Multi-Task Learning Based on Log Dynamic Loss Weighting for Sex Classification and Age Estimation on Panoramic Radiographs

Igor Prado, David Lima, Julian Liang, Ana Hougaz, Bernardo Peters, Luciano Oliveira

2024

Abstract

This paper introduces a multi-task learning (MTL) approach for simultaneous sex classification and age estimation in panoramic radiographs, aligning with the tasks pertinent to forensic dentistry. For that, we dynamically optimize the logarithm of the task-specific weights during the loss training. Our results demonstrate the superior performance of our proposed MTL network compared to the individual task-based networks, particularly evident across a diverse data set comprising 7,666 images, spanning ages from 1 to 90 years and encompassing significant sex variability. Our network achieved an F1-score of 90.37%±0.54 and a mean absolute error of 5.66±0.22 through a cross-validation assessment procedure, which resulted in a gain of 1.69 percentage points and 1.15 years with respect to the individual sex classification and age estimation procedures. To the best of our knowledge, it is the first successful MTL-based network for these two tasks.

Paper Citation

in Harvard Style

Prado I., Lima D., Liang J., Hougaz A., Peters B. and Oliveira L. (2024). Multi-Task Learning Based on Log Dynamic Loss Weighting for Sex Classification and Age Estimation on Panoramic Radiographs. In Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP; ISBN 978-989-758-679-8, SciTePress, pages 385-392. DOI: 10.5220/0012317100003660

in Bibtex Style

@conference{visapp24,
author={Igor Prado and David Lima and Julian Liang and Ana Hougaz and Bernardo Peters and Luciano Oliveira},
title={Multi-Task Learning Based on Log Dynamic Loss Weighting for Sex Classification and Age Estimation on Panoramic Radiographs},
booktitle={Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP},
year={2024},
pages={385-392},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012317100003660},
isbn={978-989-758-679-8},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP
TI - Multi-Task Learning Based on Log Dynamic Loss Weighting for Sex Classification and Age Estimation on Panoramic Radiographs
SN - 978-989-758-679-8
AU - Prado I.
AU - Lima D.
AU - Liang J.
AU - Hougaz A.
AU - Peters B.
AU - Oliveira L.
PY - 2024
SP - 385
EP - 392
DO - 10.5220/0012317100003660
PB - SciTePress