AMI-Net: Adaptive Mask Inpainting Network for Industrial Anomaly Detection and Localization

Unsupervised visual anomaly detection is crucial for enhancing industrial production quality and efficiency. Among unsupervised methods, reconstruction approaches are popular due to their simplicity and effectiveness. The key aspect of reconstruction methods lies in the restoration of anomalous regions, which current methods have not satisfactorily achieved. To tackle this issue, we introduce a novel Adaptive Mask Inpainting Network (AMI-Net) from the perspective of adaptive mask-inpainting. In contrast to traditional reconstruction methods that treat non-semantic image pixels as targets, our method uses a pre-trained network to extract multi-scale semantic features as reconstruction targets. Given the multiscale nature of industrial defects, we incorporate a training strategy involving random positional and quantitative masking. Moreover, we propose an innovative adaptive mask generator capable of generating adaptive masks that effectively mask anomalous regions while preserving normal regions. In this manner, the model can leverage the visible normal global contextual information to restore the masked anomalous regions, thereby effectively suppressing the reconstruction of defects. Extensive experimental results on the MVTec AD and BTAD industrial datasets validate the effectiveness of the proposed method. Additionally, AMI-Net exhibits exceptional real-time performance, striking a favorable balance between detection accuracy and speed, rendering it highly suitable for industrial applications. Note to Practitioners —AMI-Net restores defective images to normal ones and subsequently detects defects by leveraging the differences between them. This method only needs to collect about a few hundred defect-free samples for training, without the need for additional defect samples. It is noteworthy that AMI-Net is applicable not only to the detection of simple texture surface defects, such as carpet, leather, and tile, but also to the detection of surface defects in objects with posture diversity, such as cable, transistor, and screw. The trained model not only exhibits high detection accuracy but also demonstrates superior real-time performance, showcasing significant potential in practical industrial settings.