Home

Awesome

Probabilistic Model Distillation for Semantic Correspondence (CVPR2021)

Authors: Xin Li, Deng-Ping Fan, Fan Yang, Ao Luo, Hong Cheng, Zicheng Liu.

  1. Configuring your environment (Prerequisites): The training and testing experiments are conducted using PyTorch.

    Note that PMDNet is only tested on Ubuntu OS with the following environments. It may work on other operating systems as well but we do not guarantee that it will.

<!--2. Downloading Testing Sets: -->
  1. Downloading Testing Sets:

    • downloading PF-PASCAL and PASCAL-WILLOW dataset (Please use download_dataset.py in "data" directory).
    • downloading SPair-71K Dataset
  2. Testing Configuration:

    • After you download all the trained models Google Drive link or Baidu Pan link with the fetch code: pfk8, move it into './models/', and testing data.
    • Playing 'eval_<dataset_name>.py'. e.g. eval_willow for PASCAL-WILLOW dataset.

  1. If you think this work is helpful, please cite
@inproceedings{zhai2021Mutual,
  title={Probabilistic Model Distillation for Semantic Correspondence},
  author={Li, Xin and Fan, Deng-Ping and Yang, Fan and Luo, Ao and Cheng, Hong and Liu, Zicheng},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages={},
  year={2021}
}