Code for paper: "DICNet: Deep Instance-Level Contrastive Network for Double Incomplete Multi-View Multi-Label Classification" in AAAI-2023
You can run "python final-DICNET_bestresults.py" to train model in semi-supervised case (in the paper 100% data for training) and get the best results!
You can run 'sup_training/main-sup.py' for the supvised case (70% data for training)!
If this code is useful to you, please cite it:
@inproceedings{liu2023dicnet,
title={DICNet: Deep Instance-Level Contrastive Network for Double Incomplete Multi-View Multi-Label Classification},
author={Liu, Chengliang and Wen, Jie and Luo, Xiaoling and Huang, Chao and Wu, Zhihao and Xu, Yong},
booktitle={Proceedings of the AAAI Conference on Artificial Intelligence},
volume={37},
number={7},
pages={8807--8815},
year={2023}
}
Please contact me if you have any questions to run this code! liucl1996@163.com