Abstract | ||
---|---|---|
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. |
Year | DOI | Venue |
---|---|---|
2020 | 10.1109/CVPR42600.2020.01108 | CVPR |
DocType | Citations | PageRank |
Conference | 0 | 0.34 |
References | Authors | |
22 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Krishna Kumar Singh | 1 | 52 | 8.25 |
Dhruv K. Mahajan | 2 | 378 | 22.92 |
Kristen Grauman | 3 | 6258 | 326.34 |
Yong Jae Lee | 4 | 802 | 40.44 |
Matt Feiszli | 5 | 5 | 2.53 |
Deepti Ghadiyaram | 6 | 233 | 11.14 |