Component Adaptive Clustering for Generalized Category Discovery

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Yan, Mingfu, Huang, Jiancheng, Liu, Yifan, Chen, Shifeng
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866908430429585408
author Yan, Mingfu
Huang, Jiancheng
Liu, Yifan
Chen, Shifeng
author_facet Yan, Mingfu
Huang, Jiancheng
Liu, Yifan
Chen, Shifeng
contents Generalized Category Discovery (GCD) tackles the challenging problem of categorizing unlabeled images into both known and novel classes within a partially labeled dataset, without prior knowledge of the number of unknown categories. Traditional methods often rely on rigid assumptions, such as predefining the number of classes, which limits their ability to handle the inherent variability and complexity of real-world data. To address these shortcomings, we propose AdaGCD, a cluster-centric contrastive learning framework that incorporates Adaptive Slot Attention (AdaSlot) into the GCD framework. AdaSlot dynamically determines the optimal number of slots based on data complexity, removing the need for predefined slot counts. This adaptive mechanism facilitates the flexible clustering of unlabeled data into known and novel categories by dynamically allocating representational capacity. By integrating adaptive representation with dynamic slot allocation, our method captures both instance-specific and spatially clustered features, improving class discovery in open-world scenarios. Extensive experiments on public and fine-grained datasets validate the effectiveness of our framework, emphasizing the advantages of leveraging spatial local information for category discovery in unlabeled image datasets.
format Preprint
id arxiv_https___arxiv_org_abs_2507_01711
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Component Adaptive Clustering for Generalized Category Discovery
Yan, Mingfu
Huang, Jiancheng
Liu, Yifan
Chen, Shifeng
Computer Vision and Pattern Recognition
Generalized Category Discovery (GCD) tackles the challenging problem of categorizing unlabeled images into both known and novel classes within a partially labeled dataset, without prior knowledge of the number of unknown categories. Traditional methods often rely on rigid assumptions, such as predefining the number of classes, which limits their ability to handle the inherent variability and complexity of real-world data. To address these shortcomings, we propose AdaGCD, a cluster-centric contrastive learning framework that incorporates Adaptive Slot Attention (AdaSlot) into the GCD framework. AdaSlot dynamically determines the optimal number of slots based on data complexity, removing the need for predefined slot counts. This adaptive mechanism facilitates the flexible clustering of unlabeled data into known and novel categories by dynamically allocating representational capacity. By integrating adaptive representation with dynamic slot allocation, our method captures both instance-specific and spatially clustered features, improving class discovery in open-world scenarios. Extensive experiments on public and fine-grained datasets validate the effectiveness of our framework, emphasizing the advantages of leveraging spatial local information for category discovery in unlabeled image datasets.
title Component Adaptive Clustering for Generalized Category Discovery
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2507.01711