal deep learning framework for scalable content based visual media retrieval
- A VM/Containerized Approach for Scaling TinyML Applications
- An efficient deep learning hashing neural network for mobile visual search
- Perception Framework through Real-Time Semantic Segmentation and Scene Recognition on a Wearable System for the Visually Impaired
- Loss Landscape Dependent Self-Adjusting Learning Rates in Decentralized Stochastic Gradient Descent
- Temporally Resolution Decrement: Utilizing the Shape Consistency for Higher Computational Efficiency
- Background Activation Suppression for Weakly Supervised Object Localization
- Automatic Identification and Description of Jewelry Through Computer Vision and Neural Networks for Translators and Interpreters
- Similarity Transfer for Knowledge Distillation
- Dynamic Slimmable Network
- Shift-and-Balance Attention
- Multi-view Feature Augmentation with Adaptive Class Activation Mapping
- Complementary Relation Contrastive Distillation
- ParaDiS: Parallelly Distributable Slimmable Neural Networks
- Fed2: Feature-Aligned Federated Learning
- Semi-Online Knowledge Distillation
- Inter-channel Conv-TasNet for multichannel speech enhancement
- Arch-Net: Model Distillation for Architecture Agnostic Model Deployment
- A Survey of Large-Scale Deep Learning Serving System Optimization: Challenges and Opportunities
- Token Pooling in Vision Transformers
- Projective Manifold Gradient Layer for Deep Rotation Regression
- CondenseNet V2: Sparse Feature Reactivation for Deep Networks
- MS-DARTS: Mean-Shift Based Differentiable Architecture Search
- Rapid Elastic Architecture Search under Specialized Classes and Resource Constraints
- Greedy Network Enlarging
- Learning to Cascade: Confidence Calibration for Improving the Accuracy and Computational Cost of Cascade Inference Systems
- Joint Matrix Decomposition for Deep Convolutional Neural Networks Compression
- "BNN - BN = ?": Training Binary Neural Networks without Batch Normalization
- Zero-Cost Operation Scoring in Differentiable Architecture Search
- ShortcutFusion: From Tensorflow to FPGA-based accelerator with reuse-aware memory allocation for shortcut data
- All-You-Can-Fit 8-Bit Flexible Floating-Point Format for Accurate and Memory-Efficient Inference of Deep Neural Networks
- APNN-TC: Accelerating Arbitrary Precision Neural Networks on Ampere GPU Tensor Cores
- Adaptive Test-Time Augmentation for Low-Power CPU
- Context Prior for Scene Segmentation
- Towards Inference Delivery Networks: Distributing Machine Learning with Optimality Guarantees
- Energy Predictive Models for Convolutional Neural Networks on Mobile Platforms
- Decoupled Dynamic Filter Networks
- CASSOD-Net: Cascaded and Separable Structures of Dilated Convolution for Embedded Vision Systems and Applications
- One Backward from Ten Forward, Subsampling for Large-Scale Deep Learning
- Regression on Deep Visual Features using Artificial Neural Networks (ANNs) to Predict Hydraulic Blockage at Culverts
- Lightweight Mask R-CNN for Long-Range Wireless Power Transfer Systems
- Optimizing the Whole-life Cost in End-to-end CNN Acceleration
- Orderly Dual-Teacher Knowledge Distillation for Lightweight Human Pose Estimation
- Hybrid Attention for Automatic Segmentation of Whole Fetal Head in Prenatal Ultrasound Volumes
- The Elastic Lottery Ticket Hypothesis
- Deep Sensing of Urban Waterlogging
- Spending Your Winning Lottery Better After Drawing It
- Augmentation Inside the Network
- Finet: Using Fine-grained Batch Normalization to Train Light-weight Neural Networks
- Multi-level Knowledge Distillation via Knowledge Alignment and Correlation
- OD-SGD: One-step Delay Stochastic Gradient Descent for Distributed Training
- Multi-level Feature Fusion-based CNN for Local Climate Zone Classification from Sentinel-2 Images: Benchmark Results on the So2Sat LCZ42 Dataset
- TASO: Time and Space Optimization for Memory-Constrained DNN Inference
- Classifying Suspicious Content in Tor Darknet
- R-TOD: Real-Time Object Detector with Minimized End-to-End Delay for Autonomous Driving
- Direct Federated Neural Architecture Search
- AI-based BMI Inference from Facial Images: An Application to Weight Monitoring
- LiteDepthwiseNet: An Extreme Lightweight Network for Hyperspectral Image Classification
- S3ML: A Secure Serving System for Machine Learning Inference
- Toward Building Safer Smart Homes for the People with Disabilities
- An Efficient Quantitative Approach for Optimizing Convolutional Neural Networks
- Semi-Streaming Architecture: A New Design Paradigm for CNN Implementation on FPGAs
- AIPerf: Automated machine learning as an AI-HPC benchmark
- NeuralScale: Efficient Scaling of Neurons for Resource-Constrained Deep Neural Networks
- Neural Architecture Search as Sparse Supernet
- Resolution Switchable Networks for Runtime Efficient Image Recognition
- RoadNet-RT: High Throughput CNN Architecture and SoC Design for Real-Time Road Segmentation
- The Heterogeneity Hypothesis: Finding Layer-Wise Differentiated Network Architectures
- SkyScapes -- Fine-Grained Semantic Understanding of Aerial Scenes
- Multigrid-in-Channels Architectures for Wide Convolutional Neural Networks
- Convolutional Neural Network for emotion recognition to assist psychiatrists and psychologists during the COVID-19 pandemic: experts opinion
- StRDAN: Synthetic-to-Real Domain Adaptation Network for Vehicle Re-Identification
- Fully Dynamic Inference with Deep Neural Networks
- Prune2Edge: A Multi-Phase Pruning Pipelines to Deep Ensemble Learning in IIoT
- Real-Time Semantic Segmentation via Auto Depth, Downsampling Joint Decision and Feature Aggregation
- Handwritten Character Recognition from Wearable Passive RFID
- DP-Net: Dynamic Programming Guided Deep Neural Network Compression
- Channel Pruning Guided by Classification Loss and Feature Importance
- BiDet: An Efficient Binarized Object Detector
- Structured Sparsification with Joint Optimization of Group Convolution and Channel Shuffle
- Spatiotemporal Action Recognition in Restaurant Videos
- MCENET: Multi-Context Encoder Network for Homogeneous Agent Trajectory Prediction in Mixed Traffic
- One Weight Bitwidth to Rule Them All
- SurveilEdge: Real-time Video Query based on Collaborative Cloud-Edge Deep Learning
- Embedded Systems and Computer Vision Techniques utilized in Spray Painting Robots: A Review
- Graph Pruning for Model Compression
- Go Wider: An Efficient Neural Network for Point Cloud Analysis via Group Convolutions
- Context-Gated Convolution
- Simplifying Neural Networks using Formal Verification
- Cross-Channel Intragroup Sparsity Neural Network
- A System-Level Solution for Low-Power Object Detection
- IMMVP: An Efficient Daytime and Nighttime On-Road Object Detector
- PolyResponse: A Rank-based Approach to Task-Oriented Dialogue with Application in Restaurant Search and Booking
- Class-dependent Compression of Deep Neural Networks
- Scale Calibrated Training: Improving Generalization of Deep Networks via Scale-Specific Normalization
- Event Recognition with Automatic Album Detection based on Sequential Processing, Neural Attention and Image Captioning
- PSDNet and DPDNet: Efficient channel expansion, Depthwise-Pointwise-Depthwise Inverted Bottleneck Block
- Dual Attention MobDenseNet(DAMDNet) for Robust 3D Face Alignment
- Understanding the Disharmony between Weight Normalization Family and Weight Decay: shifted Regularizer
- Grounding Human-to-Vehicle Advice for Self-driving Vehicles
- Group Pruning using a Bounded-Lp norm for Group Gating and Regularization
- Full-Stack Filters to Build Minimum Viable CNNs
- Attention-Aware Linear Depthwise Convolution for Single Image Super-Resolution
- RRNet: Repetition-Reduction Network for Energy Efficient Decoder of Depth Estimation
- An Inter-Layer Weight Prediction and Quantization for Deep Neural Networks based on a Smoothly Varying Weight Hypothesis
- Diversifying Inference Path Selection: Moving-Mobile-Network for Landmark Recognition
- Protecting Geolocation Privacy of Photo Collections
- Filter Bank Regularization of Convolutional Neural Networks
- Greenery Segmentation In Urban Images By Deep Learning
- A Machine Learning Imaging Core using Separable FIR-IIR Filters
- Dynamic Routing Networks
- Robust, Extensible, and Fast: Teamed Classifiers for Vehicle Tracking and Vehicle Re-ID in Multi-Camera Networks
- Point-of-Care Diabetic Retinopathy Diagnosis: A Standalone Mobile Application Approach
- Widening and Squeezing: Towards Accurate and Efficient QNNs
- MDLdroid: a ChainSGD-reduce Approach to Mobile Deep Learning for Personal Mobile Sensing
- CRL: Class Representative Learning for Image Classification
- NeuroFabric: Identifying Ideal Topologies for Training A Priori Sparse Networks
- An Efficient Method of Training Small Models for Regression Problems with Knowledge Distillation
- Neural Inheritance Relation Guided One-Shot Layer Assignment Search
- FLAME: A Self-Adaptive Auto-labeling System for Heterogeneous Mobile Processors
- ADWPNAS: Architecture-Driven Weight Prediction for Neural Architecture Search
- Studying the Plasticity in Deep Convolutional Neural Networks using Random Pruning
- CamLoc: Pedestrian Location Detection from Pose Estimation on Resource-constrained Smart-cameras
- Channel-wise pruning of neural networks with tapering resource constraint
- Neural Rejuvenation: Improving Deep Network Training by Enhancing Computational Resource Utilization
- Light-weighted Saliency Detection with Distinctively Lower Memory Cost and Model Size
- Composite Binary Decomposition Networks
- ShuffleDet: Real-Time Vehicle Detection Network in On-board Embedded UAV Imagery
- Information-Theoretic Understanding of Population Risk Improvement with Model Compression
- ExGate: Externally Controlled Gating for Feature-based Attention in Artificial Neural Networks
- Dynamic Multi-path Neural Network
- Manifestation of Image Contrast in Deep Networks
- A mixed signal architecture for convolutional neural networks
- Integrating Multiple Receptive Fields through Grouped Active Convolution
- MassFace: an efficient implementation using triplet loss for face recognition
- Face Image Reflection Removal
- DepthwiseGANs: Fast Training Generative Adversarial Networks for Realistic Image Synthesis
- Realtime Rooftop Landing Site Identification and Selection in Urban City Simulation
- Deep Octonion Networks
- Improved Generalization of Heading Direction Estimation for Aerial Filming Using Semi-supervised Regression
- COFGA: Classification Of Fine-Grained Features In Aerial Images
- IEA: Inner Ensemble Average within a convolutional neural network
- Road Segmentation Using CNN and Distributed LSTM
- Robust Student Network Learning
- I/O Lower Bounds for Auto-tuning of Convolutions in CNNs
- Metric Embedding Autoencoders for Unsupervised Cross-Dataset Transfer Learning
- Person Identification with Visual Summary for a Safe Access to a Smart Home
- ESFNet: Efficient Network for Building Extraction from High-Resolution Aerial Images
- Deployment of Customized Deep Learning based Video Analytics On Surveillance Cameras
- Semantically Selective Augmentation for Deep Compact Person Re-Identification
- Creating Lightweight Object Detectors with Model Compression for Deployment on Edge Devices
- "Tom" pet robot applied to urban autism
- Quantization Mimic: Towards Very Tiny CNN for Object Detection
- Oculum afficit: Ocular Affect Recognition
- Egocentric 6-DoF Tracking of Small Handheld Objects
- Low-memory convolutional neural networks through incremental depth-first processing
- Training a Binary Weight Object Detector by Knowledge Transfer for Autonomous Driving
- CompactNet: Platform-Aware Automatic Optimization for Convolutional Neural Networks
- Toward Runtime-Throttleable Neural Networks
- Deep Learning Acceleration Techniques for Real Time Mobile Vision Applications
- Spectral Image Visualization Using Generative Adversarial Networks
- Global Context Networks
- EfficientPose: Efficient Human Pose Estimation with Neural Architecture Search
- Efficient Incorporation of Multiple Latency Targets in the Once-For-All Network
- Deep Model Compression Via Two-Stage Deep Reinforcement Learning
- Energy Efficient Hardware for On-Device CNN Inference via Transfer Learning
- Learning to Prevent Leakage: Privacy-Preserving Inference in the Mobile Cloud
- A Distributed Framework to Orchestrate Video Analytics Applications
- Compressing Facial Makeup Transfer Networks by Collaborative Distillation and Kernel Decomposition
- Modular network for high accuracy object detection
- Non-contact Real time Eye Gaze Mapping System Based on Deep Convolutional Neural Network
- Compression of descriptor models for mobile applications
- Object Detection-Based Variable Quantization Processing
- Bosch Deep Learning Hardware Benchmark
- Efficient Video Understanding via Layered Multi Frame-Rate Analysis
- Mobile Networks for Computer Go
- DAIL: Dataset-Aware and Invariant Learning for Face Recognition
- Emergent symbolic language based deep medical image classification
- Learning Connectivity of Neural Networks from a Topological Perspective
- Object Detection in the Context of Mobile Augmented Reality
- Training Domain Specific Models for Energy-Efficient Object Detection
- Towards Modality Transferable Visual Information Representation with Optimal Model Compression
- RethNet: Object-by-Object Learning for Detecting Facial Skin Problems
- Multilayer Dense Connections for Hierarchical Concept Classification
- Accelerate 3D Object Processing via Spectral Layout
- Machine Learning with Clos Networks
- Low-Rank+Sparse Tensor Compression for Neural Networks
- GPCA: A Probabilistic Framework for Gaussian Process Embedded Channel Attention
- Transfer Learning with Binary Neural Networks
- Communication-Efficient Separable Neural Network for Distributed Inference on Edge Devices
- Pacemaker: Intermediate Teacher Knowledge Distillation For On-The-Fly Convolutional Neural Network
- A Benchmarking Framework for Interactive 3D Applications in the Cloud
- Boundary-Aware Dense Feature Indicator for Single-Stage 3D Object Detection from Point Clouds
- Accelerating Deep Learning Inference with Cross-Layer Data Reuse on GPUs
- Incremental Cross-Domain Adaptation for Robust Retinopathy Screening via Bayesian Deep Learning
- DD-CNN: Depthwise Disout Convolutional Neural Network for Low-complexity Acoustic Scene Classification
- Tamed Warping Network for High-Resolution Semantic Video Segmentation
- On-device Filtering of Social Media Images for Efficient Storage
- Dataset Culling: Towards Efficient Training Of Distillation-Based Domain Specific Models
- One of these (Few) Things is Not Like the Others
- MICIK: MIning Cross-Layer Inherent Similarity Knowledge for Deep Model Compression
- Resource-Efficient Speech Mask Estimation for Multi-Channel Speech Enhancement
- Efficient Structured Pruning and Architecture Searching for Group Convolution
- NeuroMAX: A High Throughput, Multi-Threaded, Log-Based Accelerator for Convolutional Neural Networks
- JNR: Joint-based Neural Rig Representation for Compact 3D Face Modeling
- Screen Tracking for Clinical Translation of Live Ultrasound Image Analysis Methods
- Novel Adaptive Binary Search Strategy-First Hybrid Pyramid- and Clustering-Based CNN Filter Pruning Method without Parameters Setting
- Conditioned Time-Dilated Convolutions for Sound Event Detection
- Explainable, automated urban interventions to improve pedestrian and vehicle safety
- Phantom: A High-Performance Computational Core for Sparse Convolutional Neural Networks
- Deeply Shared Filter Bases for Parameter-Efficient Convolutional Neural Networks
- Discretization-Aware Architecture Search
- Right for the Right Reason: Making Image Classification Robust
- A Generalized Meta-loss function for regression and classification using privileged information
- Illumination-invariant Face recognition by fusing thermal and visual images via gradient transfer
- All-Weather Object Recognition Using Radar and Infrared Sensing
- Joslim: Joint Widths and Weights Optimization for Slimmable Neural Networks
- Cluster Regularized Quantization for Deep Networks Compression
- BNAS-v2: Memory-efficient and Performance-collapse-prevented Broad Neural Architecture Search
- DSXplore: Optimizing Convolutional Neural Networks via Sliding-Channel Convolutions
- Real-time Action Recognition with Dissimilarity-based Training of Specialized Module Networks
- MSR-DARTS: Minimum Stable Rank of Differentiable Architecture Search
- Automatic Photo to Ideophone Manga Matching
- CooGAN: A Memory-Efficient Framework for High-Resolution Facial Attribute Editing
- JIT-Masker: Efficient Online Distillation for Background Matting
- Grow-Push-Prune: aligning deep discriminants for effective structural network compression
- Sparsifying and Down-scaling Networks to Increase Robustness to Distortions
- clcNet: Improving the Efficiency of Convolutional Neural Network using Channel Local Convolutions
- Penetrating the Fog: the Path to Efficient CNN Models
- A Comparative Study of U-Net Topologies for Background Removal in Histopathology Images
- AutoBSS: An Efficient Algorithm for Block Stacking Style Search
- LETI: Latency Estimation Tool and Investigation of Neural Networks inference on Mobile GPU
- Activation Map Adaptation for Effective Knowledge Distillation
- A Study on Trees's Knots Prediction from their Bark Outer-Shape
- SpotPatch: Parameter-Efficient Transfer Learning for Mobile Object Detection
- Be Your Own Best Competitor! Multi-Branched Adversarial Knowledge Transfer
- Elastic Neural Networks for Classification
- Lightweight, Dynamic Graph Convolutional Networks for AMR-to-Text Generation
- Accelerating Neural Network Inference by Overflow Aware Quantization
- EIS -- a family of activation functions combining Exponential, ISRU, and Softplus
- Coarse and fine-grained automatic cropping deep convolutional neural network
- GHFP: Gradually Hard Filter Pruning
- Softer Pruning, Incremental Regularization
- BitSplit-Net: Multi-bit Deep Neural Network with Bitwise Activation Function
- On evaluating CNN representations for low resource medical image classification
- Dirty Pixels: Towards End-to-End Image Processing and Perception
- Robustness-aware 2-bit quantization with real-time performance for neural network
- Optimising the Performance of Convolutional Neural Networks across Computing Systems using Transfer Learning
- MobileFace: 3D Face Reconstruction with Efficient CNN Regression
- Deep Learning Derived Histopathology Image Score for Increasing Phase 3 Clinical Trial Probability of Success
- Large Scale Indexing of Generic Medical Image Data using Unbiased Shallow Keypoints and Deep CNN Features
- Dense Dual-Path Network for Real-time Semantic Segmentation
- Feature Statistics Guided Efficient Filter Pruning
- Effective Model Compression via Stage-wise Pruning
- Efficient Fusion of Sparse and Complementary Convolutions
- MixMix: All You Need for Data-Free Compression Are Feature and Data Mixing
- Cross-filter compression for CNN inference acceleration
- A CNN Accelerator on FPGA Using Depthwise Separable Convolution
- MicroNet for Efficient Language Modeling
- RetinotopicNet: An Iterative Attention Mechanism Using Local Descriptors with Global Context
- Deep Medical Image Analysis with Representation Learning and Neuromorphic Computing
- SmartDeal: Re-Modeling Deep Network Weights for Efficient Inference and Training
- User-centric Composable Services: A New Generation of Personal Data Analytics
- GraCIAS: Grassmannian of Corrupted Images for Adversarial Security
- Classification of Industrial Control Systems screenshots using Transfer Learning
- Hybrid Cosine Based Convolutional Neural Networks
- Hands-on Guidance for Distilling Object Detectors
- Spectral Tensor Train Parameterization of Deep Learning Layers
- MBS: Macroblock Scaling for CNN Model Reduction
- C2S2: Cost-aware Channel Sparse Selection for Progressive Network Pruning
- Selective Output Smoothing Regularization: Regularize Neural Networks by Softening Output Distributions
- Unpaired Single-Image Depth Synthesis with cycle-consistent Wasserstein GANs
- Network Space Search for Pareto-Efficient Spaces
- Towards Real-Time DNN Inference on Mobile Platforms with Model Pruning and Compiler Optimization
- Diagonal Memory Optimisation for Machine Learning on Micro-controllers
- Landmark-Aware and Part-based Ensemble Transfer Learning Network for Facial Expression Recognition from Static images
- Carrying out CNN Channel Pruning in a White Box
- Spatially Attentive Output Layer for Image Classification
- Width Transfer: On the (In)variance of Width Optimization
- Explore the Knowledge contained in Network Weights to Obtain Sparse Neural Networks
- Group Feature Learning and Domain Adversarial Neural Network for aMCI Diagnosis System Based on EEG
- Itsy Bitsy SpiderNet: Fully Connected Residual Network for Fraud Detection
- Anchor-based Plain Net for Mobile Image Super-Resolution
- Backtracking gradient descent method for general functions, with applications to Deep Learning
- Balancing Accuracy and Latency in Multipath Neural Networks
- Deep Virtual Networks for Memory Efficient Inference of Multiple Tasks
- Neural Architecture Search via Combinatorial Multi-Armed Bandit
- Automatic Non-Linear Video Editing Transfer
- Distilling Image Classifiers in Object Detectors
- Extreme Value Preserving Networks
- Place recognition survey: An update on deep learning approaches
- Abiotic Stress Prediction from RGB-T Images of Banana Plantlets
- Deep Tiny Network for Recognition-Oriented Face Image Quality Assessment
- Learning to Generate Content-Aware Dynamic Detectors
- RingCNN: Exploiting Algebraically-Sparse Ring Tensors for Energy-Efficient CNN-Based Computational Imaging
- AsymmNet: Towards ultralight convolution neural networks using asymmetrical bottlenecks
- LightFuse: Lightweight CNN based Dual-exposure Fusion
- Detection of preventable fetal distress during labor from scanned cardiotocogram tracings using deep learning
- AffectiveNet: Affective-Motion Feature Learningfor Micro Expression Recognition
- Annealing Knowledge Distillation
- Filter Pre-Pruning for Improved Fine-tuning of Quantized Deep Neural Networks
- Self-supervised Knowledge Distillation Using Singular Value Decomposition
- VisBuddy -- A Smart Wearable Assistant for the Visually Challenged
- Visual Domain Adaptation for Monocular Depth Estimation on Resource-Constrained Hardware
- Evolving Neural Architecture Using One Shot Model
- Block-Cyclic Stochastic Coordinate Descent for Deep Neural Networks
- Adaptive Precision Training for Resource Constrained Devices
- Auto Deep Compression by Reinforcement Learning Based Actor-Critic Structure
- HPTQ: Hardware-Friendly Post Training Quantization
- ISyNet: Convolutional Neural Networks design for AI accelerator
- Prioritized Subnet Sampling for Resource-Adaptive Supernet Training
- Integrating Information Theory and Adversarial Learning for Cross-modal Retrieval
- -LBI: Stochastic Split Linearized Bregman Iterations for Parsimonious Deep Learning
- Binary Neural Network for Speaker Verification
- ConAM: Confidence Attention Module for Convolutional Neural Networks
- The Efficiency Misnomer
- Wearable Travel Aid for Environment Perception and Navigation of Visually Impaired People
- Selective Deep Convolutional Neural Network for Low Cost Distorted Image Classification
- BRIEF: Backward Reduction of CNNs with Information Flow Analysis
- Full-stack Optimization for Accelerating CNNs with FPGA Validation
- Training Multi-bit Quantized and Binarized Networks with A Learnable Symmetric Quantizer
- Elastic Neural Networks: A Scalable Framework for Embedded Computer Vision
- Action Recognition with Kernel-based Graph Convolutional Networks
- High-quality Low-dose CT Reconstruction Using Convolutional Neural Networks with Spatial and Channel Squeeze and Excitation
- Knowledge Distillation By Sparse Representation Matching
- Leveraging Implicit Spatial Information in Global Features for Image Retrieval
- How Well Do Sparse Imagenet Models Transfer?
- Learning Pruned Structure and Weights Simultaneously from Scratch: an Attention based Approach
- On Generalization of Adaptive Methods for Over-parameterized Linear Regression
- A Lightweight Graph Transformer Network for Human Mesh Reconstruction from 2D Human Pose
- Deep Learning Approximation: Zero-Shot Neural Network Speedup
- Enabling Design Methodologies and Future Trends for Edge AI: Specialization and Co-design
- Multi-Glimpse Network: A Robust and Efficient Classification Architecture based on Recurrent Downsampled Attention
- Convergence and Stability of the Stochastic Proximal Point Algorithm with Momentum
- A Survey on Green Deep Learning
- Expert Human-Level Driving in Gran Turismo Sport Using Deep Reinforcement Learning with Image-based Representation
- Factorial Convolution Neural Networks
- Searching for TrioNet: Combining Convolution with Local and Global Self-Attention
- Two-Stage Monte Carlo Denoising with Adaptive Sampling and Kernel Pool
- VideoPose: Estimating 6D object pose from videos
- Small-Group Learning, with Application to Neural Architecture Search
- Delving into Rectifiers in Style-Based Image Translation
- A Dense Tensor Accelerator with Data Exchange Mesh for DNN and Vision Workloads
- Asian Giant Hornet Control based on Image Processing and Biological Dispersal
- Improving Differentiable Architecture Search with a Generative Model
- Learning from Mistakes based on Class Weighting with Application to Neural Architecture Search
- Real-time Human Detection Model for Edge Devices
- Differentiable Network Adaption with Elastic Search Space
- Dynamic Domain Adaptation for Efficient Inference
- Transfer Learning-based Real-time Handgun Detection
- BlockDoor: Blocking Backdoor Based Watermarks in Deep Neural Networks
- Improved knowledge distillation by utilizing backward pass knowledge in neural networks
- Depth estimation on embedded computers for robot swarms in forest
- Putting 3D Spatially Sparse Networks on a Diet
- PokeBNN: A Binary Pursuit of Lightweight Accuracy
- 3rd Place Solution for NeurIPS 2021 Shifts Challenge: Vehicle Motion Prediction
- Green Accelerated Hoeffding Tree
- Semantic Relation Preserving Knowledge Distillation for Image-to-Image Translation
- Towards a Sample Efficient Reinforcement Learning Pipeline for Vision Based Robotics
- Content-adaptive Representation Learning for Fast Image Super-resolution
- DTNN: Energy-efficient Inference with Dendrite Tree Inspired Neural Networks for Edge Vision Applications
- PSRR-MaxpoolNMS: Pyramid Shifted MaxpoolNMS with Relationship Recovery
- Scorpion detection and classification systems based on computer vision and deep learning for health security purposes
- Approximate Random Dropout
- Single Image Depth Prediction with Wavelet Decomposition
- Internal node bagging
- Robust Real-Time Pedestrian Detection on Embedded Devices
- CDN-MEDAL: Two-stage Density and Difference Approximation Framework for Motion Analysis
- LLC: Accurate, Multi-purpose Learnt Low-dimensional Binary Codes
- Lightweight Combinational Machine Learning Algorithm for Sorting Canine Torso Radiographs
- Depthwise Separable Convolutions Allow for Fast and Memory-Efficient Spectral Normalization
- Go Small and Similar: A Simple Output Decay Brings Better Performance
- SGE net: Video object detection with squeezed GRU and information entropy map
- using multiple losses for accurate facial age estimation
- CoEdge: Cooperative DNN Inference with Adaptive Workload Partitioning over Heterogeneous Edge Devices
- Edge Computing Enabled by Unmanned Autonomous Vehicles
- Quantized Neural Networks via {-1, +1} Encoding Decomposition and Acceleration
- Gradient-Based Interpretability Methods and Binarized Neural Networks
- LV-BERT: Exploiting Layer Variety for BERT
- Seeing Convolution Through the Eyes of Finite Transformation Semigroup Theory: An Abstract Algebraic Interpretation of Convolutional Neural Networks
- Doing good by fighting fraud: Ethical anti-fraud systems for mobile payments
- Normalized Label Distribution: Towards Learning Calibrated, Adaptable and Efficient Activation Maps
- Architecture Agnostic Neural Networks
- Mutually-aware Sub-Graphs Differentiable Architecture Search
- Performance landscape of resource-constrained platforms targeting DNNs
- Online Filter Clustering and Pruning for Efficient Convnets
- CompConv: A Compact Convolution Module for Efficient Feature Learning
- Cyclic orthogonal convolutions for long-range integration of features
- Form2Seq : A Framework for Higher-Order Form Structure Extraction
- Multi-Modal Association based Grouping for Form Structure Extraction
- AutoFL: Enabling Heterogeneity-Aware Energy Efficient Federated Learning
- Super Interaction Neural Network
- A Survey of Machine Learning Techniques for Detecting and Diagnosing COVID-19 from Imaging
- Log-Polar Space Convolution for Convolutional Neural Networks
- Parallel Blockwise Knowledge Distillation for Deep Neural Network Compression
- MixFaceNets: Extremely Efficient Face Recognition Networks
- Distributional Depth-Based Estimation of Object Articulation Models
- WeClick: Weakly-Supervised Video Semantic Segmentation with Click Annotations
- One-Shot Object Affordance Detection in the Wild
- Learning Deep Multimodal Feature Representation with Asymmetric Multi-layer Fusion
- FOX-NAS: Fast, On-device and Explainable Neural Architecture Search
- Multi-granularity for knowledge distillation
- Sonic: A Sampling-based Online Controller for Streaming Applications
- Multi-Precision Quantized Neural Networks via Encoding Decomposition of -1 and +1
- Analyze and Design Network Architectures by Recursion Formulas
- Separable Temporal Convolution plus Temporally Pooled Attention for Lightweight High-performance Keyword Spotting
- Power-Based Attacks on Spatial DNN Accelerators
- Exploring and Improving Mobile Level Vision Transformers
- Canoe : A System for Collaborative Learning for Neural Nets
- AIP: Adversarial Iterative Pruning Based on Knowledge Transfer for Convolutional Neural Networks
- Architecture Aware Latency Constrained Sparse Neural Networks
- Does Melania Trump have a body double from the perspective of automatic face recognition?
- Tom: Leveraging trend of the observed gradients for faster convergence
- Multi-Scale Aligned Distillation for Low-Resolution Detection
- DEM Super-Resolution with EfficientNetV2
- Recurrent Residual Module for Fast Inference in Videos
- Classification of COVID-19 from CXR Images in a 15-class Scenario: an Attempt to Avoid Bias in the System
- Summarize and Search: Learning Consensus-aware Dynamic Convolution for Co-Saliency Detection
- Approximation Algorithms for Cascading Prediction Models
- MyFood: A Food Segmentation and Classification System to Aid Nutritional Monitoring
- Accelerate Distributed Stochastic Descent for Nonconvex Optimization with Momentum
- Heterogeneous Dual-Core Overlay Processor for Light-Weight CNNs
- Boosted Locality Sensitive Hashing: Discriminative Binary Codes for Source Separation
- PolyScientist: Automatic Loop Transformations Combined with Microkernels for Optimization of Deep Learning Primitives
- Analyzing the Dependency of ConvNets on Spatial Information
- Are Accelerometers for Activity Recognition a Dead-end?
- SafeNet: An Assistive Solution to Assess Incoming Threats for Premises
- Improve SGD Training via Aligning Mini-batches
- Effects of annotation granularity in deep learning models for histopathological images
- Efficient Modelling Across Time of Human Actions and Interactions
- Empirical Study on the Software Engineering Practices in Open Source ML Package Repositories
- The Low-Resource Double Bind: An Empirical Study of Pruning for Low-Resource Machine Translation
- An Analysis of Object Representations in Deep Visual Trackers
- End-to-end Keyword Spotting using Xception-1d
- FSD: Feature Skyscraper Detector for Stem End and Blossom End of Navel Orange
- Towards Building a Real Time Mobile Device Bird Counting System Through Synthetic Data Training and Model Compression
- CRCEN: A Generalized Cost-sensitive Neural Network Approach for Imbalanced Classification
- A Comparative Study of High-Recall Real-Time Semantic Segmentation Based on Swift Factorized Network
- Radius Adaptive Convolutional Neural Network
- Model Adaption Object Detection System for Robot
- Architecture-aware Network Pruning for Vision Quality Applications
- DupNet: Towards Very Tiny Quantized CNN with Improved Accuracy for Face Detection
- Continuous Trade-off Optimization between Fast and Accurate Deep Face Detectors
- MERIT: Tensor Transform for Memory-Efficient Vision Processing on Parallel Architectures
- Space-Time-Separable Graph Convolutional Network for Pose Forecasting
- DAC: Data-free Automatic Acceleration of Convolutional Networks
- Weight Evolution: Improving Deep Neural Networks Training through Evolving Inferior Weight Values
- Mobile Recognition of Wikipedia Featured Sites using Deep Learning and Crowd-sourced Imagery
- Universal Physical Camouflage Attacks on Object Detectors
- Comb Convolution for Efficient Convolutional Architecture
- What Happens on the Edge, Stays on the Edge: Toward Compressive Deep Learning
- CheckNet: Secure Inference on Untrusted Devices
- Sub-bit Neural Networks: Learning to Compress and Accelerate Binary Neural Networks
- POD: Practical Object Detection with Scale-Sensitive Network
- Unknown Identity Rejection Loss: Utilizing Unlabeled Data for Face Recognition
- Adaptive and Iteratively Improving Recurrent Lateral Connections
- Fast Portrait Segmentation with Highly Light-weight Network
- Attention-Guided Lightweight Network for Real-Time Segmentation of Robotic Surgical Instruments
- Handcrafted vs Deep Learning Classification for Scalable Video QoE Modeling
- ERNet Family: Hardware-Oriented CNN Models for Computational Imaging Using Block-Based Inference
- A Unifying Framework of Bilinear LSTMs
- IC-Network: Efficient Structure for Convolutional Neural Networks
- Compressing Deep Convolutional Neural Networks by Stacking Low-dimensional Binary Convolution Filters
- Scalability vs. Utility: Do We Have to Sacrifice One for the Other in Data Importance Quantification?
- Machine Vision for Improved Human-Robot Cooperation in Adverse Underwater Conditions
- BAMSProd: A Step towards Generalizing the Adaptive Optimization Methods to Deep Binary Model
- Self-grouping Convolutional Neural Networks
- Artificial Intelligence in Surgery: Neural Networks and Deep Learning
- Virtual Experience to Real World Application: Sidewalk Obstacle Avoidance Using Reinforcement Learning for Visually Impaired