Unsupervised Anomaly Detection and Localization with Generative Adversarial Networks

Khouloud Abdelli; Matteo Lonardi; Jurgen Gripp; Samuel Olsson; Fabien Boitier; Patricia Layec

Unsupervised Anomaly Detection and Localization with Generative Adversarial Networks

Machine Learning 2024-09-06 v1 Signal Processing

Authors: Khouloud Abdelli , Matteo Lonardi , Jurgen Gripp , Samuel Olsson , Fabien Boitier , Patricia Layec

Abstract

We propose a novel unsupervised anomaly detection approach using generative adversarial networks and SOP-derived spectrograms. Demonstrating remarkable efficacy, our method achieves over 97% accuracy on SOP datasets from both submarine and terrestrial fiber links, all achieved without the need for labelled data.

Keywords

anomaly detection

Cite

@article{arxiv.2409.03657,
  title  = {Unsupervised Anomaly Detection and Localization with Generative Adversarial Networks},
  author = {Khouloud Abdelli and Matteo Lonardi and Jurgen Gripp and Samuel Olsson and Fabien Boitier and Patricia Layec},
  journal= {arXiv preprint arXiv:2409.03657},
  year   = {2024}
}

Comments

ECOC 2024

Related papers

View all related →

Computer Vision and Pattern Recognition · Computer Science

Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discovery

Thomas Schlegl, Philipp Seeböck, Sebastian M. Waldstein, Ursula Schmidt-Erfurth +1

2017-03-20