Contamination Map Methodology

Vision / Model

VCP-CLIP, trained on MVTec-AD

Organisation
Institute of Automation, Chinese Academy of Sciences et al.
Family
VCP-CLIP · version train_mvtec.pth
Released
2024-07-17 (arXiv v1 submission date (https://arxiv.org/abs/2407.12276))
Checkpoints
vcp_weight/train_mvtec.pth
Weights
Open
Links
PaperCode

Training data disclosure: Full list

Level determined for 12% of benchmark cells.

“As for VisA, we assess ZSAS performance after training on MVTec-AD.”
arxiv.org · paper · Appendix C · retrieved 2026-10-15

Built on

Everything these base models may have seen is inherited by VCP-CLIP, trained on MVTec-AD.

Other declared training data

Benchmark cells

Industrial anomaly detection

Test data seen MVTec AD · in fine-tuning data: its test split was used for training

Evidence (2)
“As for VisA, we assess ZSAS performance after training on MVTec-AD.”
arxiv.org · paper · Appendix C · retrieved 2026-10-15
“meta_info = json.load(open(f'{self.root}/meta_{dataset}.json', 'r')) meta_info = meta_info["test"]”
raw.githubusercontent.com · code · utils/dataset.py (MVTecDataset and VisaDataset) · retrieved 2026-10-15

Unknown MVTec AD 2 · unknown for its base model OpenAI CLIP: training data not disclosed in enough detail

Unknown MVTec LOCO AD · unknown for its base model OpenAI CLIP: training data not disclosed in enough detail

Unknown VisA · unknown for its base model OpenAI CLIP: training data not disclosed in enough detail

Unknown Real-IAD · unknown for its base model OpenAI CLIP: training data not disclosed in enough detail

Unknown MPDD · unknown for its base model OpenAI CLIP: training data not disclosed in enough detail

Unknown BTAD · unknown for its base model OpenAI CLIP: training data not disclosed in enough detail

Unknown KolektorSDD2 · unknown for its base model OpenAI CLIP: training data not disclosed in enough detail

Notes

Used only for the VisA results. During training on MVTec-AD the code evaluates on five VisA products each epoch (logging only; checkpoints saved every save_freq epochs).

Sources