DyTox: Transformers for Continual Learning with DYnamic TOken eXpansion - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

DyTox: Transformers for Continual Learning with DYnamic TOken eXpansion

Matthieu Cord
Arthur Douillard
  • Fonction : Auteur
Alexandre Ramé
  • Fonction : Auteur
  • PersonId : 1120615
  • IdRef : 276144511
Guillaume Couairon

Résumé

Deep network architectures struggle to continually learn new tasks without forgetting the previous tasks. A recent trend indicates that dynamic architectures based on an expansion of the parameters can reduce catastrophic forgetting efficiently in continual learning. However, existing approaches often require a task identifier at test-time, need complex tuning to balance the growing number of parameters, and barely share any information across tasks. As a result, they struggle to scale to a large number of tasks without significant overhead. In this paper, we propose a transformer architecture based on a dedicated encoder/decoder framework. Critically, the encoder and decoder are shared among all tasks. Through a dynamic expansion of special tokens, we specialize each forward of our decoder network on a task distribution. Our strategy scales to a large number of tasks while having negligible memory and time overheads due to strict control of the expansion of the parameters. Moreover, this efficient strategy doesn't need any hyperparameter tuning to control the network's expansion. Our model reaches excellent results on CIFAR100 and state-of-the-art performances on the large-scale ImageNet100 and ImageNet1000 while having fewer parameters than concurrent dynamic frameworks. 1
Fichier principal
Vignette du fichier
Douillard_DyTox_Transformers_for_Continual_Learning_With_DYnamic_TOken_eXpansion_CVPR_2022_paper.pdf (5.9 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03997873 , version 1 (20-02-2023)

Identifiants

Citer

Matthieu Cord, Arthur Douillard, Alexandre Ramé, Guillaume Couairon. DyTox: Transformers for Continual Learning with DYnamic TOken eXpansion. IEEE/CVF Conference on Computer Vision and Pattern Recognition, Jun 2022, New Orleans, United States. ⟨10.1109/CVPR52688.2022.00907⟩. ⟨hal-03997873⟩
18 Consultations
20 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More