Pytorch implementation of our paper "Recurrent Bilinear Optimization for Binary Neural Networks" accepted by ECCV2022 as oral presentation.
Any problem, please contact the first author (Email: shengxu@buaa.edu.cn).
Our code is heavily borrowed from ReActNet (https://github.com/liuzechun/ReActNet).
- Python 3.8
- Pytorch 1.7.1
- Torchvision 0.8.2
We test our RBONN using the same ResNet-18 structure and training setttings as ReActNet, and obtain 66.7% top-1 accuracy.
Methods | Top-1 acc | Top-5 acc | Quantized model link | Log |
---|---|---|---|---|
ReActNet | 65.9 | - | Model | - |
ReCU | 66.4 | 86.5 | Model | - |
RBONN | 66.7 | 87.0 | Model | Log |
To verify the performance of our quantized models with ReActNet-like structure on ImageNet, please do as the following steps:
- Finish the first stage training using ReActNet.
- Use the following command:
cd 2_step2_rbonn
bash run.sh
If you find this work useful in your research, please consider to cite:
@inproceedings{xu2022recurrent,
title={Recurrent bilinear optimization for binary neural networks},
author={Xu, Sheng and Li, Yanjing and Wang, Tiancheng and Ma, Teli and Zhang, Baochang and Gao, Peng and Qiao, Yu and L{\"u}, Jinhu and Guo, Guodong},
booktitle={European Conference on Computer Vision},
pages={19--35},
year={2022},
organization={Springer}
}