Generalized Category Discovery under the Long-Tailed Distribution

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zhao, Bingchen, Han, Kai
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866918065358241792
author Zhao, Bingchen
Han, Kai
author_facet Zhao, Bingchen
Han, Kai
contents This paper addresses the problem of Generalized Category Discovery (GCD) under a long-tailed distribution, which involves discovering novel categories in an unlabelled dataset using knowledge from a set of labelled categories. Existing works assume a uniform distribution for both datasets, but real-world data often exhibits a long-tailed distribution, where a few categories contain most examples, while others have only a few. While the long-tailed distribution is well-studied in supervised and semi-supervised settings, it remains unexplored in the GCD context. We identify two challenges in this setting - balancing classifier learning and estimating category numbers - and propose a framework based on confident sample selection and density-based clustering to tackle them. Our experiments on both long-tailed and conventional GCD datasets demonstrate the effectiveness of our method.
format Preprint
id arxiv_https___arxiv_org_abs_2506_12515
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Generalized Category Discovery under the Long-Tailed Distribution
Zhao, Bingchen
Han, Kai
Computer Vision and Pattern Recognition
This paper addresses the problem of Generalized Category Discovery (GCD) under a long-tailed distribution, which involves discovering novel categories in an unlabelled dataset using knowledge from a set of labelled categories. Existing works assume a uniform distribution for both datasets, but real-world data often exhibits a long-tailed distribution, where a few categories contain most examples, while others have only a few. While the long-tailed distribution is well-studied in supervised and semi-supervised settings, it remains unexplored in the GCD context. We identify two challenges in this setting - balancing classifier learning and estimating category numbers - and propose a framework based on confident sample selection and density-based clustering to tackle them. Our experiments on both long-tailed and conventional GCD datasets demonstrate the effectiveness of our method.
title Generalized Category Discovery under the Long-Tailed Distribution
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2506.12515