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.
@article{arxiv.2005.02357,
title = {Sub-Image Anomaly Detection with Deep Pyramid Correspondences},
author = {Niv Cohen and Yedid Hoshen},
journal= {arXiv preprint arXiv:2005.02357},
year = {2021}
}