Noise-to-Norm Reconstruction for Industrial Anomaly Detection and Localization
This addresses the challenge of handling large variations in object locations for anomaly detection in industrial applications, representing an incremental improvement over existing methods.
The paper tackles the problem of anomaly detection and localization in industrial quality inspection by proposing a noise-to-norm reconstruction method that avoids invariant reconstruction of anomalous regions, achieving state-of-the-art results on the MPDD dataset and competitive performance on VisA.
Anomaly detection has a wide range of applications and is especially important in industrial quality inspection. Currently, many top-performing anomaly-detection models rely on feature-embedding methods. However, these methods do not perform well on datasets with large variations in object locations. Reconstruction-based methods use reconstruction errors to detect anomalies without considering positional differences between samples. In this study, a reconstruction-based method using the noise-to-norm paradigm is proposed, which avoids the invariant reconstruction of anomalous regions. Our reconstruction network is based on M-net and incorporates multiscale fusion and residual attention modules to enable end-to-end anomaly detection and localization. Experiments demonstrate that the method is effective in reconstructing anomalous regions into normal patterns and achieving accurate anomaly detection and localization. On the MPDD and VisA datasets, our proposed method achieved more competitive results than the latest methods, and it set a new state-of-the-art standard on the MPDD dataset.