Meta-learning Approaches for Few-Shot Learning: A Survey of Recent Advances
ACM Computing Surveys · 31.12.2024 · 56 (12) · 1-41
DOI: 10.1145/3659943 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Computing Surveys, online erschienen am 25.07.2024. Verfasst von Hassan Gharoun und 3 weiteren Autor:innen. Die Arbeit wurde bisher 224-mal zitiert (Crossref) und nennt 131 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Despite its astounding success in learning deeper multi-dimensional data, the performance of deep learning declines on new unseen tasks mainly due to its focus on same-distribution prediction. Moreover, deep learning is notorious for poor generalization from few samples. Meta-learning is a promising approach that addresses these issues by adapting to new tasks with few-shot datasets. This survey first briefly introduces meta-learning and then investigates state-of-the-art meta-learning methods and recent advances in: (i) metric-based, (ii) memory-based, (iii), and learning-based methods. Finally, current challenges and insights for future researches are discussed.
Zitieren
APA
Gharoun, H., Momenifar, F., Chen, F., & Gandomi, A. H. (2024). Meta-learning Approaches for Few-Shot Learning: A Survey of Recent Advances. ACM Computing Surveys, 56(12), 1-41. https://doi.org/10.1145/3659943
Vancouver
Gharoun H, Momenifar F, Chen F, Gandomi AH. Meta-learning Approaches for Few-Shot Learning: A Survey of Recent Advances. ACM Computing Surveys. 2024;56(12):1-41. doi:10.1145/3659943
BibTeX
@article{Gharoun2024,
author = {Gharoun, Hassan and Momenifar, Fereshteh and Chen, Fang and Gandomi, Amir H.},
title = {Meta-learning Approaches for Few-Shot Learning: A Survey of Recent Advances},
journal = {ACM Computing Surveys},
year = {2024},
volume = {56},
number = {12},
pages = {1--41},
doi = {10.1145/3659943}
}
EUVIMED