Saved in:
Bibliographic Details
Main Authors: Cignoni, Giacomo, Cossu, Andrea, Gomez-Villa, Alex, van de Weijer, Joost, Carta, Antonio
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2502.09140
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916612127326208
author Cignoni, Giacomo
Cossu, Andrea
Gomez-Villa, Alex
van de Weijer, Joost
Carta, Antonio
author_facet Cignoni, Giacomo
Cossu, Andrea
Gomez-Villa, Alex
van de Weijer, Joost
Carta, Antonio
contents Online Continual Learning (OCL) methods train a model on a non-stationary data stream where only a few examples are available at a time, often leveraging replay strategies. However, usage of replay is sometimes forbidden, especially in applications with strict privacy regulations. Therefore, we propose Continual MultiPatches (CMP), an effective plug-in for existing OCL self-supervised learning strategies that avoids the use of replay samples. CMP generates multiple patches from a single example and projects them into a shared feature space, where patches coming from the same example are pushed together without collapsing into a single point. CMP surpasses replay and other SSL-based strategies on OCL streams, challenging the role of replay as a go-to solution for self-supervised OCL.
format Preprint
id arxiv_https___arxiv_org_abs_2502_09140
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Replay-free Online Continual Learning with Self-Supervised MultiPatches
Cignoni, Giacomo
Cossu, Andrea
Gomez-Villa, Alex
van de Weijer, Joost
Carta, Antonio
Machine Learning
Computer Vision and Pattern Recognition
I.2.6
Online Continual Learning (OCL) methods train a model on a non-stationary data stream where only a few examples are available at a time, often leveraging replay strategies. However, usage of replay is sometimes forbidden, especially in applications with strict privacy regulations. Therefore, we propose Continual MultiPatches (CMP), an effective plug-in for existing OCL self-supervised learning strategies that avoids the use of replay samples. CMP generates multiple patches from a single example and projects them into a shared feature space, where patches coming from the same example are pushed together without collapsing into a single point. CMP surpasses replay and other SSL-based strategies on OCL streams, challenging the role of replay as a go-to solution for self-supervised OCL.
title Replay-free Online Continual Learning with Self-Supervised MultiPatches
topic Machine Learning
Computer Vision and Pattern Recognition
I.2.6
url https://arxiv.org/abs/2502.09140