Visual Anomaly (VisA) Dataset

The Visual Anomaly (VisA) dataset is a large-scale industrial anomaly detection dataset containing 10,821 high-resolution color images with 9,621 normal and 1,200 anomalous samples.

Data and Resources

Cite this as

Yang Zou, Jongheon Jeong, Latha Pemula, Dongqing Zhang, Onkar Dabeer (2024). Dataset: Visual Anomaly (VisA) Dataset. https://doi.org/10.57702/os78k58d

DOI retrieved: December 2, 2024

Additional Info

Field Value
Created December 2, 2024
Last update December 2, 2024
Author Yang Zou
More Authors
Jongheon Jeong
Latha Pemula
Dongqing Zhang
Onkar Dabeer
Homepage https://github.com/amazon-research/spot-diff