VT-ADL: A Vision Transformer Network for Image Anomaly Detection and Localization

TL;DR

This paper introduces VT-ADL, a transformer-based model for detecting and localizing image anomalies, leveraging patch embeddings and a Gaussian mixture model, and provides a new industrial anomaly dataset for benchmarking.

Contribution

The paper proposes a novel transformer-based approach combining reconstruction and patch embedding for improved anomaly detection and localization, along with a new real-world industrial dataset.

Findings

Outperforms existing methods on MNIST and MVTec datasets

Effectively localizes anomalies using transformer and Gaussian mixture network

Provides a new dataset for industrial anomaly detection

Abstract

We present a transformer-based image anomaly detection and localization network. Our proposed model is a combination of a reconstruction-based approach and patch embedding. The use of transformer networks helps to preserve the spatial information of the embedded patches, which are later processed by a Gaussian mixture density network to localize the anomalous areas. In addition, we also publish BTAD, a real-world industrial anomaly dataset. Our results are compared with other state-of-the-art algorithms using publicly available datasets like MNIST and MVTec.