search

XLearning-SCU / 2021-CVPR-Completer

PyTorch implementation for COMPLETER: Incomplete Multi-view Clustering via Contrastive Prediction (CVPR 2021)
MIT License
105 stars 34 forks source link

Dear author, it seems that this code can only execute two view data. Do you have a multi view version? #9

Open dugzzuli opened 3 years ago

dugzzuli commented 3 years ago

Dear author, it seems that this code can only execute two view data. Do you have a multi view version?

Lin-Yijie commented 3 years ago

Thanks for your interest in our work! How to conduct contrastive learning and prediction learning for more than two views is a pendent problem due to the combination problem of multi-view data. The simplest solution is directly conducting contrastive learning and prediction learning on every two views and we are still trying to solve this problem in a more effective and efficient way.

lywinaaa commented 1 year ago

Hi，Can you ask about the incomplete data construction process?

Lin-Yijie commented 1 year ago

@lywinaaa The missing data is constructed by get_mask.py and we have released a three view version in 2022-TPAMI-DCP.