Squeeze-and-Excitation Networks

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…

• CI
  Canadian Institute for Advanced Research
• UO
  University of Manchester
• NN
  National Natural Science Foundation of China

  Awards: 61672502, 61571439, 61620106003, 61632003
• CA
  Chinese Academy of Sciences
• UD
  Universidade de Macau
• EA
  Engineering and Physical Sciences Research Council
• NK
  National Key Research and Development Program of China