Anomaly detection with partitioning overfitting autoencoder ensembles

Boris Lorbeer; Max Botler

doi:10.1117/12.2622453

4 March 2022 Anomaly detection with partitioning overfitting autoencoder ensembles

Boris Lorbeer, Max Botler

Proceedings Volume 12084, Fourteenth International Conference on Machine Vision (ICMV 2021); 1208404 (2022) https://doi.org/10.1117/12.2622453
Event: Fourteenth International Conference on Machine Vision (ICMV 2021), 2021, Rome, Italy

Abstract

In this paper, we propose POTATOES (Partitioning OverfiTting AuTOencoder EnSemble), a new method for unsupervised outlier detection (UOD). More precisely, given any autoencoder for UOD, this technique can be used to improve its accuracy while at the same time removing the burden of tuning its regularization. The idea is to not regularize at all, but to rather randomly partition the data into sufficiently many equally sized parts, overfit each part with its own autoencoder, and to use the maximum over all autoencoder reconstruction errors as the anomaly score. We apply our model to various realistic datasets and show that if the set of inliers is dense enough, our method indeed improves the UOD performance of a given autoencoder significantly. For reproducibility, the code is made available on github so the reader can recreate the results in this paper as well as apply the method to other autoencoders and datasets.

Citation Download Citation

Boris Lorbeer and Max Botler "Anomaly detection with partitioning overfitting autoencoder ensembles", Proc. SPIE 12084, Fourteenth International Conference on Machine Vision (ICMV 2021), 1208404 (4 March 2022); https://doi.org/10.1117/12.2622453

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available