Saved in:
Bibliographic Details
Main Authors: Shi, Jialu, Wei, Zhiqiang, Nie, Jie, Huang, Lei
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2403.04066
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909830264913920
author Shi, Jialu
Wei, Zhiqiang
Nie, Jie
Huang, Lei
author_facet Shi, Jialu
Wei, Zhiqiang
Nie, Jie
Huang, Lei
contents The self-supervised contrastive learning strategy has attracted considerable attention due to its exceptional ability in representation learning. However, current contrastive learning tends to learn global coarse-grained representations of the image that benefit generic object recognition, whereas such coarse-grained features are insufficient for fine-grained visual recognition. In this paper, we incorporate subtle local fine-grained feature learning into global self-supervised contrastive learning through a pure self-supervised global-local fine-grained contrastive learning framework. Specifically, a novel pretext task called local discrimination (LoDisc) is proposed to explicitly supervise the self-supervised model's focus toward local pivotal regions, which are captured by a simple but effective location-wise mask sampling strategy. We show that the LoDisc pretext task can effectively enhance fine-grained clues in important local regions and that the global-local framework further refines the fine-grained feature representations of images. Extensive experimental results on different fine-grained object recognition tasks demonstrate that the proposed method can lead to a decent improvement in different evaluation settings. The proposed method is also effective for general object recognition tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2403_04066
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle LoDisc: Learning Global-Local Discriminative Features for Self-Supervised Fine-Grained Visual Recognition
Shi, Jialu
Wei, Zhiqiang
Nie, Jie
Huang, Lei
Computer Vision and Pattern Recognition
The self-supervised contrastive learning strategy has attracted considerable attention due to its exceptional ability in representation learning. However, current contrastive learning tends to learn global coarse-grained representations of the image that benefit generic object recognition, whereas such coarse-grained features are insufficient for fine-grained visual recognition. In this paper, we incorporate subtle local fine-grained feature learning into global self-supervised contrastive learning through a pure self-supervised global-local fine-grained contrastive learning framework. Specifically, a novel pretext task called local discrimination (LoDisc) is proposed to explicitly supervise the self-supervised model's focus toward local pivotal regions, which are captured by a simple but effective location-wise mask sampling strategy. We show that the LoDisc pretext task can effectively enhance fine-grained clues in important local regions and that the global-local framework further refines the fine-grained feature representations of images. Extensive experimental results on different fine-grained object recognition tasks demonstrate that the proposed method can lead to a decent improvement in different evaluation settings. The proposed method is also effective for general object recognition tasks.
title LoDisc: Learning Global-Local Discriminative Features for Self-Supervised Fine-Grained Visual Recognition
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2403.04066