论文标题
具有深金字塔对应关系的亚图像异常检测
Sub-Image Anomaly Detection with Deep Pyramid Correspondences
论文作者
论文摘要
使用深度训练特征的最近的邻居（KNN）方法将其应用于整个图像时表现出非常强的异常检测性能。 KNN方法的局限性是缺乏分割图，描述了图像内部的异常位置。在这项工作中，我们介绍了一种基于异常图像和恒定数量相似的正常图像之间对齐的新型异常分割方法。我们的方法，语义金字塔异常检测（Spade）使用基于多分辨率特征金字塔的对应关系。 Spade证明可以在无监督的异常检测和本地化上实现最新的性能，同时几乎不需要训练时间。
Nearest neighbor (kNN) methods utilizing deep pre-trained features exhibit very strong anomaly detection performance when applied to entire images. A limitation of kNN methods is the lack of segmentation map describing where the anomaly lies inside the image. In this work we present a novel anomaly segmentation approach based on alignment between an anomalous image and a constant number of the similar normal images. Our method, Semantic Pyramid Anomaly Detection (SPADE) uses correspondences based on a multi-resolution feature pyramid. SPADE is shown to achieve state-of-the-art performance on unsupervised anomaly detection and localization while requiring virtually no training time.
