VarAD: Lightweight High-Resolution Image Anomaly Detection via Visual Autoregressive Modeling
- 16 January 2025
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 21 (4) , 3246-3255
Abstract
This article addresses a practical task: high-resolution image anomaly detection (HRIAD). In comparison to conventional image anomaly detection for low-resolution images, HRIAD imposes a heavier computational burden and necessitates superior global information capture capacity. To tackle HRIAD, this article translates image anomaly detection into visual token prediction and proposes visual autoregressive modeling-based anomaly detection (VarAD) based on visual autoregressive modeling for token prediction. Specifically, VarAD first extracts multihierarchy and multidirectional visual token sequences, and then employs an advanced model, Mamba, for visual autoregressive modeling and token prediction. During the prediction process, VarAD effectively exploits information from all preceding tokens to predict the target token. Finally, the discrepancies between predicted tokens and original tokens are utilized to score anomalies. Comprehensive experiments on four publicly available datasets and a real-world button inspection dataset demonstrate that the proposed VarAD achieves superior HRIAD performance while maintaining lightweight, rendering VarAD a viable solution for HRIAD.Keywords
All Related Versions
Funding Information
- Ministry of Industry and Information Technology of the People's Republic of China (#2023ZY01089)
- HPC Platform of Huazhong University of Science and Technology
This publication has 30 references indexed in Scilit:
- A Unified Anomaly Synthesis Strategy with Gradient Ascent for Industrial Anomaly Detection and Localization2024
- PyramidFlow: High-Resolution Defect Contrastive Localization Using Pyramid Normalizing Flow2023
- SimpleNet: A Simple Network for Image Anomaly Detection and Localization2023
- SPot-the-Difference Self-supervised Pre-training for Anomaly Detection and Segmentation2022
- Towards Total Recall in Industrial Anomaly Detection2022
- Masked Autoencoders Are Scalable Vision Learners2022
- Anomaly Detection via Reverse Distillation from One-Class Embedding2022
- Inpainting Transformer for Anomaly Detection2022
- Taming Transformers for High-Resolution Image Synthesis2021
- The MVTec Anomaly Detection Dataset: A Comprehensive Real-World Dataset for Unsupervised Anomaly DetectionInternational Journal of Computer Vision, 2021