Self-Supervised Models are Continual Learners - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

Self-Supervised Models are Continual Learners

Résumé

Self-supervised models have been shown to produce comparable or better visual representations than their supervised counterparts when trained offline on unlabeled data at scale. However, their efficacy is catastrophically reduced in a Continual Learning (CL) scenario where data is presented to the model sequentially. In this paper, we show that self-supervised loss functions can be seamlessly converted into distillation mechanisms for CL by adding a predictor network that maps the current state of the representations to their past state. This enables us to devise a framework for Continual self-supervised visual representation Learning that (i) significantly improves the quality of the learned representations, (ii) is compatible with several state-of-the-art self-supervised objectives, and (iii) needs little to no hyperparameter tuning. We demonstrate the effectiveness of our approach empirically by training six popular self-supervised models in various CL settings.

Dates et versions

hal-03626342 , version 1 (31-03-2022)

Identifiants

Citer

Enrico Fini, Victor da Costa, Xavier Alameda-Pineda, Elisa Ricci, Karteek Alahari, et al.. Self-Supervised Models are Continual Learners. CVPR 2022 - IEEE/CVF Conference on Computer Vision and Pattern Recognition, Jun 2022, New Orleans, United States. pp.9611-9620, ⟨10.1109/CVPR52688.2022.00940⟩. ⟨hal-03626342⟩
191 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More