通过空间一致性正则化提升工业异常检测的精度与鲁棒性
SPACE: SPAtial-aware Consistency rEgularization for anomaly detection in Industrial applications
- 引入空间一致性损失，防止学生模型过度模仿教师模型
- 在MVTec LOCO、MVTec AD等数据集上实现更优检测效果
- 适合需要精准识别结构与逻辑异常的工业场景
本文提出SPACE，一种新型工业异常检测方法，将特征编码器（FE）融入学生-教师框架。核心包含两个组件：空间一致性正则化损失（SCL）和特征转换模块（FM）。SCL通过避免对教师模型的过度模仿，防止学生模型过拟合，同时引导正常数据特征扩展，避开数据增强产生的异常区域，从而在正常与异常数据间建立稳健边界。FM则阻止编码器学习模糊信息，保护特征表示，提升对结构性和逻辑性异常的检测能力。该方法有效降低特征编码器的影响，兼容多种数据增强策略。在MVTec LOCO、MVTec AD和VisA数据集上的实验表明，该方法在定性评估中优于现有先进方法，各模块表现高效且具有优势。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。