2022-10-09 更新
CLAD: A Contrastive Learning based Approach for Background Debiasing
Authors:Ke Wang, Harshitha Machiraju, Oh-Hyeon Choung, Michael Herzog, Pascal Frossard
Convolutional neural networks (CNNs) have achieved superhuman performance in multiple vision tasks, especially image classification. However, unlike humans, CNNs leverage spurious features, such as background information to make decisions. This tendency creates different problems in terms of robustness or weak generalization performance. Through our work, we introduce a contrastive learning-based approach (CLAD) to mitigate the background bias in CNNs. CLAD encourages semantic focus on object foregrounds and penalizes learning features from irrelavant backgrounds. Our method also introduces an efficient way of sampling negative samples. We achieve state-of-the-art results on the Background Challenge dataset, outperforming the previous benchmark with a margin of 4.1\%. Our paper shows how CLAD serves as a proof of concept for debiasing of spurious features, such as background and texture (in supplementary material).
PDF Accepted to British Machine Vision Conference (BMVC) 2022
点此查看论文截图
