Reflash Dropout in Image Super-Resolution

Xiangtao Kong, Xina Liu, Jinjin Gu, Yu Qiao, Chao Dong; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022, pp. 6002-6012

Abstract


Dropout is designed to relieve the overfitting problem in high-level vision tasks but is rarely applied in low-level vision tasks, like image super-resolution (SR). As a classic regression problem, SR exhibits a different behaviour as high-level tasks and is sensitive to the dropout operation. However, in this paper, we show that appropriate usage of dropout benefits SR networks and improves the generalization ability. Specifically, dropout is better embedded at the end of the network and is significantly helpful for the multi-degradation settings. This discovery breaks our common sense and inspires us to explore its working mechanism. We further use two analysis tools -- one is from recent network interpretation works, and the other is specially designed for this task. The analysis results provide side proofs to our experimental findings and show us a new perspective to understand SR networks.

Related Material


[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Kong_2022_CVPR, author = {Kong, Xiangtao and Liu, Xina and Gu, Jinjin and Qiao, Yu and Dong, Chao}, title = {Reflash Dropout in Image Super-Resolution}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {6002-6012} }