Recurrent Bilinear Optimization for Binary Neural Networks (RBONN)

Pytorch implementation of our RBONN accepted by ECCV2022 as oral presentation.

Tips

Any problem, please contact the first author (Email: [email protected]).

Our code is heavily borrowed from ReActNet (https://github.com/liuzechun/ReActNet).

Dependencies

• Python 3.8
• Pytorch 1.7.1
• Torchvision 0.8.2

RBONN with two-stage tranining

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:

1. Finish the first stage training using ReActNet.
2. Use the following command:

cd 2_step2_rbonn 
bash run.sh

Other models will be open-sourced successively.