Toward Accurate Binarized Neural Networks With Sparsity for Mobile Application

doi:10.1109/TNNLS.2022.3173498

	Toward Accurate Binarized Neural Networks With Sparsity for Mobile Application
	Wang, Peisong; He, Xiangyu; Cheng, Jian
发表期刊	IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
ISSN	2162-237X
	2022-05-27
页码	13
通讯作者	Cheng, Jian(jcheng@nlpria.ac.cn)
摘要	While binarized neural networks (BNNs) have attracted great interest, popular approaches proposed so far mainly exploit the symmetric sign function for feature binarization, i.e., to binarize activations into -1 and +1 with a fixed threshold of 0. However, whether this option is optimal has been largely overlooked. In this work, we propose the Sparsity-inducing BNN (Si-BNN) to quantize the activations to be either 0 or +1, which better approximates ReLU using 1-bit. We further introduce trainable thresholds into the backward function of binarization to guide the gradient propagation. Our method dramatically outperforms the current state-of-the-art, lowering the performance gap between full-precision networks and BNNs on mainstream architectures, achieving the new state-of-the-art on binarized AlexNet (Top-1 50.5%), ResNet-18 (Top-1 62.2%), and ResNet-50 (Top-1 68.3%). At inference time, Si-BNN still enjoys the high efficiency of bit-wise operations. In our implementation, the running time of binary AlexNet on the CPU can be competitive with the popular GPU-based deep learning framework.
关键词	Quantization (signal) Deep learning Convolution Training Biological neural networks Optimization Neurons Acceleration binarized neural networks (BNNs) compression fixed-point quantization
DOI	10.1109/TNNLS.2022.3173498
收录类别	SCI
语种	英语
资助项目	National Key Research and Development Program of China[2021ZD0201504] ; National Natural Science Foundation of China[61906193] ; Strategic Priority Research Program of Chinese Academy of Sciences[XDA27040300]
项目资助者	National Key Research and Development Program of China ; National Natural Science Foundation of China ; Strategic Priority Research Program of Chinese Academy of Sciences
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Computer Science, Hardware & Architecture ; Computer Science, Theory & Methods ; Engineering, Electrical & Electronic
WOS记录号	WOS:000805801000001
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计	被引频次：2[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/49510
专题	复杂系统认知与决策实验室_高效智能计算与学习
通讯作者	Cheng, Jian
作者单位	Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
第一作者单位	模式识别国家重点实验室
通讯作者单位	模式识别国家重点实验室
推荐引用方式 GB/T 7714	Wang, Peisong,He, Xiangyu,Cheng, Jian. Toward Accurate Binarized Neural Networks With Sparsity for Mobile Application[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,2022:13.
APA	Wang, Peisong,He, Xiangyu,&Cheng, Jian.(2022).Toward Accurate Binarized Neural Networks With Sparsity for Mobile Application.IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,13.
MLA	Wang, Peisong,et al."Toward Accurate Binarized Neural Networks With Sparsity for Mobile Application".IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2022):13.