Handling Drift in Industrial Defect Detection Through MMD-Based Domain Adaptation

Xuban Barberena, Fátima A. Saiz, Iñigo Barandiaran

2025

Abstract

This study enhances industrial quality control by automating defect detection using artificial vision and deep learning techniques. It addresses the challenge of model drift, where variations in input data distribution affect performance. To tackle this, the paper proposes a simpler, practical approach to unsupervised Domain Adaptation (UDA) for object detection, focusing on industrial applicability. A technique based on the Faster R-CNN architecture and a Maximum Mean Discrepancy (MMD) regularization method for feature alignment is proposed. The study aims to detect data drift using state-of-the-art methods and evaluate the proposed UDA technique’s effectiveness in improving surface defect detection. Results show that statistical tests effectively identify variations, enabling timely adaptations. The proposed UDA method achieved mean Average Precision (mAP50) improvements of 3.1% and 6.1% under vibration and noise scenarios, respectively, and a significant 17.8% improvement for conditions with particles, advancing existing methods in the literature.

Paper Citation

in Harvard Style

Barberena X., Saiz F. and Barandiaran I. (2025). Handling Drift in Industrial Defect Detection Through MMD-Based Domain Adaptation. 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 420-429. DOI: 10.5220/0013170900003912

in Bibtex Style

@conference{visapp25,
author={Xuban Barberena and Fátima Saiz and Iñigo Barandiaran},
title={Handling Drift in Industrial Defect Detection Through MMD-Based Domain Adaptation},
booktitle={Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP},
year={2025},
pages={420-429},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013170900003912},
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 - Handling Drift in Industrial Defect Detection Through MMD-Based Domain Adaptation
SN - 978-989-758-728-3
AU - Barberena X.
AU - Saiz F.
AU - Barandiaran I.
PY - 2025
SP - 420
EP - 429
DO - 10.5220/0013170900003912
PB - SciTePress