<- Back to Datasets

MVTec AD

A Comprehensive Real-World Dataset for Unsupervised Anomaly Detection

MVTec AD

MVTec AD is a dataset for benchmarking anomaly detection methods with a focus on industrial inspection. It contains over 5000 high-resolution images divided into fifteen different object and texture categories. Each category comprises a set of defect-free training images and a test set of images with various kinds of defects as well as images without defects.

MVTec AD
Items
333
Classes
5000
Labels
Models using this dataset
Last updated on 
January 5, 2022
Licensed under 
CC-BY-NC-SA
Star