论文标题
PNI：使用位置和邻里信息的工业异常检测
PNI : Industrial Anomaly Detection using Position and Neighborhood Information
论文作者
论文摘要
由于异常样品不能用于训练，因此许多异常检测和定位方法使用预训练的网络和非参数建模来估计编码特征分布。但是，这些方法忽略了位置和邻里信息对正常特征分布的影响。为了克服这一点，我们提出了一种新的算法，\ textbf {pNi}，该算法使用给定邻域特征的条件概率估算正态分布，并以多层Perceptron网络建模。此外，通过在每个位置创建代表性特征的直方图来利用位置信息。该提出的方法不简单地调整异常图，而是采用了在合成异常图像上训练的额外的精炼网络，以更好地插值并说明输入图像的形状和边缘。我们在MVTEC AD基准数据集上进行了实验，并实现了最先进的性能，分别在异常检测和本地化中分别\ textbf {99.56 \％}和\ textbf {98.98 \％} AUROC分数。
Because anomalous samples cannot be used for training, many anomaly detection and localization methods use pre-trained networks and non-parametric modeling to estimate encoded feature distribution. However, these methods neglect the impact of position and neighborhood information on the distribution of normal features. To overcome this, we propose a new algorithm, \textbf{PNI}, which estimates the normal distribution using conditional probability given neighborhood features, modeled with a multi-layer perceptron network. Moreover, position information is utilized by creating a histogram of representative features at each position. Instead of simply resizing the anomaly map, the proposed method employs an additional refine network trained on synthetic anomaly images to better interpolate and account for the shape and edge of the input image. We conducted experiments on the MVTec AD benchmark dataset and achieved state-of-the-art performance, with \textbf{99.56\%} and \textbf{98.98\%} AUROC scores in anomaly detection and localization, respectively.
