MAPL: Memory Augmentation and Pseudo-Labeling for Semi-Supervised Anomaly Detection

TL;DR

MAPL introduces a novel semi-supervised anomaly detection method that combines memory augmentation, pseudo-labeling, and anomaly simulation to improve detection accuracy and robustness in industrial defect detection tasks.

Contribution

The paper proposes a new methodology called MAPL that integrates anomaly simulation, pseudo-labeling with ensemble classifiers, and memory-enhanced learning for improved industrial anomaly detection.

Findings

Achieves an average image-level AUROC of 86.2% on BHAD dataset.

Outperforms previous models with a 5.1% AUROC improvement.

Demonstrates effectiveness across multiple industrial defect datasets.

Abstract

Large unlabeled data and difficult-to-identify anomalies are the urgent issues need to overcome in most industrial scene. In order to address this issue, a new meth-odology for detecting surface defects in in-dustrial settings is introduced, referred to as Memory Augmentation and Pseudo-Labeling(MAPL). The methodology first in-troduces an anomaly simulation strategy, which significantly improves the model's ability to recognize rare or unknown anom-aly types by generating simulated anomaly samples. To cope with the problem of the lack of labeling of anomalous simulated samples, a pseudo-labeler method based on a one-classifier ensemble was employed in this study, which enhances the robustness of the model in the case of limited labeling data by automatically selecting key pseudo-labeling hyperparameters. Meanwhile, a memory-enhanced learning mechanism is introduced to effectively predict abnormal regions by analyzing the difference be-tween the input samples and the normal samples in the memory pool. An end-to-end learning framework is employed by MAPL to identify the abnormal regions directly from the input data, which optimizes the ef-ficiency and real-time performance of de-tection. By conducting extensive trials on the recently developed BHAD dataset (in-cluding MVTec AD [1], Visa [2], and MDPP [3]), MAPL achieves an average im-age-level AUROC score of 86.2%, demon-strating a 5.1% enhancement compared to the original MemSeg [4] model. The source code is available at https://github.com/jzc777/MAPL.