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.

通过使用统一的模型，提出了一种名为 Dual Memory bank enhanced representation learning for Anomaly Detection (DMAD) 的新框架，该框架处理了无监督和半监督场景，通过双重存储器来计算正常和异常模式之间的特征距离和特征注意力，从而构建了用于异常分数学习的增强表示。通过在 MVTec-AD 和 VisA 数据集上的评估，结果表明 DMAD 超越了当前最先进的方法，突显了 DMAD 在处理复杂的实际异常检测场景中的能力。