In this paper, we study the problem of Novel Class Discovery (NCD). NCD aims at inferring novel object categories in an unlabeled set by leveraging from prior knowledge of a labeled set containing different, but related classes. Existing approaches tackle this problem by considering multiple objective functions, usually involving specialized loss terms for the labeled and the unlabeled samples respectively, and often requiring auxiliary regularization terms. In this paper we depart from this traditional scheme and introduce a UNified Objective function (UNO) for discovering novel classes, with the explicit purpose of favoring synergy between supervised and unsupervised learning. Using a multi-view self-labeling strategy, we generate pseudo-labels that can be treated homogeneously with ground truth labels. This leads to a single classification objective operating on both known and unknown classes. Despite its simplicity, UNO outperforms the state of the art by a significant margin on several benchmarks (≈+10% on CIFAR-100 and +8% on ImageNet). The project page is available at: https://ncd-uno.github.io.

A Unified Objective for Novel Class Discovery / Fini, E.; Sangineto, E.; Lathuiliere, S.; Zhong, Z.; Nabi, M.; Ricci, E.. - (2021), pp. 9264-9272. (Intervento presentato al convegno 18th IEEE/CVF International Conference on Computer Vision, ICCV 2021 tenutosi a Virtual nel 2021) [10.1109/ICCV48922.2021.00915].

A Unified Objective for Novel Class Discovery

Fini E.;Sangineto E.;Zhong Z.;Nabi M.;Ricci E.
2021-01-01

Abstract

In this paper, we study the problem of Novel Class Discovery (NCD). NCD aims at inferring novel object categories in an unlabeled set by leveraging from prior knowledge of a labeled set containing different, but related classes. Existing approaches tackle this problem by considering multiple objective functions, usually involving specialized loss terms for the labeled and the unlabeled samples respectively, and often requiring auxiliary regularization terms. In this paper we depart from this traditional scheme and introduce a UNified Objective function (UNO) for discovering novel classes, with the explicit purpose of favoring synergy between supervised and unsupervised learning. Using a multi-view self-labeling strategy, we generate pseudo-labels that can be treated homogeneously with ground truth labels. This leads to a single classification objective operating on both known and unknown classes. Despite its simplicity, UNO outperforms the state of the art by a significant margin on several benchmarks (≈+10% on CIFAR-100 and +8% on ImageNet). The project page is available at: https://ncd-uno.github.io.
2021
Proceedings of the IEEE International Conference on Computer Vision
Virtual
Institute of Electrical and Electronics Engineers Inc.
978-1-6654-2812-5
Fini, E.; Sangineto, E.; Lathuiliere, S.; Zhong, Z.; Nabi, M.; Ricci, E.
A Unified Objective for Novel Class Discovery / Fini, E.; Sangineto, E.; Lathuiliere, S.; Zhong, Z.; Nabi, M.; Ricci, E.. - (2021), pp. 9264-9272. (Intervento presentato al convegno 18th IEEE/CVF International Conference on Computer Vision, ICCV 2021 tenutosi a Virtual nel 2021) [10.1109/ICCV48922.2021.00915].
File in questo prodotto:
Non ci sono file associati a questo prodotto.

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/11572/341688
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 73
  • ???jsp.display-item.citation.isi??? 14
social impact