%0 Conference Proceedings
%T Avalanche: an End-to-End Library for Continual Learning
%A Vincenzo Lomonaco
%A Lorenzo Pellegrini
%A Andrea Cossu
%A Antonio Carta
%A Gabriele Graffieti
%A Tyler L. Hayes
%A Matthias De Lange
%A Marc Masana
%A Jary Pomponi
%A Gido van de Ven
%A Martin Mundt
%A Qi She
%A Keiland Cooper
%A Jeremy Forest
%A Eden Belouadah
%A Simone Calderara
%A German I. Parisi
%A Fabio Cuzzolin
%A Andreas Tolias
%A Simone Scardapane
%A Luca Antiga
%A Subutai Amhad
%A Adrian Popescu
%A Christopher Kanan
%A Joost Van de Weijer
%A Tinne Tuytelaars
%A Davide Bacciu
%A Davide Maltoni
%B 34th IEEE Conference on Computer Vision and Pattern Recognition Workshops
%D 2021
%F Vincenzo Lomonaco2021
%O LAMP; 600.120
%O exported from refbase (http://refbase.cvc.uab.es/show.php?record=3567), last updated on Mon, 24 Oct 2022 15:46:27 +0200
%X 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.
%U http://refbase.cvc.uab.es/files/LPC2021.pdf
%U http://dx.doi.org/10.1109/CVPRW53098.2021.00399
%P 3595-3605