BAL: Balancing Diversity and Novelty for Active Learning
Abstract
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. Codes are available at https://github.com/JulietLJY/BAL.
Cite
@article{arxiv.2312.15944,
title = {BAL: Balancing Diversity and Novelty for Active Learning},
author = {Jingyao Li and Pengguang Chen and Shaozuo Yu and Shu Liu and Jiaya Jia},
journal= {arXiv preprint arXiv:2312.15944},
year = {2023}
}
Comments
Our paper is accepted by TPAMI