@article{Wang2024, 
author = {Rui Wang and Haiqiang Li and Chen Hu and Xiao-Jun Wu and Yingfang Bao},
title = {Deep Grassmannian multiview subspace clustering with contrastive learning},
year = {2024},
journal = {Electronic Research Archive},
volume = {32},
number = {9},
pages = {5424-5450},
keywords = {neural network, contrastive learning, Grassmannian manifold, multiview clustering, invariant representation},
url = {https://www.sciopen.com/article/10.3934/era.2024252},
doi = {10.3934/era.2024252},
abstract = {This paper investigated the problem of multiview subspace clustering, focusing on feature learning with submanifold structure and exploring the invariant representations of multiple views. A novel approach was proposed in this study, termed deep Grassmannian multiview subspace clustering with contrastive learning (DGMVCL). The proposed algorithm initially utilized a feature extraction module (FEM) to map the original input samples into a feature subspace. Subsequently, the manifold modeling module (MMM) was employed to map the aforementioned subspace features onto a Grassmannian manifold. Afterward, the designed Grassmannian manifold network was utilized for deep subspace learning. Finally, discriminative cluster assignments were achieved utilizing a contrastive learning mechanism. Extensive experiments conducted on five benchmarking datasets demonstrate the effectiveness of the proposed method. The source code is available at https://github.com/Zoo-LLi/DGMVCL.}
}