Generalized category discovery (GCD) is a recently proposed open-world problem, which aims to automatically cluster partially labeled data. The main challenge is that the unlabeled data contain instances that are not only from known categories of the labeled data but also from novel categories. This leads traditional novel category discovery (NCD) methods to be incapacitated for GCD, due to their assumption of unlabeled data are only from novel categories. One effective way for GCD is applying self-supervised learning to learn discriminate representation for unlabeled data. However, this manner largely ignores underlying relationships between instances of the same concepts (e.g., class, super-class, and sub-class), which results in inferior representation learning. In this paper, we propose a Dynamic Conceptional Contrastive Learning (DCCL)framework, which can effectively improve clustering accuracy by alternately estimating underlying visual conceptions and learning conceptional representation. In addition, we design a dynamic conception generation and update mechanism, which is able to ensure consistent conception learning and thus further facilitate the optimization of DCCL. Extensive experiments show that DCCL achieves new state-of-the-art performances on six generic and fine-grained visual recognition datasets, especially on fine-grained ones. For example, our method significantly surpasses the best competitor by 16.2% on the new classes for the CUB-200 dataset. Code is available at https://github.com/TPCD/DCCL

Dynamic Conceptional Contrastive Learning for Generalized Category Discovery / Pu, N.; Zhong, Z.; Sebe, N.. - 2023:(2023), pp. 7579-7588. (Intervento presentato al convegno 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023 tenutosi a Vancouver, BC, Canada nel 17-24 June 2023) [10.1109/CVPR52729.2023.00732].

Dynamic Conceptional Contrastive Learning for Generalized Category Discovery

Pu, N.;Zhong, Z.;Sebe, N.
2023-01-01

Abstract

Generalized category discovery (GCD) is a recently proposed open-world problem, which aims to automatically cluster partially labeled data. The main challenge is that the unlabeled data contain instances that are not only from known categories of the labeled data but also from novel categories. This leads traditional novel category discovery (NCD) methods to be incapacitated for GCD, due to their assumption of unlabeled data are only from novel categories. One effective way for GCD is applying self-supervised learning to learn discriminate representation for unlabeled data. However, this manner largely ignores underlying relationships between instances of the same concepts (e.g., class, super-class, and sub-class), which results in inferior representation learning. In this paper, we propose a Dynamic Conceptional Contrastive Learning (DCCL)framework, which can effectively improve clustering accuracy by alternately estimating underlying visual conceptions and learning conceptional representation. In addition, we design a dynamic conception generation and update mechanism, which is able to ensure consistent conception learning and thus further facilitate the optimization of DCCL. Extensive experiments show that DCCL achieves new state-of-the-art performances on six generic and fine-grained visual recognition datasets, especially on fine-grained ones. For example, our method significantly surpasses the best competitor by 16.2% on the new classes for the CUB-200 dataset. Code is available at https://github.com/TPCD/DCCL
2023
Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Piscataway, NJ USA
IEEE Computer Society
979-8-3503-0129-8
Pu, N.; Zhong, Z.; Sebe, N.
Dynamic Conceptional Contrastive Learning for Generalized Category Discovery / Pu, N.; Zhong, Z.; Sebe, N.. - 2023:(2023), pp. 7579-7588. (Intervento presentato al convegno 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023 tenutosi a Vancouver, BC, Canada nel 17-24 June 2023) [10.1109/CVPR52729.2023.00732].
File in questo prodotto:
File Dimensione Formato  
Pu_Dynamic_Conceptional_Contrastive_Learning_for_Generalized_Category_Discovery_CVPR_2023_paper (1).pdf

accesso aperto

Descrizione: CVPR paper is the Open Access version, provided by the Computer Vision Foundation
Tipologia: Post-print referato (Refereed author’s manuscript)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 8.58 MB
Formato Adobe PDF
8.58 MB Adobe PDF Visualizza/Apri
Dynamic_Conceptional_Contrastive_Learning_for_Generalized_Category_Discovery.pdf

Solo gestori archivio

Tipologia: Versione editoriale (Publisher’s layout)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 575.07 kB
Formato Adobe PDF
575.07 kB Adobe PDF   Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11572/395049
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 16
  • ???jsp.display-item.citation.isi??? 8
social impact