Skip to Main content Skip to Navigation
Conference papers

A Unified Objective for Novel Class Discovery

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:
Document type :
Conference papers
Complete list of metadata
Contributor : Stéphane Lathuilière Connect in order to contact the contributor
Submitted on : Monday, September 6, 2021 - 4:31:55 PM
Last modification on : Tuesday, October 19, 2021 - 11:15:25 AM

Links full text


  • HAL Id : hal-03335979, version 1
  • ARXIV : 2108.08536



Enrico Fini, Enver Sangineto, Stéphane Lathuilière, Zhun Zhong, Moin Nabi, et al.. A Unified Objective for Novel Class Discovery. International Conference on Computer Vision, Oct 2021, virtual, France. ⟨hal-03335979⟩



Record views