CTypiClust: Confidence-Aware Typical Clustering for Budget-Agnostic Active Learning with Confidence Calibration

Takuya Okano, Yohei Minekawa, Miki Hayakawa

2025

Abstract

Active Learning (AL) has been widely studied to reduce annotation costs in deep learning. In AL, the appropriate method varies depending on the number of annotatable data (budget). In low-budget settings, it is appropriate to prioritize sampling typical data, while in high-budget settings, it is better to prioritize sampling data with high uncertainty. This study proposes Confidence-aware Typical Clustering (CTypiClust), an AL method that performs well regardless of the budget. CTypiClust dynamically switches between typical data sampling and low-confidence data sampling based on confidence. Additionally, to mitigate the overconfidence problem in low-budget settings, we propose a new confidence calibration method Cluster-Enhanced Confidence (CEC). By applying CEC to CTypiClust, we suppress the occurrence of overconfidence in low-budget settings. To evaluate the effectiveness of the proposed method, we conducted experiments using multiple benchmark datasets, and confirmed that CTypiClust consistently shows high performance regardless of the budget.

Paper Citation

in Harvard Style

Okano T., Minekawa Y. and Hayakawa M. (2025). CTypiClust: Confidence-Aware Typical Clustering for Budget-Agnostic Active Learning with Confidence Calibration. In Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP; ISBN 978-989-758-728-3, SciTePress, pages 340-347. DOI: 10.5220/0013139400003912

in Bibtex Style

@conference{visapp25,
author={Takuya Okano and Yohei Minekawa and Miki Hayakawa},
title={CTypiClust: Confidence-Aware Typical Clustering for Budget-Agnostic Active Learning with Confidence Calibration},
booktitle={Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP},
year={2025},
pages={340-347},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013139400003912},
isbn={978-989-758-728-3},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP
TI - CTypiClust: Confidence-Aware Typical Clustering for Budget-Agnostic Active Learning with Confidence Calibration
SN - 978-989-758-728-3
AU - Okano T.
AU - Minekawa Y.
AU - Hayakawa M.
PY - 2025
SP - 340
EP - 347
DO - 10.5220/0013139400003912
PB - SciTePress