Self-Navigated Residual Mamba for Universal Industrial Anomaly Detection

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Hanxi, Wu, Jingqi, Wu, Lin Yuanbo, Li, Mingliang, Liu, Deyin, Shen, Jialie, Shen, Chunhua
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913982266212352
author Li, Hanxi
Wu, Jingqi
Wu, Lin Yuanbo
Li, Mingliang
Liu, Deyin
Shen, Jialie
Shen, Chunhua
author_facet Li, Hanxi
Wu, Jingqi
Wu, Lin Yuanbo
Li, Mingliang
Liu, Deyin
Shen, Jialie
Shen, Chunhua
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2508_01591
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Self-Navigated Residual Mamba for Universal Industrial Anomaly Detection
Li, Hanxi
Wu, Jingqi
Wu, Lin Yuanbo
Li, Mingliang
Liu, Deyin
Shen, Jialie
Shen, Chunhua
Computer Vision and Pattern Recognition
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.
title Self-Navigated Residual Mamba for Universal Industrial Anomaly Detection
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2508.01591