학술논문
Avalanche: an End-to-End Library for Continual Learning
Document Type
Conference
Author
Lomonaco, Vincenzo; Pellegrini, Lorenzo; Cossu, Andrea; Carta, Antonio; Graffieti, Gabriele; Hayes, Tyler L.; De Lange, Matthias; Masana, Marc; Pomponi, Jary; van de Ven, Gido M.; Mundt, Martin; She, Qi; Cooper, Keiland; Forest, Jeremy; Belouadah, Eden; Calderara, Simone; Parisi, German I.; Cuzzolin, Fabio; Tolias, Andreas S.; Scardapane, Simone; Antiga, Luca; Ahmad, Subutai; Popescu, Adrian; Kanan, Christopher; van de Weijer, Joost; Tuytelaars, Tinne; Bacciu, Davide; Maltoni, Davide
Source
2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) CVPRW Computer Vision and Pattern Recognition Workshops (CVPRW), 2021 IEEE/CVF Conference on. :3595-3605 Jun, 2021
Subject
Language
ISSN
2160-7516
Abstract
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.