Collaborative Reconstruction and Repair for Multi-class Industrial Anomaly Detection

2025-12-12

AI Summary

Industrial anomaly detection is an open-set, multi-class anomaly identification task where conventional reconstruction-based methods often suffer from identity mapping, leading to missed detections. To address this, we propose a unified multi-class anomaly detection framework that introduces the novel “reconstruction-to-repair” paradigm: synthetic anomaly repair training explicitly guides the model to focus on anomalous regions; feature-level random masking enhances local discriminative capability; and a segmentation network with pixel-level supervision improves localization accuracy. Built upon an autoencoder architecture, our method enables end-to-end joint optimization of reconstruction, repair, and segmentation. Extensive experiments on multiple industrial benchmark datasets demonstrate that our approach significantly mitigates identity mapping, achieving state-of-the-art performance in both anomaly detection and precise localization.

Technology Category

• Machine Learning: Feature Construction/Reformulation
• Data Mining & Knowledge Management: Anomaly/Outlier Detection
• Computer Vision: Segmentation

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work

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.

Problem

• Unified multi-class anomaly detection framework development
• Mitigating identity mapping in reconstruction-based networks
• Enhancing anomaly localization with collaborative reconstruction and repair

Innovation

• Collaborative Reconstruction and Repair framework
• Feature-level random masking for local information
• Segmentation network with synthetic anomaly masks