TY - CONF AU - Vincenzo Lomonaco AU - Lorenzo Pellegrini AU - Andrea Cossu AU - Antonio Carta AU - Gabriele Graffieti AU - Tyler L. Hayes AU - Matthias De Lange AU - Marc Masana AU - Jary Pomponi AU - Gido van de Ven AU - Martin Mundt AU - Qi She AU - Keiland Cooper AU - Jeremy Forest AU - Eden Belouadah AU - Simone Calderara AU - German I. Parisi AU - Fabio Cuzzolin AU - Andreas Tolias AU - Simone Scardapane AU - Luca Antiga AU - Subutai Amhad AU - Adrian Popescu AU - Christopher Kanan AU - Joost Van de Weijer AU - Tinne Tuytelaars AU - Davide Bacciu AU - Davide Maltoni A2 - CVPRW PY - 2021// TI - Avalanche: an End-to-End Library for Continual Learning BT - 34th IEEE Conference on Computer Vision and Pattern Recognition Workshops SP - 3595 EP - 3605 N2 - 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. L1 - http://refbase.cvc.uab.es/files/LPC2021.pdf UR - http://dx.doi.org/10.1109/CVPRW53098.2021.00399 N1 - LAMP; 600.120 ID - Vincenzo Lomonaco2021 ER -