Multi-Class Anomaly Detection based on Regularized Discriminative Coupled hypersphere-based Feature Adaptation

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Rafiei, Mehdi, Iosifidis, Alexandros
Format: Preprint
Veröffentlicht: 2023
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917580903546880
author Rafiei, Mehdi
Iosifidis, Alexandros
author_facet Rafiei, Mehdi
Iosifidis, Alexandros
contents In anomaly detection, identification of anomalies across diverse product categories is a complex task. This paper introduces a new model by including class discriminative properties obtained by a modified Regularized Discriminative Variational Auto-Encoder (RD-VAE) in the feature extraction process of Coupled-hypersphere-based Feature Adaptation (CFA). By doing so, the proposed Regularized Discriminative Coupled-hypersphere-based Feature Adaptation (RD-CFA), forms a solution for multi-class anomaly detection. By using the discriminative power of RD-VAE to capture intricate class distributions, combined with CFA's robust anomaly detection capability, the proposed method excels in discerning anomalies across various classes. Extensive evaluations on multi-class anomaly detection and localization using the MVTec AD and BeanTech AD datasets showcase the effectiveness of RD-CFA compared to eight leading contemporary methods.
format Preprint
id arxiv_https___arxiv_org_abs_2311_14506
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Multi-Class Anomaly Detection based on Regularized Discriminative Coupled hypersphere-based Feature Adaptation
Rafiei, Mehdi
Iosifidis, Alexandros
Computer Vision and Pattern Recognition
In anomaly detection, identification of anomalies across diverse product categories is a complex task. This paper introduces a new model by including class discriminative properties obtained by a modified Regularized Discriminative Variational Auto-Encoder (RD-VAE) in the feature extraction process of Coupled-hypersphere-based Feature Adaptation (CFA). By doing so, the proposed Regularized Discriminative Coupled-hypersphere-based Feature Adaptation (RD-CFA), forms a solution for multi-class anomaly detection. By using the discriminative power of RD-VAE to capture intricate class distributions, combined with CFA's robust anomaly detection capability, the proposed method excels in discerning anomalies across various classes. Extensive evaluations on multi-class anomaly detection and localization using the MVTec AD and BeanTech AD datasets showcase the effectiveness of RD-CFA compared to eight leading contemporary methods.
title Multi-Class Anomaly Detection based on Regularized Discriminative Coupled hypersphere-based Feature Adaptation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2311.14506