ALMRR: Anomaly Localization Mamba on Industrial Textured Surface with Feature Reconstruction and Refinement

TL;DR

This paper introduces ALMRR, a novel unsupervised anomaly localization method for industrial textured images that combines feature reconstruction, refinement, and artificial anomaly augmentation to improve detection accuracy.

Contribution

The paper proposes ALMRR, a new approach that reconstructs and refines semantic features with anomaly augmentation, outperforming existing reconstruction-based methods.

Findings

Superior performance on MVTec-AD-Textured dataset

Effective anomaly localization with refined semantic features

Outperforms state-of-the-art methods

Abstract

Unsupervised anomaly localization on industrial textured images has achieved remarkable results through reconstruction-based methods, yet existing approaches based on image reconstruction and feature reconstruc-tion each have their own shortcomings. Firstly, image-based methods tend to reconstruct both normal and anomalous regions well, which lead to over-generalization. Feature-based methods contain a large amount of distin-guishable semantic information, however, its feature structure is redundant and lacks anomalous information, which leads to significant reconstruction errors. In this paper, we propose an Anomaly Localization method based on Mamba with Feature Reconstruction and Refinement(ALMRR) which re-constructs semantic features based on Mamba and then refines them through a feature refinement module. To equip the model with prior knowledge of anomalies, we enhance it by adding artificially simulated anomalies to the original images. Unlike image reconstruction or repair, the features of synthesized defects are repaired along with those of normal areas. Finally, the aligned features containing rich semantic information are fed in-to the refinement module to obtain the anomaly map. Extensive experiments have been conducted on the MVTec-AD-Textured dataset and other real-world industrial dataset, which has demonstrated superior performance com-pared to state-of-the-art (SOTA) methods.