Data Invariants to Understand Unsupervised Out-of-Distribution Detection

Doorenbos, Lars; Sznitman, Raphael; Márquez-Neila, Pablo (October 2022). Data Invariants to Understand Unsupervised Out-of-Distribution Detection (In Press). In: European conference on computer vision.

Text 4951.pdf - Accepted Version Restricted to registered users only Available under License Publisher holds Copyright. Download (3MB)

Unsupervised out-of-distribution (U-OOD) detection has recently attracted much attention due to its importance in mission-critical systems and broader applicability over its supervised counterpart.
Despite this increased attention, U-OOD methods suffer from important shortcomings.
By performing a large-scale evaluation on different benchmarks and image modalities, we show in this work that most popular state-of-the-art methods are unable to consistently outperform a simple anomaly detector based on pre-trained features and the Mahalanobis distance (MahaAD).
A key reason for the inconsistencies of these methods is the lack of a formal description of U-OOD.
Motivated by a simple thought experiment, we propose a characterization of U-OOD based on the invariants of the training dataset.
We show how this characterization is unknowingly embodied in the top-scoring MahaAD method, thereby explaining its quality. Furthermore, our approach can be used to interpret predictions of U-OOD detectors and provides insights into good practices for evaluating future U-OOD methods.

Interest & Impact

Downloads

1 since deposited on 26 Jul 2022
0 in the past 12 months

Citations

5 Citations in Web of Science ®
6 Citations in Scopus

Search

in Google Scholar™

Services

Actions (login required)

Edit item

Actions (login required)

Edit item