用于通用工业异常检测的自导航残差 Mamba
Self-Navigated Residual Mamba for Universal Industrial Anomaly Detection
AI总结：
提出SNARM框架，通过测试图像内的自参考学习动态计算残差间和残差内特征，结合多头的Mamba模块聚焦异常区域，在多个工业异常检测基准上达到SOTA性能。
摘要：
本文提出了自导航残差 Mamba（SNARM），这是一种用于通用工业异常检测的新颖框架，它利用测试图像内的“自参考学习”来增强异常判别能力。与仅依赖来自正常训练数据的预训练特征的传统方法不同，SNARM 通过迭代地将测试图像块与自适应选择的图像内参考进行比较，动态地细化异常检测。具体而言，我们首先通过将测试图像块与训练特征库进行对比来计算“残差间”特征。然后，将表现出小范数残差（表明高正常性）的图像块用作自生成的参考图像块，以计算“残差内”，从而放大判别信号。这些残差间和残差内特征被拼接并输入到一个具有多个头的新颖 Mamba 模块中，这些头由残差属性动态导航以聚焦于异常区域。最后，通过在集成学习范式中聚合自导航 Mamba 的输出来获得 AD 结果。在 MVTec AD、MVTec 3D 和 VisA 基准上的大量实验表明，SNARM 实现了最先进的（SOTA）性能，在所有指标上均有显著提升，包括 Image-AUROC、Pixel-AURC、PRO 和 AP。
英文摘要：
In this paper, we propose Self-Navigated Residual Mamba (SNARM), a novel framework for universal industrial anomaly detection that leverages ``self-referential learning'' within test images to enhance anomaly discrimination. Unlike conventional methods that depend solely on pre-trained features from normal training data, SNARM dynamically refines anomaly detection by iteratively comparing test patches against adaptively selected in-image references. Specifically, we first compute the ``inter-residuals'' features by contrasting test image patches with the training feature bank. Patches exhibiting small-norm residuals (indicating high normality) are then utilized as self-generated reference patches to compute ``intra-residuals'', amplifying discriminative signals. These inter- and intra-residual features are concatenated and fed into a novel Mamba module with multiple heads, which are dynamically navigated by residual properties to focus on anomalous regions. Finally, AD results are obtained by aggregating the outputs of a self-navigated Mamba in an ensemble learning paradigm. Extensive experiments on MVTec AD, MVTec 3D, and VisA benchmarks demonstrate that SNARM achieves state-of-the-art (SOTA) performance, with notable improvements in all metrics, including Image-AUROC, Pixel-AURC, PRO, and AP.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
