Collaborative Reconstruction and Repair for Multi-class Industrial Anomaly Detection

TL;DR

This paper introduces a unified framework called Collaborative Reconstruction and Repair (CRR) for multi-class industrial anomaly detection, effectively addressing the identity mapping problem and improving localization accuracy.

Contribution

The study proposes a novel CRR framework that transforms reconstruction into repair, incorporating feature masking and supervised segmentation to enhance multi-class anomaly detection.

Findings

CRR achieves state-of-the-art performance on industrial datasets.

It effectively mitigates the identity mapping problem.

The method improves anomaly localization accuracy.

Abstract

Industrial anomaly detection is a challenging open-set task that aims to identify unknown anomalous patterns deviating from normal data distribution. To avoid the significant memory consumption and limited generalizability brought by building separate models per class, we focus on developing a unified framework for multi-class anomaly detection. However, under this challenging setting, conventional reconstruction-based networks often suffer from an identity mapping problem, where they directly replicate input features regardless of whether they are normal or anomalous, resulting in detection failures. To address this issue, this study proposes a novel framework termed Collaborative Reconstruction and Repair (CRR), which transforms the reconstruction to repairation. First, we optimize the decoder to reconstruct normal samples while repairing synthesized anomalies. Consequently, it generates distinct representations for anomalous regions and similar representations for normal areas compared to the encoder's output. Second, we implement feature-level random masking to ensure that the representations from decoder contain sufficient local information. Finally, to minimize detection errors arising from the discrepancies between feature representations from the encoder and decoder, we train a segmentation network supervised by synthetic anomaly masks, thereby enhancing localization performance. Extensive experiments on industrial datasets that CRR effectively mitigates the identity mapping issue and achieves state-of-the-art performance in multi-class industrial anomaly detection.