Classifier Ensemble for Efficient Uncertainty Calibration of Deep Neural Networks for Image Classification

Michael Schulze, Nikolas Ebert, Laurenz Reichardt, Oliver Wasenmüller

2025

Abstract

This paper investigates novel classifier ensemble techniques for uncertainty calibration applied to various deep neural networks for image classification. We evaluate both accuracy and calibration metrics, focusing on Expected Calibration Error (ECE) and Maximum Calibration Error (MCE). Our work compares different methods for building simple yet efficient classifier ensembles, including majority voting and several metamodel-based approaches. Our evaluation reveals that while state-of-the-art deep neural networks for image classification achieve high accuracy on standard datasets, they frequently suffer from significant calibration errors. Basic ensemble techniques like majority voting provide modest improvements, while metamodel-based ensembles consistently reduce ECE and MCE across all architectures. Notably, the largest of our compared metamodels demonstrate the most substantial calibration improvements, with minimal impact on accuracy. Moreover, classifier ensembles with metamodels outperform traditional model ensembles in calibration performance, while requiring significantly fewer parameters. In comparison to traditional post-hoc calibration methods, our approach removes the need for a separate calibration dataset. These findings underscore the potential of our proposed metamodel-based classifier ensembles as an efficient and effective approach to improving model calibration, thereby contributing to more reliable deep learning systems.

Paper Citation

in Harvard Style

Schulze M., Ebert N., Reichardt L. and Wasenmüller O. (2025). Classifier Ensemble for Efficient Uncertainty Calibration of Deep Neural Networks for Image Classification. 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 316-323. DOI: 10.5220/0013129000003912

in Bibtex Style

@conference{visapp25,
author={Michael Schulze and Nikolas Ebert and Laurenz Reichardt and Oliver Wasenmüller},
title={Classifier Ensemble for Efficient Uncertainty Calibration of Deep Neural Networks for Image Classification},
booktitle={Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP},
year={2025},
pages={316-323},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013129000003912},
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 - Classifier Ensemble for Efficient Uncertainty Calibration of Deep Neural Networks for Image Classification
SN - 978-989-758-728-3
AU - Schulze M.
AU - Ebert N.
AU - Reichardt L.
AU - Wasenmüller O.
PY - 2025
SP - 316
EP - 323
DO - 10.5220/0013129000003912
PB - SciTePress