AdaptCLIP

Universal Visual Anomaly Detection model based on CLIP with learnable adapters.

Model Description

AdaptCLIP is a universal (zero-shot and few-shot) anomaly detection framework that leverages CLIP's vision-language capabilities with lightweight learnable adapters for open-word industrial and medical anomaly detection.

Model Variants

Checkpoint	Training Dataset	Description
adaptclip_checkpoints/12_4_128_train_on_mvtec_3adapters_batch8/epoch_15.pth	MVTec-AD	Trained on MVTec-AD dataset
adaptclip_checkpoints/12_4_128_train_on_visa_3adapters_batch8/epoch_15.pth	VisA	Trained on VisA dataset

Usage

# Load checkpoint
import torch
checkpoint = torch.load("./adaptclip_checkpoints/12_4_128_train_on_mvtec_3adapters_batch8/epoch_15.pth")

Citation

If you find this model useful, please cite our work.

@inproceedings{adaptclip,
  title={AdaptCLIP: Adapting CLIP for Universal Visual Anomaly Detection},
  author={Gao, Bin-Bin and Zhou, Yue and Yan, Jiangtao and Cai, Yuezhi and Zhang, Weixi and Wang, Meng and Liu, Jun and Liu, Yong and Wang, Lei and Wang, Chengjie},
  booktitle={AAAI}
  year={2026}
}

License

gpl-2.0