Implementation for the MICCAI 2023 paper "Medical Phrase Grounding with Region-Phrase Context Contrastive Alignment"[ArXiv link].
As shown in requirements.txt
- Download our released checkpoint to folder
released_checkpoint
- Modify line 144,145,146 in
demo.py
to config the input (we put some images in the folderdata_demo
) - Run
demo.py
and the output image will be saved indemo_cases
- Download the pretrained baseline model to folder
pretrained
(include DETR pretrained model and TransVG pretrained model) - Download the MS_CXR dataset to folder
ln_data
- Run the script
script_ours_MS_CXR.sh
to train, val and test our model, models will be saved in foldercheckpoint
@inproceedings{chen23MedRPG,
author = {Chen, Zhihao and Zhou, Yang and Tran, Anh and Zhao, Junting and Wan, Liang and Ooi, G.S.K. and Cheng, L.T.-E. and Thng, C.H. and Xu, Xinxing and Liu, Yong and Fu, Huazhu},
title = {Medical Phrase Grounding with Region-Phrase Context Contrastive Alignment},
booktitle = {MICCAI},
year = {2023}
}