Hierarchical Vector Quantized Transformer for Multi-class Unsupervised Anomaly Detection

TL;DR

This paper introduces a hierarchical vector quantized Transformer model for multi-class unsupervised anomaly detection, effectively capturing normal patterns as discrete prototypes to improve detection accuracy and interpretability.

Contribution

It proposes a novel hierarchical vector quantized Transformer framework that uses discrete prototypes and a prototype-oriented optimal transport method for improved multi-class anomaly detection.

Findings

Outperforms state-of-the-art on MVTec-AD and VisA datasets.

Addresses codebook collapse and shortcut issues in anomaly detection.

Provides interpretable anomaly scores with a hierarchical prototype approach.

Abstract

Unsupervised image Anomaly Detection (UAD) aims to learn robust and discriminative representations of normal samples. While separate solutions per class endow expensive computation and limited generalizability, this paper focuses on building a unified framework for multiple classes. Under such a challenging setting, popular reconstruction-based networks with continuous latent representation assumption always suffer from the "identical shortcut" issue, where both normal and abnormal samples can be well recovered and difficult to distinguish. To address this pivotal issue, we propose a hierarchical vector quantized prototype-oriented Transformer under a probabilistic framework. First, instead of learning the continuous representations, we preserve the typical normal patterns as discrete iconic prototypes, and confirm the importance of Vector Quantization in preventing the model from falling into the shortcut. The vector quantized iconic prototype is integrated into the Transformer for reconstruction, such that the abnormal data point is flipped to a normal data point.Second, we investigate an exquisite hierarchical framework to relieve the codebook collapse issue and replenish frail normal patterns. Third, a prototype-oriented optimal transport method is proposed to better regulate the prototypes and hierarchically evaluate the abnormal score. By evaluating on MVTec-AD and VisA datasets, our model surpasses the state-of-the-art alternatives and possesses good interpretability. The code is available at https://github.com/RuiyingLu/HVQ-Trans.