Exploring Self-Attention for Image Recognition

Hengshuang Zhao, Jiaya Jia, Vladlen Koltun; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020, pp. 10076-10085

Abstract


Recent work has shown that self-attention can serve as a basic building block for image recognition models. We explore variations of self-attention and assess their effectiveness for image recognition. We consider two forms of self-attention. One is pairwise self-attention, which generalizes standard dot-product attention and is fundamentally a set operator. The other is patchwise self-attention, which is strictly more powerful than convolution. Our pairwise self-attention networks match or outperform their convolutional counterparts, and the patchwise models substantially outperform the convolutional baselines. We also conduct experiments that probe the robustness of learned representations and conclude that self-attention networks may have significant benefits in terms of robustness and generalization.

Related Material


[pdf] [arXiv]
[bibtex]
@InProceedings{Zhao_2020_CVPR,
author = {Zhao, Hengshuang and Jia, Jiaya and Koltun, Vladlen},
title = {Exploring Self-Attention for Image Recognition},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2020}
}