Squeeze-and-Excitation Networks

• Published in: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition pp. 7132 - 7141
• Main Authors: Hu, Jie, Shen, Li, Sun, Gang
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.06.2018
• Subjects: Adaptation models; Computational modeling; Computer architecture; Convolution; Convolutional codes; Stacking; Task analysis
• DOI: 10.1109/CVPR.2018.00745

Convolutional neural networks are built upon the convolution operation, which extracts informative features by fusing spatial and channel-wise information together within local receptive fields. In order to boost the representational power of a network, several recent approaches have shown the benefit of enhancing spatial encoding. In this work, we focus 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 demonstrate that by stacking these blocks together, we can construct SENet architectures that generalise extremely well across challenging datasets. Crucially, we find that SE blocks produce significant performance improvements for existing state-of-the-art deep architectures at minimal additional computational cost. SENets formed the foundation of our ILSVRC 2017 classification submission which won first place and significantly reduced the top-5 error to 2.251%, achieving a ~25% relative improvement over the winning entry of 2016. Code and models are available at https://github.com/hujie-frank/SENet.