CutPaste: Self-Supervised Learning for Anomaly Detection and Localization

We aim at constructing a high performance model for defect detection that detects unknown anomalous patterns of an image without anomalous data. To this end, we propose a two-stage framework for building anomaly detectors using normal training data only. We first learn self-supervised deep representations and then build a generative one-class classifier on learned representations. We learn representations by classifying normal data from the CutPaste, a simple data augmentation strategy that cuts an image patch and pastes at a random location of a large image. Our empirical study on MVTec anomaly detection dataset demonstrates the proposed algorithm is general to be able to detect various types of real-world defects. We bring the improvement upon previous arts by 3.1 AUCs when learning representations from scratch. By transfer learning on pretrained representations on ImageNet, we achieve a new state-of-theart 96.6 AUC. Lastly, we extend the framework to learn and extract representations from patches to allow localizing defective areas without annotations during training.

PDF Abstract CVPR 2021 PDF CVPR 2021 Abstract

Results from the Paper

Ranked #15 on Anomaly Detection on MVTec AD (using extra training data)

     Get a GitHub badge
Task Dataset Model Metric Name Metric Value Global Rank Uses Extra
Training Data
Result Benchmark
Anomaly Detection MVTec AD CutPaste Detection AUROC 95.2 # 21
Segmentation AUROC 96.0 # 22

Results from Other Papers

Task Dataset Model Metric Name Metric Value Rank Uses Extra
Training Data
Source Paper Compare
Anomaly Detection MVTec AD CutPaste Detection AUROC 97.1 # 15


No methods listed for this paper. Add relevant methods here