Rectifying the Shortcut Learning of Background for Few-Shot Learning
Abstract
The category gap between training and evaluation has been characterised as one of the main obstacles to the success of Few-Shot Learning (FSL). In this paper, we for the first time empirically identify image background, common in realistic images, as a shortcut knowledge helpful for in-class classification but ungeneralizable beyond training categories in FSL. A novel framework, COSOC, is designed to tackle this problem by extracting foreground objects in images at both training and evaluation without any extra supervision. Extensive experiments carried on inductive FSL tasks demonstrate the effectiveness of our approaches.
Cite
Text
Luo et al. "Rectifying the Shortcut Learning of Background for Few-Shot Learning." Neural Information Processing Systems, 2021.Markdown
[Luo et al. "Rectifying the Shortcut Learning of Background for Few-Shot Learning." Neural Information Processing Systems, 2021.](https://mlanthology.org/neurips/2021/luo2021neurips-rectifying/)BibTeX
@inproceedings{luo2021neurips-rectifying,
title = {{Rectifying the Shortcut Learning of Background for Few-Shot Learning}},
author = {Luo, Xu and Wei, Longhui and Wen, Liangjian and Yang, Jinrong and Xie, Lingxi and Xu, Zenglin and Tian, Qi},
booktitle = {Neural Information Processing Systems},
year = {2021},
url = {https://mlanthology.org/neurips/2021/luo2021neurips-rectifying/}
}