Avalanche: an end-to-end library for continual learning - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

Avalanche: an end-to-end library for continual learning

Qi She
  • Fonction : Auteur
Luca Antiga
  • Fonction : Auteur
Subutai Ahmad
  • Fonction : Auteur

Résumé

Learning continually from non-stationary data streams is a long-standing goal and a challenging problem in machine learning. Recently, we have witnessed a renewed and fast-growing interest in continual learning, especially within the deep learning community. However, algorithmic solutions are often difficult to re-implement, evaluate and port across different settings, where even results on standard benchmarks are hard to reproduce. In this work, we propose Avalanche, an open-source end-to-end library for continual learning research based on PyTorch. Avalanche is designed to provide a shared and collaborative codebase for fast prototyping, training, and reproducible evaluation of continual learning algorithms.
Fichier principal
Vignette du fichier
Lomonaco_Avalanche_An_End-to-End_Library_for_Continual_Learning_CVPRW_2021_paper.pdf (496.55 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04315450 , version 1 (30-11-2023)

Licence

Paternité - Pas d'utilisation commerciale - Pas de modification

Identifiants

Citer

Vincenzo Lomonaco, Lorenzo Pellegrini, Andrea Cossu, Antonio Carta, Gabriele Graffieti, et al.. Avalanche: an end-to-end library for continual learning. CVPRW 2021 - 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, Jun 2021, Nashville, United States. pp.3595-3605, ⟨10.1109/CVPRW53098.2021.00399⟩. ⟨hal-04315450⟩
13 Consultations
21 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More