Few-Shot Class-Incremental Learning for Classification and Object Detection: A Survey
IEEE Transactions on Pattern Analysis and Machine Intelligence · 2025-04 · 47 (4) · 2924-2945
DOI: 10.1109/tpami.2025.3529038 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025-04. Verfasst von Jinghua Zhang und 4 weiteren Autor:innen. Die Arbeit wurde bisher 92-mal zitiert (Crossref) und nennt 117 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Science and Technology Innovation Program of Hunan Province, Key Stone.
Abstract (Originalsprache)
Few-shot Class-Incremental Learning (FSCIL) presents a unique challenge in Machine Learning (ML), as it necessitates the Incremental Learning (IL) of new classes from sparsely labeled training samples without forgetting previous knowledge. While this field has seen recent progress, it remains an active exploration area. This paper aims to provide a comprehensive and systematic review of FSCIL. In our in-depth examination, we delve into various facets of FSCIL, encompassing the problem definition, the discussion of the primary challenges of unreliable empirical risk minimization and the stability-plasticity dilemma, general schemes, and relevant problems of IL and Few-shot Learning (FSL). Besides, we offer an overview of benchmark datasets and evaluation metrics. Furthermore, we introduce the Few-shot Class-incremental Classification (FSCIC) methods from data-based, structure-based, and optimization-based approaches and the Few-shot Class-incremental Object Detection (FSCIOD) methods from anchor-free and anchor-based approaches. Beyond these, we present several promising research directions within FSCIL that merit further investigation.
Förderung
- National Natural Science Foundation of China
- Science and Technology Innovation Program of Hunan Province
- Key Stone
- National University of Defense Technology
Zitieren
APA
Zhang, J., Liu, L., Silven, O., Pietikainen, M., & Hu, D. (2025). Few-Shot Class-Incremental Learning for Classification and Object Detection: A Survey. IEEE Transactions on Pattern Analysis and Machine Intelligence, 47(4), 2924-2945. https://doi.org/10.1109/tpami.2025.3529038
Vancouver
Zhang J, Liu L, Silven O, Pietikainen M, Hu D. Few-Shot Class-Incremental Learning for Classification and Object Detection: A Survey. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2025;47(4):2924-2945. doi:10.1109/tpami.2025.3529038
BibTeX
@article{Zhang2025,
author = {Zhang, Jinghua and Liu, Li and Silven, Olli and Pietikainen, Matti and Hu, Dewen},
title = {Few-Shot Class-Incremental Learning for Classification and Object Detection: A Survey},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
year = {2025},
volume = {47},
number = {4},
pages = {2924--2945},
doi = {10.1109/tpami.2025.3529038}
}
EUVIMED