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

TL;DR

This paper proposes RD-CFA, a novel multi-class anomaly detection method combining discriminative auto-encoders with hypersphere-based feature adaptation, demonstrating superior performance on benchmark datasets.

Contribution

It introduces RD-CFA, integrating a modified RD-VAE with CFA for enhanced multi-class anomaly detection and localization.

Findings

Outperforms eight leading methods on MVTec AD dataset

Effective in multi-class anomaly detection and localization

Captures intricate class distributions with RD-VAE

Abstract

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.