Journal
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
Volume 42, Issue 8, Pages 2011-2023Publisher
IEEE COMPUTER SOC
DOI: 10.1109/TPAMI.2019.2913372
Keywords
Squeeze-and-excitation; image representations; attention; convolutional neural networks
Funding
- NSFC [61632003, 61620106003, 61672502, 61571439]
- National Key R&D Program of China [2017YFB1002701]
- Macao FDCT Grant [068/2015/A2]
- EPSRC AIMS CDT [EP/L015897/1]
- EPSRC [EP/L015897/1] Funding Source: UKRI
Ask authors/readers for more resources
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.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available