RB-Net: Training Highly Accurate and Efficient Binary Neural Networks with Reshaped Point-wise Convolution and Balanced Activation

Published in IEEE Transactions on Circuits and Systems for Video Technology (IEEE TCSVT), 2022, 2022

RB-Net: Training Highly Accurate and Efficient Binary Neural Networks with Reshaped Point-wise Convolution and Balanced Activation

Chunlei Liu, Wenrui Ding, Peng Chen, Bohan Zhuang, Yufeng Wang, Yang Zhao, Baochang Zhang, Yuqi Han. RB-Net: Training Highly Accurate and Efficient Binary Neural Networks with Reshaped Point-wise Convolution and Balanced Activation. IEEE Transactions on Circuits and Systems for Video Technology (IEEE TCSVT), 2022.

Recommended citation: Chunlei Liu, Wenrui Ding, Peng Chen, Bohan Zhuang, Yufeng Wang, Yang Zhao, Baochang Zhang, Yuqi Han. RB-Net: Training Highly Accurate and Efficient Binary Neural Networks with Reshaped Point-wise Convolution and Balanced Activation. IEEE Transactions on Circuits and Systems for Video Technology (IEEE TCSVT), 2022.
Download Paper