Self-Navigated Residual Mamba for Universal Industrial Anomaly Detection

TL;DR

SNARM introduces a self-referential, iterative anomaly detection framework that dynamically refines detection within test images, achieving state-of-the-art results across multiple industrial benchmarks.

Contribution

The paper presents SNARM, a novel anomaly detection method that uses self-generated references and a dynamic multi-head module for improved accuracy.

Findings

Achieves SOTA performance on MVTec AD, MVTec 3D, and VisA datasets.

Significant improvements in Image-AUROC, Pixel-AURC, PRO, and AP metrics.

Demonstrates effective self-referential learning within test images.

Abstract

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.