Contamination Map Methodology

Vision / Dataset

MVTec AD

Industrial anomaly detection dataset of 5354 high-resolution color images in 15 categories (5 textures: carpet, grid, leather, tile, wood; 10 objects: bottle, cable, capsule, hazelnut, metal nut, pill, screw, toothbrush, transistor, zipper). 3629 defect-free images for training and validation; 1725 test images (467 defect-free, 1258 defective) covering 73 defect types, with pixel-precise ground-truth regions for all anomalies (1888 regions).

Also known as
MVTec Anomaly Detection, MVTec Anomaly Detection dataset, MVTec-AD, MAD
Domain
manufacturing inspection
License
CC BY-NC-SA 4.0
Test items from
2019-06-01
Evidence
“Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019, pp. 9592-9600”
openaccess.thecvf.com · paper · header · retrieved 2026-10-15
“month = {June}, year = {2019}”
openaccess.thecvf.com · paper · bibtex · retrieved 2026-10-15
Homepage
www.mvtec.com

Exposure by model

BenchmarkModelLevelReason
Industrial anomaly detection AA-CLIP, trained on MVTec AD (for VisA results) Seen, split unclear in fine-tuning data: the dataset was used; the source does not say which part
Industrial anomaly detection AA-CLIP, trained on VisA Unknown unknown for its base model OpenAI CLIP: training data not disclosed in enough detail
Industrial anomaly detection AdaCLIP, trained on all 14 datasets (demo model) Test data seen in fine-tuning data: its test split was used for training
Industrial anomaly detection AdaCLIP, trained on MVTec AD + ColonDB Test data seen in fine-tuning data: its test split was used for training
Industrial anomaly detection AdaCLIP, trained on VisA + ClinicDB Unknown unknown for its base model OpenAI CLIP: training data not disclosed in enough detail
Industrial anomaly detection AdaptCLIP, trained on MVTec AD Test data seen in fine-tuning data: its test split was used for training
Industrial anomaly detection AdaptCLIP, trained on VisA Unknown unknown for its base model OpenAI CLIP: training data not disclosed in enough detail
Industrial anomaly detection Anomaly-OneVision (Anomaly-OV) Seen, split unclear in fine-tuning data: the dataset was used; the source does not say which part
Industrial anomaly detection AnomalyCLIP, trained on MVTec AD Test data seen in fine-tuning data: its test split was used for training
Industrial anomaly detection AnomalyCLIP, trained on VisA Unknown unknown for its base model OpenAI CLIP: training data not disclosed in enough detail
Industrial anomaly detection AnomalyDINO Unknown unknown for its base model DINOv2: training data not disclosed in enough detail
Industrial anomaly detection AnomalyGPT, unsupervised on MVTec AD Training data seen in fine-tuning data: only the training split was used, not the benchmark's test data
Industrial anomaly detection AnomalyGPT, supervised (demo model) Seen, split unclear in fine-tuning data: the dataset was used; the source does not say which part
Industrial anomaly detection AnomalyGPT, unsupervised on VisA Unknown training data not disclosed in enough detail
Industrial anomaly detection APRIL-GAN (VAND 2023), trained on MVTec AD Test data seen in fine-tuning data: its test split was used for training
Industrial anomaly detection APRIL-GAN (VAND 2023), trained on VisA Unknown unknown for its base model OpenAI CLIP: training data not disclosed in enough detail
Industrial anomaly detection OpenAI CLIP Unknown training data not disclosed in enough detail
Industrial anomaly detection DINOv2 Unknown training data not disclosed in enough detail
Industrial anomaly detection DINOv3 (web / LVD-1689M models) Unknown training data not disclosed in enough detail
Industrial anomaly detection FiLo, trained on MVTec AD Test data seen in fine-tuning data: its test split was used for training
Industrial anomaly detection FiLo, trained on VisA Unknown unknown for its base model OpenAI CLIP: training data not disclosed in enough detail
Industrial anomaly detection WideResNet-50-2 (supervised ImageNet-1k, torchvision) Not seen absent from the complete list of training data
Industrial anomaly detection InCTRL, trained on MVTec AD Test data seen in fine-tuning data: the whole dataset was used
Industrial anomaly detection InCTRL, trained on VisA Unknown unknown for its base model OpenCLIP (LAION-400M checkpoints): training data not disclosed in enough detail
Industrial anomaly detection MetaUAS Unknown training data not disclosed in enough detail
Industrial anomaly detection MuSc Unknown unknown for its base model OpenAI CLIP: training data not disclosed in enough detail
Industrial anomaly detection OpenCLIP (LAION-2B checkpoints) Unknown training data not disclosed in enough detail
Industrial anomaly detection OpenCLIP (LAION-400M checkpoints) Unknown training data not disclosed in enough detail
Industrial anomaly detection Segment Any Anomaly (SAA / SAA+) Unknown unknown for its base model Segment Anything Model (SAM): training data not disclosed in enough detail
Industrial anomaly detection SAM 2 / SAM 2.1 Unknown training data not disclosed in enough detail
Industrial anomaly detection Segment Anything Model (SAM) Unknown training data not disclosed in enough detail
Industrial anomaly detection SigLIP 2 Unknown training data not disclosed in enough detail
Industrial anomaly detection SigLIP Unknown training data not disclosed in enough detail
Industrial anomaly detection UniVAD Unknown unknown for its base model OpenAI CLIP: training data not disclosed in enough detail
Industrial anomaly detection VCP-CLIP, trained on MVTec-AD Test data seen in fine-tuning data: its test split was used for training
Industrial anomaly detection VCP-CLIP, trained on VisA Unknown unknown for its base model OpenAI CLIP: training data not disclosed in enough detail
Industrial anomaly detection WinCLIP / WinCLIP+ Unknown unknown for its base model OpenCLIP (LAION-400M checkpoints): training data not disclosed in enough detail

Notes

published_from = first day of the month of the CVPR 2019 proceedings (bibtex month June 2019); neither the paper nor the official page gives an exact release date, and the dataset may have been downloadable somewhat earlier. Extended journal version published in IJCV on 06 January 2021. Download on the official page requires filling in a form.

Sources