DMAD: Dual Memory Bank for Real-World Anomaly Detection
This work addresses the problem of anomaly detection in industrial settings, where access to annotated anomalies is limited, offering a practical solution for multi-class scenarios.
The paper tackles real-world industrial anomaly detection by proposing DMAD, a unified framework that leverages both normal and few annotated anomalies to enhance representation learning, achieving state-of-the-art results on MVTec-AD and VisA datasets.
Training a unified model is considered to be more suitable for practical industrial anomaly detection scenarios due to its generalization ability and storage efficiency. However, this multi-class setting, which exclusively uses normal data, overlooks the few but important accessible annotated anomalies in the real world. To address the challenge of real-world anomaly detection, we propose a new framework named Dual Memory bank enhanced representation learning for Anomaly Detection (DMAD). This framework handles both unsupervised and semi-supervised scenarios in a unified (multi-class) setting. DMAD employs a dual memory bank to calculate feature distance and feature attention between normal and abnormal patterns, thereby encapsulating knowledge about normal and abnormal instances. This knowledge is then used to construct an enhanced representation for anomaly score learning. We evaluated DMAD on the MVTec-AD and VisA datasets. The results show that DMAD surpasses current state-of-the-art methods, highlighting DMAD's capability in handling the complexities of real-world anomaly detection scenarios.