We study the new task of class-incremental Novel Class Discovery (class-iNCD), which refers to the problem of discovering novel categories in an unlabelled data set by leveraging a pre-trained model that has been trained on a labelled data set containing disjoint yet related categories. Apart from discovering novel classes, we also aim at preserving the ability of the model to recognize previously seen base categories. Inspired by rehearsal-based incremental learning methods, in this paper we propose a novel approach for class-iNCD which prevents forgetting of past information about the base classes by jointly exploiting base class feature prototypes and feature-level knowledge distillation. We also propose a self-training clustering strategy that simultaneously clusters novel categories and trains a joint classifier for both the base and novel classes. This makes our method able to operate in a class-incremental setting. Our experiments, conducted on three common benchmarks, demonstrate that our method significantly outperforms state-of-the-art approaches.

Class-Incremental Novel Class Discovery / Roy, Subhankar; Liu, Mingxuan; Zhong, Zhun; Sebe, Nicu; Ricci, Elisa. - 13693:(2022), pp. 317-333. (Intervento presentato al convegno European Conference on Computer Vision (ECCV) tenutosi a Tel Aviv nel 23-27 October 2022) [10.1007/978-3-031-19827-4_19].

Class-Incremental Novel Class Discovery

Roy, Subhankar;Liu, Mingxuan;Zhong, Zhun;Sebe, Nicu;Ricci, Elisa
2022-01-01

Abstract

We study the new task of class-incremental Novel Class Discovery (class-iNCD), which refers to the problem of discovering novel categories in an unlabelled data set by leveraging a pre-trained model that has been trained on a labelled data set containing disjoint yet related categories. Apart from discovering novel classes, we also aim at preserving the ability of the model to recognize previously seen base categories. Inspired by rehearsal-based incremental learning methods, in this paper we propose a novel approach for class-iNCD which prevents forgetting of past information about the base classes by jointly exploiting base class feature prototypes and feature-level knowledge distillation. We also propose a self-training clustering strategy that simultaneously clusters novel categories and trains a joint classifier for both the base and novel classes. This makes our method able to operate in a class-incremental setting. Our experiments, conducted on three common benchmarks, demonstrate that our method significantly outperforms state-of-the-art approaches.
2022
European Conference on Computer Vision (ECCV)
Heidelberg
Springer
978-3-031-19826-7
978-3-031-19827-4
Roy, Subhankar; Liu, Mingxuan; Zhong, Zhun; Sebe, Nicu; Ricci, Elisa
Class-Incremental Novel Class Discovery / Roy, Subhankar; Liu, Mingxuan; Zhong, Zhun; Sebe, Nicu; Ricci, Elisa. - 13693:(2022), pp. 317-333. (Intervento presentato al convegno European Conference on Computer Vision (ECCV) tenutosi a Tel Aviv nel 23-27 October 2022) [10.1007/978-3-031-19827-4_19].
File in questo prodotto:
File Dimensione Formato  
136930312.pdf

Open Access dal 03/11/2023

Tipologia: Post-print referato (Refereed author’s manuscript)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 1.9 MB
Formato Adobe PDF
1.9 MB 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/11572/361310
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 7
  • ???jsp.display-item.citation.isi??? 6
social impact