Don't Judge an Object by Its Context: Learning to Overcome Contextual Bias
This addresses robustness issues in computer vision models for object and attribute classification, though it is incremental as it builds on existing methods to reduce bias.
The paper tackles the problem of contextual bias in object recognition models, which rely on co-occurrences between objects and context, by learning decorrelated feature representations to improve robustness without compromising performance when context is present, achieving effectiveness on 4 challenging datasets.
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.