Improving Plasticity in Online Continual Learning via Collaborative Learning - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2024

Improving Plasticity in Online Continual Learning via Collaborative Learning

Maorong Wang
  • Fonction : Auteur
  • PersonId : 1364824
Toshihiko Yamasaki
  • Fonction : Auteur
  • PersonId : 1364826

Résumé

Online Continual Learning (CL) solves the problem of learning the ever-emerging new classification tasks from a continuous data stream. Unlike its offline counterpart, in online CL, the training data can only be seen once. Most existing online CL research regards catastrophic forgetting (i.e., model stability) as almost the only challenge. In this paper, we argue that the model's capability to acquire new knowledge (i.e., model plasticity) is another challenge in online CL. While replay-based strategies have been shown to be effective in alleviating catastrophic forgetting, there is a notable gap in research attention toward improving model plasticity. To this end, we propose Collaborative Continual Learning (CCL), a collaborative learning based strategy to improve the model's capability in acquiring new concepts. Additionally, we introduce Distillation Chain (DC), a novel collaborative learning scheme to boost the training of the models. We adapted CCL-DC to existing representative online CL works. Extensive experiments demonstrate that even if the learners are well-trained with state-of-the-art online CL methods, our strategy can still improve model plasticity dramatically, and thereby improve the overall performance by a large margin.
Fichier principal
Vignette du fichier
2024_CVPR_Maorong-2.pdf (5.74 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04509749 , version 1 (18-03-2024)

Identifiants

Citer

Maorong Wang, Nicolas Michel, Ling Xiao, Toshihiko Yamasaki. Improving Plasticity in Online Continual Learning via Collaborative Learning. 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2024), Jun 2024, Seattle, WA, United States. ⟨hal-04509749⟩
4 Consultations
4 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More