Semi-supervised learning made simple with self-supervised clustering - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Semi-supervised learning made simple with self-supervised clustering

Résumé

Self-supervised learning models have been shown to learn rich visual representations without requiring human annotations. However, in many real-world scenarios, labels are partially available, motivating a recent line of work on semi-supervised methods inspired by self-supervised principles. In this paper, we propose a conceptually simple yet empirically powerful approach to turn clustering-based self-supervised methods such as SwAV or DINO into semi-supervised learners. More precisely, we introduce a multi-task framework merging a supervised objective using ground-truth labels and a self-supervised objective relying on clustering assignments with a single cross-entropy loss. This approach may be interpreted as imposing the cluster centroids to be class prototypes. Despite its simplicity, we provide empirical evidence that our approach is highly effective and achieves state-of-the-art performance on CIFAR100 and ImageNet.
Fichier principal
Vignette du fichier
fini23.pdf (488.19 Ko) Télécharger le fichier
fini23-supp.pdf (1.61 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04073630 , version 1 (18-04-2023)

Licence

Paternité

Identifiants

Citer

Enrico Fini, Pietro Astolfi, Karteek Alahari, Xavier Alameda-Pineda, Julien Mairal, et al.. Semi-supervised learning made simple with self-supervised clustering. CVPR 2023 – IEEE/CVF Conference on Computer Vision and Pattern Recognition, Jun 2023, Vancouver, Canada. pp.1-11. ⟨hal-04073630⟩
113 Consultations
123 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More