MixedTeacher: Knowledge Distillation for Fast Inference Textural Anomaly Detection
Simon Thomine, Simon Thomine, Hichem Snoussi, Mahmoud Soua
2023
Abstract
For a very long time, unsupervised learning for anomaly detection has been at the heart of image processing research and a stepping stone for high performance industrial automation process. With the emergence of CNN, several methods have been proposed such as Autoencoders, GAN, deep feature extraction, etc. In this paper, we propose a new method based on the promising concept of knowledge distillation which consists of training a network (the student) on normal samples while considering the output of a larger pretrained network (the teacher). The main contributions of this paper are twofold: First, a reduced student architecture with optimal layer selection is proposed, then a new Student-Teacher architecture with network bias reduction combining two teachers is proposed in order to jointly enhance the performance of anomaly detection and its localization accuracy. The proposed texture anomaly detector has an outstanding capability to detect defects in any texture and a fast inference time compared to the SOTA methods.
DownloadPaper Citation
in Harvard Style
Thomine S., Snoussi H. and Soua M. (2023). MixedTeacher: Knowledge Distillation for Fast Inference Textural Anomaly Detection. In Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023) - Volume 5: VISAPP; ISBN 978-989-758-634-7, SciTePress, pages 487-494. DOI: 10.5220/0011633100003417
in Bibtex Style
@conference{visapp23,
author={Simon Thomine and Hichem Snoussi and Mahmoud Soua},
title={MixedTeacher: Knowledge Distillation for Fast Inference Textural Anomaly Detection},
booktitle={Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023) - Volume 5: VISAPP},
year={2023},
pages={487-494},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011633100003417},
isbn={978-989-758-634-7},
}
in EndNote Style
TY - CONF
JO - Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023) - Volume 5: VISAPP
TI - MixedTeacher: Knowledge Distillation for Fast Inference Textural Anomaly Detection
SN - 978-989-758-634-7
AU - Thomine S.
AU - Snoussi H.
AU - Soua M.
PY - 2023
SP - 487
EP - 494
DO - 10.5220/0011633100003417
PB - SciTePress