Training Compact Neural Networks with Binary Weights and Low Precision Activations
Explore this paper's citation graph
Summary
The proposed network with binary weights and low-bitwidth activations, named Group-Net, outperform the previous best binary neural network in terms of accuracy as well as saving more than 5 times computational complexity on ImageNet with ResNet-18 and Res net-50.
- Type
- preprint
- Published
- 2018-08-08
- Cited by
- 14
- References
- 44
- Access
- Open access
- OpenAlex
- https://openalex.org/W2887204394
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:51941823
Keywords
Computer science, Feature (linguistics), Binary number, Set (abstract data type), Artificial neural network
References
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- You Only Look Once: Unified, Real-Time Object Detection
- BinaryConnect: Training Deep Neural Networks with binary weights during propagations
- Fully convolutional networks for semantic segmentation
- Going deeper with convolutions
- ImageNet Large Scale Visual Recognition Challenge
- ImageNet classification with deep convolutional neural networks
- Rethinking the Inception Architecture for Computer Vision
- Deep Residual Learning for Image Recognition
- Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation
- Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning
- SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <1MB model size
- An Analysis of Deep Neural Network Models for Practical Applications
- DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients
- Xception: Deep Learning with Depthwise Separable Convolutions
- Aggregated Residual Transformations for Deep Neural Networks
- Loss-aware Binarization of Deep Networks
- Deep Learning with Low Precision by Half-Wave Gaussian Quantization
- Incremental Network Quantization: Towards Lossless CNNs with Low-Precision Weights
- MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
Cited by
- Mixed Precision Quantization of ConvNets via Differentiable Neural Architecture Search
- Additive Noise Annealing and Approximation Properties of Quantized Neural Networks
- Efficient Deep Neural Networks
- A Novel Compound Synapse Using Probabilistic Spin–Orbit-Torque Switching for MTJ-Based Deep Neural Networks
- Model Compression and Hardware Acceleration for Neural Networks: A Comprehensive Survey
- Exploring compression and parallelization techniques for distribution of deep neural networks over Edge-Fog continuum - a review
- Improving Bi-Real Net with block-wise quantization and multiple-steps binarization on activation
- Neuromorphic on-chip recognition of saliva samples of COPD and healthy controls using memristive devices
- FPGA Oriented Compression of DNN Using Layer-Targeted Weights and Activations Quantization
- Efficient binary 3D convolutional neural network and hardware accelerator
- Efficient Visual Recognition: A Survey on Recent Advances and Brain-inspired Methodologies
- Mixed-Precision Neural Networks: A Survey
- Xtreme Margin: A Tunable Loss Function for Binary Classification Problems
- Model Quantization and Hardware Acceleration for Vision Transformers: A Comprehensive Survey
Related papers
- Residual Network 모델의 특징에 관한 실증비교연구
- An Adaptable Real-Time Object Detection for Traffic Surveillance using R-CNN over CNN with Improved Accuracy
- ResNet for Histopathologic Cancer Detection, the Deeper, the Better?
- Road Network Traffic Data Prediction Using ResNet
- A Lightweight Identity Recognition Network using the ArcFace
- Liver Tumour Segmentation based on ResNet Technique
- Interpretation of ResNet by Visualization of Preferred Stimulus in Receptive Fields
- Classification of Paintings Authorship Using Convolutional Neural Network
- Brain Hemorrhage Diagnosis by Using Deep Learning
- Comparison of different convolutional neural network techniques for car models classification