# CLAD: A Contrastive Learning based Approach for Background Debiasing Source: [CLAD: A Contrastive Learning based Approach for Background Debiasing]() Collection index: [llms.txt]() Data updated: 2025-10-26T00:37:22.464Z Authors: Ke Wang, Harshitha Machiraju, Oh-Hyeon Choung, Michael Herzog, Pascal Frossard Published: 2022-10-06T08:33:23.000Z ## Abstract 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). ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. ## Original sources and implementation [Original paper]() [PDF]()