arXiv Analytics

Sign in

arXiv:2001.03152 [cs.CV]AbstractReferencesReviewsResources

Don't Judge an Object by Its Context: Learning to Overcome Contextual Bias

Krishna Kumar Singh, Dhruv Mahajan, Kristen Grauman, Yong Jae Lee, Matt Feiszli, Deepti Ghadiyaram

Published 2020-01-09Version 1

Existing models often leverage co-occurrences between objects and their context to improve recognition accuracy. However, strongly relying on context risks a model's generalizability, especially when typical co-occurrence patterns are absent. This work focuses on addressing such contextual biases to improve the robustness of the learnt feature representations. Our goal is to accurately recognize a category in the absence of its context, without compromising on performance when it co-occurs with context. Our key idea is to decorrelate feature representations of a category from its co-occurring context. We achieve this by learning a feature subspace that explicitly represents categories occurring in the absence of context along side a joint feature subspace that represents both categories and context. Our very simple yet effective method is extensible to two multi-label tasks -- object and attribute classification. On 4 challenging datasets, we demonstrate the effectiveness of our method in reducing contextual bias.

Related articles:
arXiv:2104.13582 [cs.CV] (Published 2021-04-28)
[Re] Don't Judge an Object by Its Context: Learning to Overcome Contextual Bias
arXiv:2403.09506 [cs.CV] (Published 2024-03-14)
Don't Judge by the Look: A Motion Coherent Augmentation for Video Recognition