RB-Net: Training Highly Accurate and Efficient Binary Neural Networks With Reshaped Point-Wise Convolution and Balanced Activation
- 12 April 2022
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 32 (9) , 6414-6424
Abstract
In this paper, we find that the conventional convolution operation becomes the bottleneck for extremely efficient binary neural networks (BNNs). To address this issue, we open up a new direction by introducing a reshaped point-wise convolution (RPC) to replace the conventional one to build BNNs. Specifically, we conduct a point-wise convolution after rearranging the spatial information into depth, with which at least $2.25\times $ computation reduction can be achieved. Such an efficient RPC allows us to explore more powerful representational capacity of BNNs under a given computation complexity budget. Moreover, we propose to use a balanced activation (BA) to adjust the distribution of the scaled activations after binarization, which enables significant performance improvement of BNNs. After integrating RPC and BA, the proposed network, dubbed as RB-Net, strikes a good trade-off between accuracy and efficiency, achieving superior performance with lower computational cost against the state-of-the-art BNN methods. Specifically, our RB-Net achieves 66.8% Top-1 accuracy with ResNet-18 backbone on ImageNet, exceeding the state-of-the-art Real-to-Binary Net (65.4%) by 1.4% while achieving more than $3\times $ reduction (52M vs. 165M) in computational complexity.
Keywords
Funding Information
- China Postdoctoral Science Foundation (2021TQ0177)
This publication has 29 references indexed in Scilit:
- Bi-Real Net: Enhancing the Performance of 1-Bit CNNs with Improved Representational Capability and Advanced Training Algorithm2018
- LQ-Nets: Learned Quantization for Highly Accurate and Compact Deep Neural Networks2018
- ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices2018
- Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference2018
- True Gradient-Based Training of Deep Binary Activated Neural Networks Via Continuous Binarization2018
- Channel Pruning for Accelerating Very Deep Neural Networks2017
- Deep Learning with Low Precision by Half-Wave Gaussian Quantization2017
- XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks2016
- Deep Residual Learning for Image Recognition2016
- ImageNet Large Scale Visual Recognition ChallengeInternational Journal of Computer Vision, 2015