Existing K-nearest neighbor (KNN) retrieval-based methods usually conduct industrial anomaly detection in two stages: obtain feature representations with a pre-trained CNN model and perform distance measures for defect detection. However, the features are not fully exploited as they ignore domain bias and the difference of local density in feature space, which limits the detection performance. In this paper, we propose Reducing Biases (REB) in representation by considering the domain bias of the pre-trained model and building a self-supervised learning task for better domain adaption with a defect generation strategy (DefectMaker) imitating the natural defects. Additionally, we propose a local density KNN (LDKNN) to reduce the local density bias and obtain effective anomaly detection. We achieve a promising result of 99.5\% AUROC on the widely used MVTec AD benchmark. We also achieve 88.0\% AUROC on the challenging MVTec LOCO AD dataset and bring an improvement of 4.7\% AUROC to the state-of-the-art result. All results are obtained with smaller backbone networks such as Vgg11 and Resnet18, which indicates the effectiveness and efficiency of REB for practical industrial applications.

翻译：现有基于K近邻（KNN）检索的方法通常分两阶段进行工业异常检测：利用预训练CNN模型提取特征表征，然后进行距离度量以检测缺陷。然而，由于忽略领域偏差和特征空间中局部密度的差异，特征未被充分利用，从而限制了检测性能。本文提出表征偏差减少方法（REB），通过考虑预训练模型的领域偏差并构建自监督学习任务以更好地适应领域，采用模仿自然缺陷的缺陷生成策略（DefectMaker）。此外，我们提出局部密度KNN（LDKNN）以减少局部密度偏差，实现有效的异常检测。在广泛使用的MVTec AD基准上取得了99.5%的AUROC成绩。在具有挑战性的MVTec LOCO AD数据集上也达到88.0%的AUROC，相比当前最优结果提升了4.7%的AUROC。所有结果均基于Vgg11和Resnet18等更小的骨干网络获得，这表明REB在工业实际应用中的有效性和高效性。