Object-aware Contrastive Learning for Debiased Scene Representation

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 79
  • Download : 0
DC FieldValueLanguage
dc.contributor.authorMo, Sangwooko
dc.contributor.authorKang, Hyunwooko
dc.contributor.authorSohn, Kihyunkko
dc.contributor.authorLi, Chun-Liangko
dc.contributor.authorShin, Jinwooko
dc.identifier.citation35th Conference on Neural Information Processing Systems, NeurIPS 2021-
dc.description.abstractContrastive self-supervised learning has shown impressive results in learning visual representations from unlabeled images by enforcing invariance against different data augmentations. However, the learned representations are often contextually biased to the spurious scene correlations of different objects or object and background, which may harm their generalization on the downstream tasks. To tackle the issue, we develop a novel object-aware contrastive learning framework that first (a) localizes objects in a self-supervised manner and then (b) debias scene correlations via appropriate data augmentations considering the inferred object locations. For (a), we propose the contrastive class activation map (ContraCAM), which finds the most discriminative regions (e.g., objects) in the image compared to the other images using the contrastively trained models. We further improve the ContraCAM to detect multiple objects and entire shapes via an iterative refinement procedure. For (b), we introduce two data augmentations based on ContraCAM, object-aware random crop and background mixup, which reduce contextual and background biases during contrastive self-supervised learning, respectively. Our experiments demonstrate the effectiveness of our representation learning framework, particularly when trained under multi-object images or evaluated under the background (and distribution) shifted images. Code is available at https://github.com/alinlab/object-aware-contrastive.-
dc.publisherNeural Information Processing Systems-
dc.titleObject-aware Contrastive Learning for Debiased Scene Representation-
dc.citation.publicationname35th Conference on Neural Information Processing Systems, NeurIPS 2021-
dc.contributor.localauthorShin, Jinwoo-
dc.contributor.nonIdAuthorSohn, Kihyunk-
dc.contributor.nonIdAuthorLi, Chun-Liang-
Appears in Collection
RIMS Conference Papers
Files in This Item
There are no files associated with this item.


  • mendeley


rss_1.0 rss_2.0 atom_1.0