中国科学院机构知识库网格系统: Squeeze-and-Excitation Networks

Squeeze-and-Excitation Networks

文献类型：期刊论文


作者	Hu, Jie 2,3,7; Shen, Li 5; Albanie, Samuel 5; Sun, Gang3,6 ; Wu, Enhua 1,2,4,7
刊名	IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
出版日期	2020-08-01
卷号	42 期号:8 页码:2011-2023
ISSN号	0162-8828
关键词	Squeeze-and-excitation image representations attention convolutional neural networks
DOI	10.1109/TPAMI.2019.2913372
通讯作者	Shen, Li(lishen@robots.ox.ac.uk)
英文摘要	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.
WOS关键词	VISUAL-ATTENTION ; MODEL
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]
WOS研究方向	Computer Science ; Engineering
语种	英语
出版者	IEEE COMPUTER SOC
WOS记录号	WOS:000545415400015
资助机构	NSFC ; National Key R&D Program of China ; Macao FDCT Grant ; EPSRC AIMS CDT
源URL	[http://ir.ia.ac.cn/handle/173211/40089]
专题	自动化研究所_模式识别国家重点实验室_多媒体计算与图形学团队
通讯作者	Shen, Li
作者单位	1.Univ Macau, AI Ctr, Taipa, Macao, 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 Oxford, Visual Geometry Grp, Oxford OX1 2JD, England 6.Chinese Acad Sci, Inst Automat, LIAMA NLPR, Beijing 100190, Peoples R China 7.Chinese Acad Sci, Inst Software, State Key Lab Comp Sci, Beijing 100190, Peoples R China
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.

入库方式： OAI收割

来源：自动化研究所

下载0

Squeeze-and-Excitation Networks

其他版本