SelEx: Self-Expertise in Fine-Grained Generalized Category Discovery

TL;DR

SelEx introduces a novel self-expertise approach combining supervised and unsupervised strategies with hierarchical pseudo-labeling to improve fine-grained generalized category discovery, outperforming existing methods.

Contribution

The paper proposes the concept of self-expertise and integrates hierarchical pseudo-labeling to enhance category recognition and discovery in fine-grained datasets.

Findings

Outperforms state-of-the-art in fine-grained datasets

Effective use of hierarchical pseudo-labeling

Improved recognition of subtle category differences

Abstract

In this paper, we address Generalized Category Discovery, aiming to simultaneously uncover novel categories and accurately classify known ones. Traditional methods, which lean heavily on self-supervision and contrastive learning, often fall short when distinguishing between fine-grained categories. To address this, we introduce a novel concept called `self-expertise', which enhances the model's ability to recognize subtle differences and uncover unknown categories. Our approach combines unsupervised and supervised self-expertise strategies to refine the model's discernment and generalization. Initially, hierarchical pseudo-labeling is used to provide `soft supervision', improving the effectiveness of self-expertise. Our supervised technique differs from traditional methods by utilizing more abstract positive and negative samples, aiding in the formation of clusters that can generalize to novel categories. Meanwhile, our unsupervised strategy encourages the model to sharpen its category distinctions by considering within-category examples as `hard' negatives. Supported by theoretical insights, our empirical results showcase that our method outperforms existing state-of-the-art techniques in Generalized Category Discovery across several fine-grained datasets. Our code is available at: https://github.com/SarahRastegar/SelEx.