BAL: Balancing Diversity and Novelty for Active Learning
IEEE Transactions on Pattern Analysis and Machine Intelligence · 2024-05 · 46 (5) · 3653-3664
DOI: 10.1109/tpami.2023.3345844 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024-05. Verfasst von Jingyao Li und 4 weiteren Autor:innen. Die Arbeit wurde bisher 25-mal zitiert (Crossref) und nennt 45 Literaturangaben.
Abstract (Originalsprache)
The objective of Active Learning is to strategically label a subset of the dataset to maximize performance within a predetermined labeling budget. In this study, we harness features acquired through self-supervised learning. We introduce a straightforward yet potent metric, Cluster Distance Difference, to identify diverse data. Subsequently, we introduce a novel framework, Balancing Active Learning (BAL), which constructs adaptive sub-pools to balance diverse and uncertain data. Our approach outperforms all established active learning methods on widely recognized benchmarks by 1.20%. Moreover, we assess the efficacy of our proposed framework under extended settings, encompassing both larger and smaller labeling budgets. Experimental results demonstrate that, when labeling 80% of the samples, the performance of the current SOTA method declines by 0.74%, whereas our proposed BAL achieves performance comparable to the full dataset.
Zitieren
APA
Li, J., Chen, P., Yu, S., Liu, S., & Jia, J. (2024). BAL: Balancing Diversity and Novelty for Active Learning. IEEE Transactions on Pattern Analysis and Machine Intelligence, 46(5), 3653-3664. https://doi.org/10.1109/tpami.2023.3345844
Vancouver
Li J, Chen P, Yu S, Liu S, Jia J. BAL: Balancing Diversity and Novelty for Active Learning. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2024;46(5):3653-3664. doi:10.1109/tpami.2023.3345844
BibTeX
@article{Li2024,
author = {Li, Jingyao and Chen, Pengguang and Yu, Shaozuo and Liu, Shu and Jia, Jiaya},
title = {BAL: Balancing Diversity and Novelty for Active Learning},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
year = {2024},
volume = {46},
number = {5},
pages = {3653--3664},
doi = {10.1109/tpami.2023.3345844}
}
EUVIMED