Avalanche: an End-to-End Library for Continual Learning

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...

Full description

Saved in:
Bibliographic Details
Published in2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) pp. 3595 - 3605
Main Authors 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
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.06.2021
Subjects
Collaboration
Computer vision
Conferences
Deep learning
Libraries
Machine learning algorithms
Training
Online AccessGet full text

Cover

More Information
Summary: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.
ISSN:2160-7516
DOI:10.1109/CVPRW53098.2021.00399