<12.06.2022> We provided our pre-trained models on the LA and ACDC datasets, see './SS-Net/pretrained_pth';

<09.06.2022> We released the codes;

git clone https://github.com/ycwu1997/SS-Net.git

cd SS-Net
# e.g., for 5% labels on LA
python ./code/train_ss_3d.py --labelnum 4 --gpu 0

cd SS-Net
# e.g., for 5% labels on LA
python ./code/test_LA.py --labelnum 4

  @inproceedings{wu2022exploring,
    title={Exploring Smoothness and Class-Separation for Semi-supervised Medical Image Segmentation},
    author={Wu, Yicheng and Wu, Zhonghua and Wu, Qianyi and Ge, Zongyuan and Cai, Jianfei},
    booktitle={International Conference on Medical Image Computing and Computer-Assisted Intervention},
    pages={34--43},
    volume={13435},
    year={2022},    
    doi={10.1007/978-3-031-16443-9\_4},
    organization={Springer, Cham}
    }