Domain-Generalized Textured Surface Anomaly Detection

TL;DR

This paper introduces a patch-based meta-learning approach for domain-generalized textured surface anomaly detection, capable of identifying and localizing anomalies in unseen domains with limited normal data during testing.

Contribution

It proposes a novel meta-learning model that generalizes to unseen textured surface domains and localizes anomalies using only image-level labels during training.

Findings

Outperforms state-of-the-art methods in various settings.

Successfully localizes abnormal regions in unseen domains.

Generalizes well with limited normal data during testing.

Abstract

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.