用自回归建模实现轻量高分辨率图像异常检测
VarAD: Lightweight High-Resolution Image Anomaly Detection via Visual Autoregressive Modeling
- 将图像异常检测转为视觉标记预测任务，利用Mamba模型建模序列依赖
- 在四个公开数据集和真实工业数据上均达领先性能，参数量更少
- 适合需要低资源部署的工业质检场景，尤其适用于高清图像
本文针对高分辨率图像异常检测（HRIAD）这一实际问题展开研究。相比传统低分辨率图像异常检测，HRIAD带来更大计算负担并要求更强的全局信息捕获能力。为此，本文将图像异常检测转化为视觉标记预测任务，提出基于视觉自回归建模的VarAD方法。具体而言，VarAD首先提取多层级、多方向的视觉标记序列，并采用先进的Mamba模型进行视觉自回归建模与标记预测。在预测过程中，有效利用所有前序标记的信息来预测目标标记。最后，通过比较预测标记与原始标记的差异来评分异常。在四个公开数据集及一个真实世界按钮检测数据集上的综合实验表明，所提VarAD在保持轻量化的同时，实现了优异的高分辨率图像异常检测性能，验证了其在实际应用中的可行性。代码已开源。
原文摘要 · Abstract (English)
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 \href{https://github.com/caoyunkang/VarAD}{\url{https://github.com/caoyunkang/VarAD}}.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。