Squeeze-and-Excitation Networks

doi:10.1109/TPAMI.2019.2913372

	Squeeze-and-Excitation Networks
	Hu, Jie 1,2,3; Shen, Li 7; Albanie, Samuel 7; Sun, Gang3,6 ; Wu, Enhua 1,2,4,5
发表期刊	IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
ISSN	0162-8828
	2020-08-01
卷号	42 期号:8 页码:2011-2023
通讯作者	Shen, Li(lishen@robots.ox.ac.uk)
摘要	The central building block of convolutional neural networks (CNNs) is the convolution operator, which enables networks to construct informative features by fusing both spatial and channel-wise information within local receptive fields at each layer. A broad range of prior research has investigated the spatial component of this relationship, seeking to strengthen the representational power of a CNN by enhancing the quality of spatial encodings throughout its feature hierarchy. In this work, we focus instead on the channel relationship and propose a novel architectural unit, which we term the "Squeeze-and-Excitation" (SE) block, that adaptively recalibrates channel-wise feature responses by explicitly modelling interdependencies between channels. We show that these blocks can be stacked together to form SENet architectures that generalise extremely effectively across different datasets. We further demonstrate that SE blocks bring significant improvements in performance for existing state-of-the-art CNNs at slight additional computational cost. Squeeze-and-Excitation Networks formed the foundation of our ILSVRC 2017 classification submission which won first place and reduced the top-5 error to 2.251 percent, surpassing the winning entry of 2016 by a relative improvement of similar to 25 percent. Models and code are available at https://github.com/hujie-frank/SENet.
关键词	Squeeze-and-excitation image representations attention convolutional neural networks
DOI	10.1109/TPAMI.2019.2913372
关键词[WOS]	VISUAL-ATTENTION ; MODEL
收录类别	SCI
语种	英语
资助项目	NSFC[61632003] ; NSFC[61620106003] ; NSFC[61672502] ; NSFC[61571439] ; National Key R&D Program of China[2017YFB1002701] ; Macao FDCT Grant[068/2015/A2] ; EPSRC AIMS CDT[EP/L015897/1]
项目资助者	NSFC ; National Key R&D Program of China ; Macao FDCT Grant ; EPSRC AIMS CDT
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:000545415400015
出版者	IEEE COMPUTER SOC
七大方向——子方向分类	人工智能基础理论
引用统计	被引频次：350[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/173211/40090
专题	多模态人工智能系统全国重点实验室_多媒体计算
通讯作者	Shen, Li
作者单位	1.Chinese Acad Sci, Inst Software, State Key Lab Comp Sci, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Beijing 100049, Peoples R China 3.Momenta, Dongsheng Plaza A,8 Zhongguancun East Rd, Beijing 100083, Peoples R China 4.Univ Macau, Fac Sci & Technol, Taipa, Macao, Peoples R China 5.Univ Macau, AI Ctr, Taipa, Macao, Peoples R China 6.Chinese Acad Sci, Inst Automat, LIAMA NLPR, Beijing 100190, Peoples R China 7.Univ Oxford, Visual Geometry Grp, Oxford OX1 2JD, England
推荐引用方式 GB/T 7714	Hu, Jie,Shen, Li,Albanie, Samuel,et al. Squeeze-and-Excitation Networks[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,2020,42(8):2011-2023.
APA	Hu, Jie,Shen, Li,Albanie, Samuel,Sun, Gang,&Wu, Enhua.(2020).Squeeze-and-Excitation Networks.IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,42(8),2011-2023.
MLA	Hu, Jie,et al."Squeeze-and-Excitation Networks".IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 42.8(2020):2011-2023.