LoDisc: Learning Global-Local Discriminative Features for Self-Supervised Fine-Grained Visual Recognition

TL;DR

LoDisc introduces a self-supervised global-local contrastive learning framework that enhances fine-grained visual recognition by explicitly focusing on local pivotal regions, improving feature representations beyond global coarse features.

Contribution

The paper proposes a novel local discrimination pretext task and a global-local contrastive framework for self-supervised fine-grained visual recognition.

Findings

Improves fine-grained recognition accuracy across multiple tasks.

Enhances local feature emphasis in self-supervised learning.

Effective also for general object recognition.

Abstract

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.