Squeeze-and-Excitation Networks

TLDR

Convolutional neural networks fuse spatial and channel information, yet prior work has mainly strengthened spatial encodings, leaving channel relationships underexplored. This study introduces the Squeeze‑and‑Excitation block to adaptively recalibrate channel‑wise feature responses by modeling inter‑channel dependencies. The SE block can be stacked into SENet architectures, which generalize effectively across datasets. SE blocks significantly improve performance of state‑of‑the‑art CNNs with minimal extra computation, enabling the ILSVRC 2017 entry to win with a 2.251 % top‑5 error, a ~25 % relative improvement over 2016. Models and code are available at https://github.com/hujie-frank/SENet.

Abstract

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%, surpassing the winning entry of 2016 by a relative improvement of ~25%. Models and code are available at https://github.com/hujie-frank/SENet.