Learning Debiased Classifier with Biased Committee

NeurIPS 2022(2022)

引用 21|浏览31
暂无评分
摘要
Neural networks are prone to be biased towards spurious correlations between classes and latent attributes exhibited in a major portion of training data, which ruins their generalization capability. We propose a new method for training debiased classifiers with no spurious attribute label. The key idea is to employ a committee of classifiers as an auxiliary module that identifies bias-conflicting data, i.e., data without spurious correlation, and assigns large weights to them when training the main classifier. The committee is learned as a bootstrapped ensemble so that a majority of its classifiers are biased as well as being diverse, and intentionally fail to predict classes of bias-conflicting data accordingly. The consensus within the committee on prediction difficulty thus provides a reliable cue for identifying and weighting bias-conflicting data. Moreover, the committee is also trained with knowledge transferred from the main classifier so that it gradually becomes debiased along with the main classifier and emphasizes more difficult data as training progresses. On five real-world datasets, our method outperforms prior arts using no spurious attribute label like ours and even surpasses those relying on bias labels occasionally.
更多
查看译文
关键词
Debiasing,bootstrap ensemble,self-supervised learning,image classification,spurious correlation
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要