Learning non-linear invariants for unsupervised out-of-distribution detection

Doorenbos, Lars Jelte; Sznitman, Raphael; Márquez Neila, Pablo (6 May 2022). Learning non-linear invariants for unsupervised out-of-distribution detection (Unpublished). In: Bern Data Science Day 2022. University of Bern. 06 May 2022.

Preview

Text (Poster) _BDSD_2022__Non_linear_invariants_poster.pdf - Other Available under License Creative Commons: Attribution (CC-BY). Download (480kB) | Preview

An important hurdle to overcome before machine learning models can be reliably deployed in practice is identifying when samples are different from those seen during training, as the output for unexpected samples are often confidently incorrect, while not being identifiable as such. This problem is known as out-of-distribution (OOD) detection. A popular approach for the unsupervised OOD case is to reject samples with a high Mahalanobis distance with regards to the mean features of the training data. Recent work showed that the Mahalanobis distance can be thought of as finding the training data invariants, and rejecting OOD samples that violate them. A key limitation to this approach is that it is limited to linear relations only. Here, we present a novel method capable of identifying non-linear invariants in the data. These are learned using a reversible neural network, consisting of alternating rotation and coupling layers. Results on a varied number of tasks show it to be the best method overall, and achieving state-of-the-art results on some of the experiments.

Interest & Impact

Downloads

76 since deposited on 30 May 2022
27 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