Anomaly Detection via Self-organizing Map
This addresses the challenge of detecting rare anomalies without large annotated datasets, which is crucial for product quality control in manufacturing.
The paper tackled the problem of anomaly detection in industrial manufacturing by proposing an unsupervised approach using Self-organizing Map (SOM), achieving state-of-the-art performance on the MVTec dataset.
Anomaly detection plays a key role in industrial manufacturing for product quality control. Traditional methods for anomaly detection are rule-based with limited generalization ability. Recent methods based on supervised deep learning are more powerful but require large-scale annotated datasets for training. In practice, abnormal products are rare thus it is very difficult to train a deep model in a fully supervised way. In this paper, we propose a novel unsupervised anomaly detection approach based on Self-organizing Map (SOM). Our method, Self-organizing Map for Anomaly Detection (SOMAD) maintains normal characteristics by using topological memory based on multi-scale features. SOMAD achieves state-of the-art performance on unsupervised anomaly detection and localization on the MVTec dataset.