arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2005.02357cs.CVcs.LG
收藏

基于深金字塔对应的子图像异常检测

Sub-Image Anomaly Detection with Deep Pyramid Correspondences

The Hebrew University of Jerusalem(耶路撒冷希伯来大学)

Niv Cohen, Yedid Hoshen

摘要:

利用深度预训练特征的最近邻(kNN)方法在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描述异常位于图像内的位置的分割图。在这项工作中,我们提出了一种新的异常分割方法的基础上对齐的异常图像和一个常数数量的相似的正常图像。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是实现国家的最先进的无监督的异常检测和定位的性能,而几乎不需要训练时间。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑