Self-supervised learning of Split Invariant Equivariant representations - Laboratoire d'informatique Gaspard-Monge Accéder directement au contenu
Pré-Publication, Document De Travail (Preprint/Prepublication) Année : 2023

Self-supervised learning of Split Invariant Equivariant representations

Résumé

Recent progress has been made towards learning invariant or equivariant representations with self-supervised learning. While invariant methods are evaluated on large scale datasets, equivariant ones are evaluated in smaller, more controlled, settings. We aim at bridging the gap between the two in order to learn more diverse representations that are suitable for a wide range of tasks. We start by introducing a dataset called 3DIEBench, consisting of renderings from 3D models over 55 classes and more than 2.5 million images where we have full control on the transformations applied to the objects. We further introduce a predictor architecture based on hypernetworks to learn equivariant representations with no possible collapse to invariance. We introduce SIE (Split Invariant-Equivariant) which combines the hypernetwork-based predictor with representations split in two parts, one invariant, the other equivariant, to learn richer representations. We demonstrate significant performance gains over existing methods on equivariance related tasks from both a qualitative and quantitative point of view. We further analyze our introduced predictor and show how it steers the learned latent space. We hope that both our introduced dataset and approach will enable learning richer representations without supervision in more complex scenarios.
Fichier principal
Vignette du fichier
main.pdf (10.09 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03984775 , version 1 (13-02-2023)
hal-03984775 , version 2 (19-06-2023)

Identifiants

Citer

Quentin Garrido, Laurent Najman, Yann Lecun. Self-supervised learning of Split Invariant Equivariant representations. 2023. ⟨hal-03984775v1⟩
97 Consultations
100 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More