# VarAD: Lightweight High-Resolution Image Anomaly Detection via Visual Autoregressive Modeling

arXiv: https://arxiv.org/abs/2412.17263 · HTML: https://mlsanity.com/paper/2412.17263/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 36 references that are in the map.
- First posted on arXiv 23 Dec 2024.

## Builds on (most cited first, 23 of 23)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [Deep High-Resolution Representation Learning for Visual Recognition](https://mlsanity.com/paper/1908.07919/) (2019)
- [VMamba: Visual State Space Model](https://mlsanity.com/paper/2401.10166/) (2024)
- [Towards Total Recall in Industrial Anomaly Detection](https://mlsanity.com/paper/2106.08265/) (2021)
- [Anomaly Detection via Reverse Distillation from One-Class Embedding](https://mlsanity.com/paper/2201.10703/) (2022)
- [SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and Segmentation](https://mlsanity.com/paper/2207.14315/) (2022)
- [SimpleNet: A Simple Network for Image Anomaly Detection and Localization](https://mlsanity.com/paper/2303.15140/) (2023)
- [VT-ADL: A Vision Transformer Network for Image Anomaly Detection and Localization](https://mlsanity.com/paper/2104.10036/) (2021)
- [Sequential Modeling Enables Scalable Learning for Large Vision Models](https://mlsanity.com/paper/2312.00785/) (2023)
- [EfficientAD: Accurate Visual Anomaly Detection at Millisecond-Level Latencies](https://mlsanity.com/paper/2303.14535/) (2023)
- [Inpainting Transformer for Anomaly Detection](https://mlsanity.com/paper/2104.13897/) (2021)
- [Omni-frequency Channel-selection Representations for Unsupervised Anomaly Detection](https://mlsanity.com/paper/2203.00259/) (2022)
- [IM-IAD: Industrial Image Anomaly Detection Benchmark in Manufacturing](https://mlsanity.com/paper/2301.13359/) (2023)
- [Collaborative Discrepancy Optimization for Reliable Image Anomaly Localization](https://mlsanity.com/paper/2302.08769/) (2023)
- [VISION Datasets: A Benchmark for Vision-based InduStrial InspectiON](https://mlsanity.com/paper/2306.07890/) (2023)
- [Learning Global-Local Correspondence with Semantic Bottleneck for Logical Anomaly Detection](https://mlsanity.com/paper/2303.05768/) (2023)
- [Prior Normality Prompt Transformer for Multi-class Industrial Image Anomaly Detection](https://mlsanity.com/paper/2406.11507/) (2024)
- [AMI-Net: Adaptive Mask Inpainting Network for Industrial Anomaly Detection and Localization](https://mlsanity.com/paper/2412.11802/) (2024)

## Built on by (most cited first, 9 of 9)

- [Exploring Intrinsic Normal Prototypes within a Single Image for Universal Anomaly Detection](https://mlsanity.com/paper/2503.02424/) (2025)
- [Boosting Global-Local Feature Matching via Anomaly Synthesis for Multi-Class Point Cloud Anomaly Detection](https://mlsanity.com/paper/2505.07375/) (2025)
- [Center-aware Residual Anomaly Synthesis for Multi-class Industrial Anomaly Detection](https://mlsanity.com/paper/2505.17551/) (2025)
- [Visual Anomaly Detection under Complex View-Illumination Interplay: A Large-Scale Benchmark](https://mlsanity.com/paper/2505.10996/) (2025)
- [Towards High-Resolution Industrial Image Anomaly Detection](https://mlsanity.com/paper/2508.12931/) (2025)
- [A Comprehensive Survey for Real-World Industrial Defect Detection: Challenges, Approaches, and Prospects](https://mlsanity.com/paper/2507.13378/) (2025)
- [IAD-GPT: Advancing Visual Knowledge in Multimodal Large Language Model for Industrial Anomaly Detection](https://mlsanity.com/paper/2510.16036/) (2025)
- [URA-Net: Uncertainty-Integrated Anomaly Perception and Restoration Attention Network for Unsupervised Anomaly Detection](https://mlsanity.com/paper/2603.22840/) (2026)
- [ProtoAnomalyNCD: Prototype Learning for Multi-class Novel Anomaly Discovery in Industrial Scenarios](https://mlsanity.com/paper/2511.12938/) (2025)

## Abstract (arXiv)

This paper 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 paper translates image anomaly detection into visual token prediction and proposes VarAD based on visual autoregressive modeling for token prediction. Specifically, VarAD first extracts multi-hierarchy and multi-directional 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 high-resolution image anomaly detection performance while maintaining lightweight, rendering VarAD a viable solution for HRIAD. Code is available at hrefhttps://github.com/caoyunkang/VarADurlhttps://github.com/caoyunkang/VarAD.