Domain-Generalized Textured Surface Anomaly Detection
This addresses the problem of anomaly detection in unseen domains for industrial inspection applications, representing a novel combination of domain generalization and anomaly detection.
The paper tackles domain-generalized textured surface anomaly detection, enabling models trained on multiple source domains to detect anomalies in unseen textured surfaces with only a small number of normal test images. The patch-based meta-learning model achieves favorable performance against state-of-the-art methods in various settings.
Anomaly detection aims to identify abnormal data that deviates from the normal ones, while typically requiring a sufficient amount of normal data to train the model for performing this task. Despite the success of recent anomaly detection methods, performing anomaly detection in an unseen domain remain a challenging task. In this paper, we address the task of domain-generalized textured surface anomaly detection. By observing normal and abnormal surface data across multiple source domains, our model is expected to be generalized to an unseen textured surface of interest, in which only a small number of normal data can be observed during testing. Although with only image-level labels observed in the training data, our patch-based meta-learning model exhibits promising generalization ability: not only can it generalize to unseen image domains, but it can also localize abnormal regions in the query image. Our experiments verify that our model performs favorably against state-of-the-art anomaly detection and domain generalization approaches in various settings.