paper

Unsupervised Anomaly Detection and Localization with Generative Adversarial Networks

arXiv:2409.03657

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.

ECOC 2024

Unsupervised Anomaly Detection and Localization with Generative Adversarial Networks · wovepaper