Rectifying the Shortcut Learning of Background for Few-Shot Learning

NeurIPS 2021  ·  Xu Luo, Longhui Wei, Liangjian Wen, Jinrong Yang, Lingxi Xie, Zenglin Xu, Qi Tian ·

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.

PDF Abstract NeurIPS 2021 PDF NeurIPS 2021 Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Few-Shot Image Classification Mini-Imagenet 5-way (1-shot) COSOC (inductive) Accuracy 69.28 # 34
Compare
Few-Shot Image Classification Mini-Imagenet 5-way (5-shot) COSOC (inductive) Accuracy 85.16 # 20
Compare

Methods
Add Remove

No methods listed for this paper. Add relevant methods here
Contact us on: hello@paperswithcode.com . Papers With Code is a free resource with all data licensed under CC-BY-SA.
Terms Data policy Cookies policy