Enclosing Prototypical Variational Autoencoder for Explainable Out-of-Distribution Detection

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Orglmeister, Conrad, Bochinski, Erik, Eiselein, Volker, Fleig, Elvira
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866918061558202368
author Orglmeister, Conrad
Bochinski, Erik
Eiselein, Volker
Fleig, Elvira
author_facet Orglmeister, Conrad
Bochinski, Erik
Eiselein, Volker
Fleig, Elvira
contents Understanding the decision-making and trusting the reliability of Deep Machine Learning Models is crucial for adopting such methods to safety-relevant applications. We extend self-explainable Prototypical Variational models with autoencoder-based out-of-distribution (OOD) detection: A Variational Autoencoder is applied to learn a meaningful latent space which can be used for distance-based classification, likelihood estimation for OOD detection, and reconstruction. The In-Distribution (ID) region is defined by a Gaussian mixture distribution with learned prototypes representing the center of each mode. Furthermore, a novel restriction loss is introduced that promotes a compact ID region in the latent space without collapsing it into single points. The reconstructive capabilities of the Autoencoder ensure the explainability of the prototypes and the ID region of the classifier, further aiding the discrimination of OOD samples. Extensive evaluations on common OOD detection benchmarks as well as a large-scale dataset from a real-world railway application demonstrate the usefulness of the approach, outperforming previous methods.
format Preprint
id arxiv_https___arxiv_org_abs_2506_14390
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Enclosing Prototypical Variational Autoencoder for Explainable Out-of-Distribution Detection
Orglmeister, Conrad
Bochinski, Erik
Eiselein, Volker
Fleig, Elvira
Machine Learning
Computer Vision and Pattern Recognition
Understanding the decision-making and trusting the reliability of Deep Machine Learning Models is crucial for adopting such methods to safety-relevant applications. We extend self-explainable Prototypical Variational models with autoencoder-based out-of-distribution (OOD) detection: A Variational Autoencoder is applied to learn a meaningful latent space which can be used for distance-based classification, likelihood estimation for OOD detection, and reconstruction. The In-Distribution (ID) region is defined by a Gaussian mixture distribution with learned prototypes representing the center of each mode. Furthermore, a novel restriction loss is introduced that promotes a compact ID region in the latent space without collapsing it into single points. The reconstructive capabilities of the Autoencoder ensure the explainability of the prototypes and the ID region of the classifier, further aiding the discrimination of OOD samples. Extensive evaluations on common OOD detection benchmarks as well as a large-scale dataset from a real-world railway application demonstrate the usefulness of the approach, outperforming previous methods.
title Enclosing Prototypical Variational Autoencoder for Explainable Out-of-Distribution Detection
topic Machine Learning
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2506.14390