Self-supervised fine-grained image classification by focus on local important regions with LoDisc
Self-supervised fine-grained image classification by focus on local important regions with LoDisc
LoDisc: Learning Global-Local Discriminative Features for Self-Supervised Fine-Grained Visual Recognition
arXiv paper abstract https://arxiv.org/abs/2403.04066
arXiv PDF paper https://arxiv.org/pdf/2403.04066.pdf
Self-supervised contrastive learning strategy has attracted remarkable attention due to its exceptional ability in representation learning.
However, current contrastive learning … learn global coarse-grained representations … that benefit generic object recognition … are insufficient for fine-grained visual recognition.
… present to incorporate the subtle local fine-grained feature learning into global self-supervised contrastive learning through a pure self-supervised global-local fine-grained contrastive learning framework.
… pretext task called Local Discrimination (LoDisc) … to explicitly supervise self-supervised model’s focus towards local pivotal regions which are captured by a simple-but-effective location-wise mask sampling strategy.
… show that Local Discrimination pretext task … enhance fine-grained clues in important local regions, and the global-local framework further refines the fine-grained feature representations of images.
… method can lead to a decent improvement in different evaluation settings … is also effective in general object recognition tasks.
Stay up to date. Subscribe to my posts https://morrislee1234.wixsite.com/website/contact
Web site with my other posts by category https://morrislee1234.wixsite.com/website
LinkedIn https://www.linkedin.com/in/morris-lee-47877b7b
