Novel Class Discovery: an Introduction and Key Concepts - Pôle Cyber & Réseaux Access content directly
Preprints, Working Papers, ... (Preprint) Year : 2023

Novel Class Discovery: an Introduction and Key Concepts

Abstract

Novel Class Discovery (NCD) is a growing field where we are given during training a labeled set of known classes and an unlabeled set of different classes that must be discovered. In recent years, many methods have been proposed to address this problem, and the field has begun to mature. In this paper, we provide a comprehensive survey of the state-of-the-art NCD methods. We start by formally defining the NCD problem and introducing important notions. We then give an overview of the different families of approaches, organized by the way they transfer knowledge from the labeled set to the unlabeled set. We find that they either learn in two stages, by first extracting knowledge from the labeled data only and then applying it to the unlabeled data, or in one stage by conjointly learning on both sets. For each family, we describe their general principle and detail a few representative methods. Then, we briefly introduce some new related tasks inspired by the increasing number of NCD works. We also present some common tools and techniques used in NCD, such as pseudo labeling, self-supervised learning and contrastive learning. Finally, to help readers unfamiliar with the NCD problem differentiate it from other closely related domains, we summarize some of the closest areas of research and discuss their main differences.
Fichier principal
Vignette du fichier
Novel_Class_Discovery__an_Introduction___Version_KAIS_23_02_2023.pdf (5.13 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-04158805 , version 1 (11-07-2023)

Identifiers

Cite

Colin Troisemaine, Vincent Lemaire, Stéphane Gosselin, Alexandre Reiffers-Masson, Joachim Flocon-Cholet, et al.. Novel Class Discovery: an Introduction and Key Concepts. 2023. ⟨hal-04158805⟩
21 View
25 Download

Altmetric

Share

Gmail Facebook X LinkedIn More