LogicAL：面向无监督异常定位的逻辑异常合成研究
LogicAL: Towards logical anomaly synthesis for unsupervised anomaly localization
AI总结：
针对现有无监督异常定位的异常合成方法忽略逻辑约束的问题，提出基于边缘操控的LogicAL框架，结合逻辑与结构异常生成策略及边缘重建，在多个数据集上验证了其在两类异常定位上的优势。
摘要：
异常定位是提升工业生产线效率的实用技术。由于异常形式多样且难以采集，现有无监督研究通常配备异常合成方法，但多数方法偏向结构缺陷合成，忽略了底层逻辑约束。为填补这一空白并提升异常定位性能，我们提出一种基于边缘操控的异常合成框架LogicAL，可生成兼具真实感的逻辑异常与结构异常。我们引入了擅长打破逻辑约束的逻辑异常生成策略，以及对结构缺陷合成起补充作用的结构异常生成策略，还通过在网络结构中引入边缘重建进一步提升异常定位性能。在MVTecLOCO、MVTecAD、VisA和MADsim数据集上开展的大量实验，验证了所提LogicAL在逻辑与结构异常定位两方面的优势。
英文摘要：
Anomaly localization is a practical technology for improving industrial production line efficiency. Due to anomalies are manifold and hard to be collected, existing unsupervised researches are usually equipped with anomaly synthesis methods. However, most of them are biased towards structural defects synthesis while ignoring the underlying logical constraints. To fill the gap and boost anomaly localization performance, we propose an edge manipulation based anomaly synthesis framework, named LogicAL, that produces photo-realistic both logical and structural anomalies. We introduce a logical anomaly generation strategy that is adept at breaking logical constraints and a structural anomaly generation strategy that complements to the structural defects synthesis. We further improve the anomaly localization performance by introducing edge reconstruction into the network structure. Extensive experiments on the challenge MVTecLOCO, MVTecAD, VisA and MADsim datasets verify the advantage of proposed LogicAL on both logical and structural anomaly localization.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
