mlsanityData to 7 Oct 2026

RepBNN: towards a precise Binary Neural Network with Enhanced Feature Map via Repeating

arXiv 2207.09049 ↗First posted 19 Jul 2022cs.CV cs.AI cs.LGcited by 2

Not on the map. Why?

Abstract (arXiv)

Binary neural network (BNN) is an extreme quantization version of convolutional neural networks (CNNs) with all features and weights mapped to just 1-bit. Although BNN saves a lot of memory and computation demand to make CNN applicable on edge or mobile devices, BNN suffers the drop of network performance due to the reduced representation capability after binarization. In this paper, we propose a new replaceable and easy-to-use convolution module RepConv, which enhances feature maps through replicating input or output along channel dimension by β times without extra cost on the number of parameters and convolutional computation. We also define a set of RepTran rules to use RepConv throughout BNN modules like binary convolution, fully connected layer and batch normalization. Experiments demonstrate that after the RepTran transformation, a set of highly cited BNNs have achieved universally better performance than the original BNN versions. For example, the Top-1 accuracy of Rep-ReCU-ResNet-20, i.e., a RepBconv enhanced ReCU-ResNet-20, reaches 88.97% on CIFAR-10, which is 1.47% higher than that of the original network. And Rep-AdamBNN-ReActNet-A achieves 71.342% Top-1 accuracy on ImageNet, a fresh state-of-the-art result of BNNs. Code and models are available at:https://github.com/imfinethanks/RepAdamBNN.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 27 of its 29 references that are in the map. First posted on arXiv 19 Jul 2022.

Builds on

27 of 29 references.

References · 27

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  3. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  4. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
  5. 2013Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computationcited by 2,031
  6. 2019Searching for MobileNetV3cited by 1,984
  7. 2018DARTS: Differentiable Architecture Searchcited by 1,782
  8. 2017ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devicescited by 1,194
  9. 2016XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networkscited by 829
  10. 2017Learning Efficient Convolutional Networks through Network Slimmingcited by 673
  11. 2016DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradientscited by 557
  12. 2018Bi-Real Net: Enhancing the Performance of 1-bit CNNs With Improved Representational Capability and Advanced Training Algorithmcited by 233
15 more
  1. 2020ReActNet: Towards Precise Binary Neural Network with Generalized Activation Functionscited by 183
  2. 2019Forward and Backward Information Retention for Accurate Binary Neural Networkscited by 169
  3. 2020Training Binary Neural Networks with Real-to-Binary Convolutionscited by 111
  4. 2016Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1cited by 102
  5. 2020Rotated Binary Neural Networkcited by 77
  6. 2019Global Sparse Momentum SGD for Pruning Very Deep Neural Networkscited by 70
  7. 2021ReCU: Reviving the Dead Weights in Binary Neural Networkscited by 51
  8. 2021How Do Adam and Training Strategies Help BNNs Optimization?cited by 46
  9. 2021A comprehensive review of Binary Neural Networkcited by 44
  10. 2020Searching for Low-Bit Weights in Quantized Neural Networkscited by 43
  11. 2018Binary Ensemble Neural Network: More Bits per Network or More Networks per Bit?cited by 38
  12. 2018Structured Binary Neural Networks for Accurate Image Classification and Semantic Segmentationcited by 37
  13. 2020High-Capacity Expert Binary Networkscited by 34
  14. 2020MeliusNet: Can Binary Neural Networks Achieve MobileNet-level Accuracy?cited by 32
  15. 2020FracBNN: Accurate and FPGA-Efficient Binary Neural Networks with Fractional Activationscited by 30

Built on by

Cited by year

Citing papers per year: 2023: 2.

2 papers.

  1. 2023Input Layer Binarization with Bit-Plane Encodingcited by 3
  2. 2023Optimizing data-flow in Binary Neural Networkscited by 2