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

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. Spe...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE transactions on circuits and systems for video technology Ročník 32; číslo 9; s. 6414 - 6424
Hlavní autoři: Liu, Chunlei, Ding, Wenrui, Chen, Peng, Zhuang, Bohan, Wang, Yufeng, Zhao, Yang, Zhang, Baochang, Han, Yuqi
Médium: Journal Article
Jazyk:angličtina
Vydáno: New York IEEE 01.09.2022
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:
Accuracy
balanced activation
Binary neural network
Complexity
Computational efficiency
Computing costs
Convolution
Kernel
Neural networks
object classification
Remote procedure calls
reshaped point-wise convolution
Spatial data
Spatial databases
Training
ISSN:1051-8215, 1558-2205
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí: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 <inline-formula> <tex-math notation="LaTeX">2.25\times </tex-math></inline-formula> 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 <inline-formula> <tex-math notation="LaTeX">3\times </tex-math></inline-formula> reduction (52M vs. 165M) in computational complexity.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1051-8215
1558-2205
DOI:10.1109/TCSVT.2022.3166803