Unsupervised anomaly detection and localization is crucial to the practical application when collecting and labeling sufficient anomaly data is infeasible. Most existing representation-based approaches extract normal image features with a deep convolutional neural network and characterize the corresponding distribution through non-parametric distribution estimation methods. The anomaly score is calculated by measuring the distance between the feature of the test image and the estimated distribution. However, current methods can not effectively map image features to a tractable base distribution and ignore the relationship between local and global features which are important to identify anomalies. To this end, we propose FastFlow implemented with 2D normalizing flows and use it as the probability distribution estimator. Our FastFlow can be used as a plug-in module with arbitrary deep feature extractors such as ResNet and vision transformer for unsupervised anomaly detection and localization. In training phase, FastFlow learns to transform the input visual feature into a tractable distribution and obtains the likelihood to recognize anomalies in inference phase. Extensive experimental results on the MVTec AD dataset show that FastFlow surpasses previous state-of-the-art methods in terms of accuracy and inference efficiency with various backbone networks. Our approach achieves 99.4% AUC in anomaly detection with high inference efficiency.
翻译:在收集和标注足够的异常数据时,未经监督的异常点检测和本地化对于实际应用来说至关重要。大多数基于演示的现有方法都以深卷神经网络提取正常图像特征,并且通过非参数分布估计方法对相应的分布进行定性。异常点评分是通过测量测试图像特征与估计分布之间的距离计算的。然而,目前的方法无法有效地将图像特征映射成可移植基分布图,忽视对识别异常点十分重要的地方和全球特征之间的关系。为此,我们提议用2D正常流执行快速Flow,并将其用作概率分布估计器。我们快速法可以使用一个插件模块,使用任意的深度特征提取器,如ResNet和视觉变压器,用于不受监督的异常检测和本地化。在培训阶段,FastFlow学会将输入的视觉特征转换成可移植基本分布,并获得在判断偏差阶段识别异常现象的可能性。MVTec AD数据集的广泛实验结果显示,快速Flow超越了先前的状态分布估计值估计值,并用作99度分布估计值的估测算器。以高精度的方式,在Starferferferferus 中,实现了我们的主节点探测效率。