A Comprehensive Empirical Evaluation on Online Continual Learning

by   Albin Soutif--Cormerais, et al.
Scuola Normale Superiore
Universitat Autònoma de Barcelona
University of Pisa
University of St. Gallen

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.


Online Continual Learning Via Candidates Voting

Continual learning in online scenario aims to learn a sequence of new ta...

Meta-Learning Representations for Continual Learning

A continual learning agent should be able to build on top of existing kn...

Adversarial Shapley Value Experience Replay for Task-Free Continual Learning

Continual learning is a branch of deep learning that seeks to strike a b...

Tackling Online One-Class Incremental Learning by Removing Negative Contrasts

Recent work studies the supervised online continual learning setting whe...

New Insights on Relieving Task-Recency Bias for Online Class Incremental Learning

To imitate the ability of keeping learning of human, continual learning ...

Rapid Adaptation in Online Continual Learning: Are We Evaluating It Right?

We revisit the common practice of evaluating adaptation of Online Contin...

New Insights on Reducing Abrupt Representation Change in Online Continual Learning

In the online continual learning paradigm, agents must learn from a chan...

Please sign up or login with your details

Forgot password? Click here to reset