Abstract

Artificial neural networks thrive in solving the classification problem for a particular rigid task, acquiring knowledge through generalized learning behaviour from a distinct training phase. The resulting network resembles a static entity of knowledge, with endeavours to extend this knowledge without targeting the original task resulting in a catastrophic forgetting. Continual learning shifts this paradigm towards networks that can continually accumulate knowledge over different tasks without the need to retrain from scratch. We focus on task incremental classification, where tasks arrive sequentially and are delineated by clear boundaries. Our main contributions concern: (1) a taxonomy and extensive overview of the state-of-the-art; (2) a novel framework to continually determine the stability-plasticity trade-off of the continual learner; (3) a comprehensive experimental comparison of 11 state-of-the-art continual learning methods; and (4) baselines. We empirically scrutinize method strengths and weaknesses on three benchmarks, considering Tiny Imagenet and large-scale unbalanced iNaturalist and a sequence of recognition datasets. We study the influence of model capacity, weight decay and dropout regularization, and the order in which the tasks are presented, and qualitatively compare methods in terms of required memory, computation time, and storage.

Keywords

ForgettingComputer scienceArtificial intelligenceMachine learningTask (project management)Artificial neural networkTask analysisCognitive psychology

MeSH Terms

AlgorithmsLearningNeural NetworksComputer

Affiliated Institutions

Related Publications

Publication Info

Year
2021
Type
article
Volume
44
Issue
7
Pages
1-1
Citations
1488
Access
Closed

Social Impact

Social media, news, blog, policy document mentions

Citation Metrics

1488
OpenAlex
142
Influential
772
CrossRef

Cite This

Matthias Delange, Rahaf Aljundi, Marc Masana et al. (2021). A continual learning survey: Defying forgetting in classification tasks. IEEE Transactions on Pattern Analysis and Machine Intelligence , 44 (7) , 1-1. https://doi.org/10.1109/tpami.2021.3057446

Identifiers

DOI
10.1109/tpami.2021.3057446
PMID
33544669

Data Quality

Data completeness: 90%