holmes-gu/anomalyclip

AnomalyCLIP: Object-agnostic Prompt Learning for Zero-shot Anomaly Detection

We will release the code once the paper is accepted.

We provide the reproduction of WinCLIP here

Overview of AnomalyCLIP

Analysis of different text prompt templates

Main results

Industrial dataset

Medical dataset

Visualization

BibTex Citation

If you find this paper and repository useful, please cite our paper.

@article{zhou2023anomalyclip,
  title={AnomalyCLIP: Object-agnostic Prompt Learning for Zero-shot Anomaly Detection},
  author={Zhou, Qihang and Pang, Guansong and Tian, Yu and He, Shibo and Chen, Jiming},
  journal={arXiv preprint arXiv:2310.18961},
  year={2023}
}