2022/10/06 by Ke Wang, Wang, Ke, Harshitha Machiraju +7 · 2 citations
Computer Science · #Artificial Intelligence (cs.AI) #Computer Vision and Pattern Recognition (cs.CV) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #FOS: Electrical engineering #Face recognition and analysis #Image and Video Processing (eess.IV) #Machine Learning (cs.LG) #Video Surveillance and Tracking Methods #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2210.02748
openalex publication_date 2022/10/06 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
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).