Uncertainty-Driven Past-Sample Selection for Replay-Based Continual Learning

Anxo-Lois Pereira, Eduardo Aguilar, Eduardo Aguilar, Petia Radeva

2025

Abstract

In a continual learning environment, methods must cope with catastrophic forgetting, i.e. avoid forgetting previously acquired knowledge when new data arrives. Replay-based methods have proven effective for this problem; in particular, simple strategies such as random selection have provided very competitive results. In this paper, we go a step further and propose a novel approach to image recognition utilizing a replay-based continual learning method with uncertainty-driven past-sample selection. Our method aims to address the challenges of data variability and evolving databases by selectively retaining and revisiting samples based on their uncertainty score. It ensures robust performance and adaptability, improving image classification accuracy over time. Based on uncertainty quantification, three groups of methods were proposed and validated, which we call: sample sorting, sample clustering, and sample filtering. We experimented and evaluated the proposed methods on three public datasets: CIFAR10, CIFAR100 and FOOD101. We obtained very encouraging results largely outperforming the baseline sample selection method for rehearsal on all the datasets.

Paper Citation

in Harvard Style

Pereira A., Aguilar E. and Radeva P. (2025). Uncertainty-Driven Past-Sample Selection for Replay-Based Continual Learning. In Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP; ISBN 978-989-758-728-3, SciTePress, pages 365-372. DOI: 10.5220/0013140700003912

in Bibtex Style

@conference{visapp25,
author={Anxo-Lois Pereira and Eduardo Aguilar and Petia Radeva},
title={Uncertainty-Driven Past-Sample Selection for Replay-Based Continual Learning},
booktitle={Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP},
year={2025},
pages={365-372},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013140700003912},
isbn={978-989-758-728-3},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP
TI - Uncertainty-Driven Past-Sample Selection for Replay-Based Continual Learning
SN - 978-989-758-728-3
AU - Pereira A.
AU - Aguilar E.
AU - Radeva P.
PY - 2025
SP - 365
EP - 372
DO - 10.5220/0013140700003912
PB - SciTePress