中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
热门
Squeeze-and-Excitation Networks

文献类型:期刊论文

AuthorHu, Jie2,3,7; Shen, Li5; Albanie, Samuel5; Sun, Gang3,6; Wu, Enhua1,2,4,7
SourceIEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
Issued Date2020-08-01
Volume42Issue:8Pages:2011-2023
KeywordSqueeze-and-excitation image representations attention convolutional neural networks
ISSN0162-8828
DOI10.1109/TPAMI.2019.2913372
Corresponding AuthorShen, Li(lishen@robots.ox.ac.uk)
English AbstractThe 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.
Funding ProjectNSFC[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 KeywordVISUAL-ATTENTION ; MODEL
WOS Research AreaComputer Science ; Engineering
Language英语
PublisherIEEE COMPUTER SOC
WOS IDWOS:000545415400015
Funding OrganizationNSFC ; National Key R&D Program of China ; Macao FDCT Grant ; EPSRC AIMS CDT