SPACE：面向工业应用异常检测的空间感知一致性正则化
SPACE: SPAtial-aware Consistency rEgularization for anomaly detection in Industrial applications
AI总结：
SPACE通过集成特征编码器到学生-教师框架，利用空间一致性正则化损失和特征转换器模块，在工业异常检测中实现稳健边界与高效检测，并在多个数据集上验证了优越性。
摘要：
本文提出SPACE，一种新颖的异常检测方法，它将特征编码器（FE）集成到学生-教师方法的结构中。该方法包含两个关键要素：空间一致性正则化损失（SCL）和特征转换器模块（FM）。SCL通过避免学生模型对教师模型的过度模仿来防止其过拟合，同时，通过避开数据增强生成的异常区域，促进正常数据特征的扩展。这种双重功能确保了正常与异常数据之间的稳健边界。FM防止从FE学习模糊信息，从而保护学习到的特征，并实现对结构性和逻辑性异常更有效的检测。通过这些要素，SPACE能够在整合各种数据增强的同时，最大限度地减少FE的影响。在本研究中，我们在MVTec LOCO、MVTec AD和VisA数据集上评估了所提出的方法。实验结果通过定性评估，展示了与最先进方法相比，每个模块在检测和效率方面的优越性。
英文摘要：
In this paper, we propose SPACE, a novel anomaly detection methodology that integrates a Feature Encoder (FE) into the structure of the Student-Teacher method. The proposed method has two key elements: Spatial Consistency regularization Loss (SCL) and Feature converter Module (FM). SCL prevents overfitting in student models by avoiding excessive imitation of the teacher model. Simultaneously, it facilitates the expansion of normal data features by steering clear of abnormal areas generated through data augmentation. This dual functionality ensures a robust boundary between normal and abnormal data. The FM prevents the learning of ambiguous information from the FE. This protects the learned features and enables more effective detection of structural and logical anomalies. Through these elements, SPACE is available to minimize the influence of the FE while integrating various data augmentations.In this study, we evaluated the proposed method on the MVTec LOCO, MVTec AD, and VisA datasets. Experimental results, through qualitative evaluation, demonstrate the superiority of detection and efficiency of each module compared to state-of-the-art methods.
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。
