Towards Explainability in Using Deep Learning for Face Detection in Paintings

Siwar Bengamra, Siwar Bengamra, Olfa Mzoughi, André Bigand, Ezzeddine Zagrouba

2023

Abstract

Explainable Artificial Intelligence (XAI) is an active research area to interpret a neural network’s decision by ensuring transparency and trust in the task-specified learned models. In fact, despite the great success of deep learning networks in many fields, their adoption by practitioners presents some limits, one significant of them is the complex nature of these networks which prevents human comprehension of the decision-making process. This is especially the case in artworks analysis. To address this issue, we explore Detector Randomized Input Sampling for Explanation (DRISE), a visualization method for explainable artificial intelligence to comprehend and improve CNN-based face detector on Tenebrism painting images. The results obtained show local explanations for model’s prediction and consequently offer insights into the model’s decision-making. This paper will be of great help to researchers as a future support for explainability of object detection in other domain application.

Paper Citation

in Harvard Style

Bengamra S., Mzoughi O., Bigand A. and Zagrouba E. (2023). Towards Explainability in Using Deep Learning for Face Detection in Paintings. In Proceedings of the 12th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-758-626-2, pages 832-841. DOI: 10.5220/0011670300003411

in Bibtex Style

@conference{icpram23,
author={Siwar Bengamra and Olfa Mzoughi and André Bigand and Ezzeddine Zagrouba},
title={Towards Explainability in Using Deep Learning for Face Detection in Paintings},
booktitle={Proceedings of the 12th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2023},
pages={832-841},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011670300003411},
isbn={978-989-758-626-2},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 12th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - Towards Explainability in Using Deep Learning for Face Detection in Paintings
SN - 978-989-758-626-2
AU - Bengamra S.
AU - Mzoughi O.
AU - Bigand A.
AU - Zagrouba E.
PY - 2023
SP - 832
EP - 841
DO - 10.5220/0011670300003411