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

arXiv: https://arxiv.org/abs/2202.03716 · HTML: https://mlsanity.com/paper/2202.03716/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 50 references that are in the map.
- First posted on arXiv 8 Feb 2022.

## Builds on (most cited first, 30 of 31)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference](https://mlsanity.com/paper/1712.05877/) (2017)
- [Enhanced Deep Residual Networks for Single Image Super-Resolution](https://mlsanity.com/paper/1707.02921/) (2017)
- [MMDetection: Open MMLab Detection Toolbox and Benchmark](https://mlsanity.com/paper/1906.07155/) (2019)
- [Objects as Points](https://mlsanity.com/paper/1904.07850/) (2019)
- [ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design](https://mlsanity.com/paper/1807.11164/) (2018)
- [XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks](https://mlsanity.com/paper/1603.05279/) (2016)
- [DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients](https://mlsanity.com/paper/1606.06160/) (2016)
- [RepVGG: Making VGG-style ConvNets Great Again](https://mlsanity.com/paper/2101.03697/) (2021)
- [Quantizing deep convolutional networks for efficient inference: A whitepaper](https://mlsanity.com/paper/1806.08342/) (2018)
- [Learning Deconvolution Network for Semantic Segmentation](https://mlsanity.com/paper/1505.04366/) (2015)
- [Bi-Real Net: Enhancing the Performance of 1-bit CNNs With Improved Representational Capability and Advanced Training Algorithm](https://mlsanity.com/paper/1808.00278/) (2018)
- [R2D2: Repeatable and Reliable Detector and Descriptor](https://mlsanity.com/paper/1906.06195/) (2019)
- [ReActNet: Towards Precise Binary Neural Network with Generalized Activation Functions](https://mlsanity.com/paper/2003.03488/) (2020)
- [Forward and Backward Information Retention for Accurate Binary Neural Networks](https://mlsanity.com/paper/1909.10788/) (2019)
- [FINN: A Framework for Fast, Scalable Binarized Neural Network Inference](https://mlsanity.com/paper/1612.07119/) (2016)
- [Towards Accurate Binary Convolutional Neural Network](https://mlsanity.com/paper/1711.11294/) (2017)
- [Rotated Binary Neural Network](https://mlsanity.com/paper/2009.13055/) (2020)
- [ReCU: Reviving the Dead Weights in Binary Neural Networks](https://mlsanity.com/paper/2103.12369/) (2021)
- [WRPN: Wide Reduced-Precision Networks](https://mlsanity.com/paper/1709.01134/) (2017)
- [Structured Binary Neural Networks for Accurate Image Classification and Semantic Segmentation](https://mlsanity.com/paper/1811.10413/) (2018)
- [BiDet: An Efficient Binarized Object Detector](https://mlsanity.com/paper/2003.03961/) (2020)
- [MeliusNet: Can Binary Neural Networks Achieve MobileNet-level Accuracy?](https://mlsanity.com/paper/2001.05936/) (2020)
- [Efficient Super Resolution Using Binarized Neural Network](https://mlsanity.com/paper/1812.06378/) (2018)
- [daBNN: A Super Fast Inference Framework for Binary Neural Networks on ARM devices](https://mlsanity.com/paper/1908.05858/) (2019)
- [BMXNet: An Open-Source Binary Neural Network Implementation Based on MXNet](https://mlsanity.com/paper/1705.09864/) (2017)
- [RBCN: Rectified Binary Convolutional Networks for Enhancing the Performance of 1-bit DCNNs](https://mlsanity.com/paper/1908.07748/) (2019)

## Built on by (most cited first, 1 of 1)

- [BOLD: Boolean Logic Deep Learning](https://mlsanity.com/paper/2405.16339/) (2024)

## 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.