Sub-Image Anomaly Detection with Deep Pyramid Correspondences

Code

• github.com/byungjae89/SPADE-pytorch
  pytorch★ 251
• github.com/rvorias/ind_knn_ad
  pytorch★ 165
• github.com/Burf/tfdetection
  tf★ 56
• github.com/any-tech/SPADE-fast
  pytorch★ 22
• github.com/areylng/SPADE-MVTEC-LOCO-AD-dataset
  pytorch★ 6

Abstract

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.

Tasks

Benchmark Results

Reproductions