# A Comprehensive Empirical Evaluation on Online Continual Learning

Source: [A Comprehensive Empirical Evaluation on Online Continual Learning](<https://www.sota2.com/research/paper/68fa70b41e209131cea4cb11>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T01:47:58.595Z

Authors: Albin Soutif--Cormerais, Antonio Carta, Andrea Cossu, Julio Hurtado, Hamed Hemati, Vincenzo Lomonaco, Joost Van de Weijer

Published: 2023-08-20T17:52:02.000Z

## Abstract

Online continual learning aims to get closer to a live learning experience by learning directly on a stream of data with temporally shifting distribution and by storing a minimum amount of data from that stream. In this empirical evaluation, we evaluate various methods from the literature that tackle online continual learning. More specifically, we focus on the class-incremental setting in the context of image classification, where the learner must learn new classes incrementally from a stream of data. We compare these methods on the Split-CIFAR100 and Split-TinyImagenet benchmarks, and measure their average accuracy, forgetting, stability, and quality of the representations, to evaluate various aspects of the algorithm at the end but also during the whole training period. We find that most methods suffer from stability and underfitting issues. However, the learned representations are comparable to i.i.d. training under the same computational budget. No clear winner emerges from the results and basic experience replay, when properly tuned and implemented, is a very strong baseline. We release our modular and extensible codebase at https://github.com/AlbinSou/ocl\_survey based on the avalanche framework to reproduce our results and encourage future research.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2308.10328>)

[PDF](<https://arxiv.org/pdf/2308.10328.pdf>)
