Class-Incremental Learning: Survey and Performance Evaluation on Image Classification
IEEE Transactions on Pattern Analysis and Machine Intelligence · 01.05.2023 · 45 (5) · 5513-5533
DOI: 10.1109/tpami.2022.3213473 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, erschienen am 01.05.2023. Verfasst von Marc Masana und 5 weiteren Autor:innen. Die Arbeit wurde bisher 658-mal zitiert (Crossref) und nennt 124 Literaturangaben. Gefördert von: Huawei Kirin Solution, Generalitat de Catalunya, Spanish Project.
Abstract (Originalsprache)
For future learning systems, incremental learning is desirable because it allows for: efficient resource usage by eliminating the need to retrain from scratch at the arrival of new data; reduced memory usage by preventing or limiting the amount of data required to be stored - also important when privacy limitations are imposed; and learning that more closely resembles human learning. The main challenge for incremental learning is catastrophic forgetting, which refers to the precipitous drop in performance on previously learned tasks after learning a new one. Incremental learning of deep neural networks has seen explosive growth in recent years. Initial work focused on task-incremental learning, where a task-ID is provided at inference time. Recently, we have seen a shift towards class-incremental learning where the learner must discriminate at inference time between all classes seen in previous tasks without recourse to a task-ID. In this paper, we provide a complete survey of existing class-incremental learning methods for image classification, and in particular, we perform an extensive experimental evaluation on thirteen class-incremental methods. We consider several new experimental scenarios, including a comparison of class-incremental methods on multiple large-scale image classification datasets, an investigation into small and large domain shifts, and a comparison of various network architectures.
Förderung
- Huawei Kirin Solution
- Generalitat de Catalunya
- Spanish Project
- European Commission
Zitieren
APA
Masana, M., Liu, X., Twardowski, B., Menta, M., Bagdanov, A. D., & van de Weijer, J. (2023). Class-Incremental Learning: Survey and Performance Evaluation on Image Classification. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(5), 5513-5533. https://doi.org/10.1109/tpami.2022.3213473
Vancouver
Masana M, Liu X, Twardowski B, Menta M, Bagdanov AD, van de Weijer J. Class-Incremental Learning: Survey and Performance Evaluation on Image Classification. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2023;45(5):5513-5533. doi:10.1109/tpami.2022.3213473
BibTeX
@article{Masana2023,
author = {Masana, Marc and Liu, Xialei and Twardowski, Bartlomiej and Menta, Mikel and Bagdanov, Andrew D and van de Weijer, Joost},
title = {Class-Incremental Learning: Survey and Performance Evaluation on Image Classification},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
year = {2023},
volume = {45},
number = {5},
pages = {5513--5533},
doi = {10.1109/tpami.2022.3213473}
}
EUVIMED