This repository is the official implementation of "Diffusion Adversarial Representation Learning for Self-supervised Vessel Segmentation".

[ICLR 2023] [arXiv]

• OS : Ubuntu
• Python >= 3.6
• PyTorch >= 1.4.0

In our experiments, we used the publicly available XCAD dataset. Please refer to our main paper.

To train our model, run this command:

python3 main.py -p train -c config/train.json

To test the trained our model, run:

python3 main.py -p test -c config/test.json

You can download our pretrained model of XCAD dataset here. Then, you can test the model by saving the pretrained weights in the directory ./pretrained_model. To brifely test our method given the pretrained model, we provided the toy example in the directory './data/'.

@inproceedings{
kim2023diffusion,
title={Diffusion Adversarial Representation Learning for Self-supervised Vessel Segmentation},
author={Boah Kim and Yujin Oh and Jong Chul Ye},
booktitle={The Eleventh International Conference on Learning Representations },
year={2023},
url={https://openreview.net/forum?id=H0gdPxSwkPb}
}