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

2021/04/20 by Pankaj Mishra, Riccardo Verk, Daniele Fornasier +2 · 3 citations
Computer Science · #cs.CV #cs.AI #cs.LG

paper · pdf · doi:10.1109/isie45552.2021.9576231

published as IEEE 30th International Symposium on Industrial Electronics (ISIE), 2021 · 6 Pages, 4 images, conference published paper

arxiv created 2021/04/20 · arxiv updated 2021/11/03

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.

Cited by

• Zero-Shot Industrial Anomaly Segmentation with Image-Aware Prompt Generation
• MathPhys-Guided Coarse-to-Fine Anomaly Synthesis with SQE-Driven Bi-Level Optimization for Anomaly Detection
• Crane: Context-Guided Prompt Learning and Attention Refinement for Zero-Shot Anomaly Detection