Moving Fuzzy Windows with Gaussian Processed Labels for Ordinal Regression

Paper

A novel ordinal regression algorithm, called moving fuzzy window with gaussian processed labels (MFW-GL), is proposed in this paper.

The full paper can be found via the link above.

Datasets

Dependencies

Python 3
Pytorch
Matlab 2020

Preprocessing

We use and borrow the codes for face detection and face alignment from SSR-Net which is provided by Tsun-Yi Yang for face alignment.

Pretrained Models and Reference Lists

You can download pretrained models and reference lists here.

Test

Use the following command for evaluation.

Reference

Note: If you use this repository in your research, we kindly request you to cite following papers:

Kang, C., Yu, X., Wang, S. H., Guttery, D., Pandey, H., Tian, Y., & Zhang, Y. (2020). A heuristic neural network structure relying on fuzzy logic for images scoring. IEEE Transactions on Fuzzy Systems.

Bibtex:

@article{kang2020heuristic,
  title={A heuristic neural network structure relying on fuzzy logic for images scoring},
  author={Kang, Cheng and Yu, Xiang and Wang, Shui-Hua and Guttery, David S and Pandey, Hari Mohan and Tian, Yingli and Zhang, Yu-Dong},
  journal={IEEE transactions on fuzzy systems},
  volume={29},
  number={1},
  pages={34--45},
  year={2020},
  publisher={IEEE}
}

ChengKang520/FW-with-GPL-for-Ordinal-Regression