mlsanityData to 7 Oct 2026

Binary Neural Networks as a general-propose compute paradigm for on-device computer vision

arXiv 2202.03716 ↗First posted 8 Feb 2022cs.CVcited by 1

Not on the map. Why?

Abstract (arXiv)

For binary neural networks (BNNs) to become the mainstream on-device computer vision algorithm, they must achieve a superior speed-vs-accuracy tradeoff than 8-bit quantization and establish a similar degree of general applicability in vision tasks. To this end, we propose a BNN framework comprising 1) a minimalistic inference scheme for hardware-friendliness, 2) an over-parameterized training scheme for high accuracy, and 3) a simple procedure to adapt to different vision tasks. The resultant framework overtakes 8-bit quantization in the speed-vs-accuracy tradeoff for classification, detection, segmentation, super-resolution and matching: our BNNs not only retain the accuracy levels of their 8-bit baselines but also showcase 1.3-2.4× faster FPS on mobile CPUs. Similar conclusions can be drawn for prototypical systolic-array-based AI accelerators, where our BNNs promise 2.8-7× fewer execution cycles than 8-bit and 2.1-2.7× fewer cycles than alternative BNN designs. These results suggest that the time for large-scale BNN adoption could be upon us.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 31 of its 50 references that are in the map. First posted on arXiv 8 Feb 2022.

Builds on

31 of 50 references.

References · 31

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  3. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  4. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,827
  5. 2017Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inferencecited by 1,548
  6. 2017Enhanced Deep Residual Networks for Single Image Super-Resolutioncited by 1,543
  7. 2019MMDetection: Open MMLab Detection Toolbox and Benchmarkcited by 1,379
  8. 2019Objects as Pointscited by 1,172
  9. 2018ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Designcited by 1,132
  10. 2016XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networkscited by 829
  11. 2016DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradientscited by 557
  12. 2021RepVGG: Making VGG-style ConvNets Great Againcited by 520
19 more
  1. 2018Quantizing deep convolutional networks for efficient inference: A whitepapercited by 507
  2. 2015Learning Deconvolution Network for Semantic Segmentationcited by 365
  3. 2018Bi-Real Net: Enhancing the Performance of 1-bit CNNs With Improved Representational Capability and Advanced Training Algorithmcited by 233
  4. 2019R2D2: Repeatable and Reliable Detector and Descriptorcited by 206
  5. 2020ReActNet: Towards Precise Binary Neural Network with Generalized Activation Functionscited by 183
  6. 2019Forward and Backward Information Retention for Accurate Binary Neural Networkscited by 169
  7. 2017Towards Accurate Binary Convolutional Neural Networkcited by 148
  8. 2016FINN: A Framework for Fast, Scalable Binarized Neural Network Inferencecited by 141
  9. 2020Rotated Binary Neural Networkcited by 77
  10. 2021ReCU: Reviving the Dead Weights in Binary Neural Networkscited by 51
  11. 2017WRPN: Wide Reduced-Precision Networkscited by 49
  12. 2018Structured Binary Neural Networks for Accurate Image Classification and Semantic Segmentationcited by 37
  13. 2020BiDet: An Efficient Binarized Object Detectorcited by 33
  14. 2020MeliusNet: Can Binary Neural Networks Achieve MobileNet-level Accuracy?cited by 32
  15. 2018Efficient Super Resolution Using Binarized Neural Networkcited by 29
  16. 2019daBNN: A Super Fast Inference Framework for Binary Neural Networks on ARM devicescited by 27
  17. 2017BMXNet: An Open-Source Binary Neural Network Implementation Based on MXNetcited by 11
  18. 2019RBCN: Rectified Binary Convolutional Networks for Enhancing the Performance of 1-bit DCNNscited by 4
  19. 2019PhoneBit: Efficient GPU-Accelerated Binary Neural Network Inference Engine for Mobile Phonescited by 3

Built on by

Cited by year

Citing papers per year: 2024: 1.

1 paper.

  1. 2024BOLD: Boolean Logic Deep Learningcited by 3