Beyond the Known: Adversarial Autoencoders in Novelty Detection

Muhammad Asad, Muhammad Asad, Ihsan Ullah, Ihsan Ullah, Ganesh Sistu, Michael Madden, Michael Madden

2024

Abstract

In novelty detection, the goal is to decide if a new data point should be categorized as an inlier or an outlier, given a training dataset that primarily captures the inlier distribution. Recent approaches typically use deep encoder and decoder network frameworks to derive a reconstruction error, and employ this error either to determine a novelty score, or as the basis for a one-class classifier. In this research, we use a similar framework but with a lightweight deep network, and we adopt a probabilistic score with reconstruction error. Our methodology calculates the probability of whether the sample comes from the inlier distribution or not. This work makes two key contributions. The first is that we compute the novelty probability by linearizing the manifold that holds the structure of the inlier distribution. This allows us to interpret how the probability is distributed and can be determined in relation to the local coordinates of the manifold tangent space. The second contribution is that we improve the training protocol for the network. Our results indicate that our approach is effective at learning the target class, and it outperforms recent state-of-the-art methods on several benchmark datasets.

Paper Citation

in Harvard Style

Asad M., Ullah I., Sistu G. and Madden M. (2024). Beyond the Known: Adversarial Autoencoders in Novelty Detection. In Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP; ISBN 978-989-758-679-8, SciTePress, pages 256-265. DOI: 10.5220/0012459600003660

in Bibtex Style

@conference{visapp24,
author={Muhammad Asad and Ihsan Ullah and Ganesh Sistu and Michael Madden},
title={Beyond the Known: Adversarial Autoencoders in Novelty Detection},
booktitle={Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP},
year={2024},
pages={256-265},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012459600003660},
isbn={978-989-758-679-8},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP
TI - Beyond the Known: Adversarial Autoencoders in Novelty Detection
SN - 978-989-758-679-8
AU - Asad M.
AU - Ullah I.
AU - Sistu G.
AU - Madden M.
PY - 2024
SP - 256
EP - 265
DO - 10.5220/0012459600003660
PB - SciTePress