Deep Grassmannian multiview subspace clustering with contrastive learning
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 contra...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
AIMS Press
2024-09-01
|
| Series: | Electronic Research Archive |
| Subjects: | |
| Online Access: | https://www.aimspress.com/article/doi/10.3934/era.2024252 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832590844048179200 |
|---|---|
| author | Rui Wang Haiqiang Li Chen Hu Xiao-Jun Wu Yingfang Bao |
| author_facet | Rui Wang Haiqiang Li Chen Hu Xiao-Jun Wu Yingfang Bao |
| author_sort | Rui Wang |
| collection | DOAJ |
| description | 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. |
| format | Article |
| id | doaj-art-bff120f135e14e39bbce264d9aec06fb |
| institution | Kabale University |
| issn | 2688-1594 |
| language | English |
| publishDate | 2024-09-01 |
| publisher | AIMS Press |
| record_format | Article |
| series | Electronic Research Archive |
| spelling | doaj-art-bff120f135e14e39bbce264d9aec06fb2025-01-23T07:52:42ZengAIMS PressElectronic Research Archive2688-15942024-09-013295424545010.3934/era.2024252Deep Grassmannian multiview subspace clustering with contrastive learningRui Wang0Haiqiang Li1Chen Hu2Xiao-Jun Wu3Yingfang Bao4School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi 214122, ChinaSchool of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi 214122, ChinaSchool of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi 214122, ChinaSchool of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi 214122, ChinaAffiliated Wuxi Fifth Hospital of Jiangnan University, Wuxi 214007, ChinaThis 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.https://www.aimspress.com/article/doi/10.3934/era.2024252multiview clusteringcontrastive learninggrassmannian manifoldneural networkinvariant representation |
| spellingShingle | Rui Wang Haiqiang Li Chen Hu Xiao-Jun Wu Yingfang Bao Deep Grassmannian multiview subspace clustering with contrastive learning Electronic Research Archive multiview clustering contrastive learning grassmannian manifold neural network invariant representation |
| title | Deep Grassmannian multiview subspace clustering with contrastive learning |
| title_full | Deep Grassmannian multiview subspace clustering with contrastive learning |
| title_fullStr | Deep Grassmannian multiview subspace clustering with contrastive learning |
| title_full_unstemmed | Deep Grassmannian multiview subspace clustering with contrastive learning |
| title_short | Deep Grassmannian multiview subspace clustering with contrastive learning |
| title_sort | deep grassmannian multiview subspace clustering with contrastive learning |
| topic | multiview clustering contrastive learning grassmannian manifold neural network invariant representation |
| url | https://www.aimspress.com/article/doi/10.3934/era.2024252 |
| work_keys_str_mv | AT ruiwang deepgrassmannianmultiviewsubspaceclusteringwithcontrastivelearning AT haiqiangli deepgrassmannianmultiviewsubspaceclusteringwithcontrastivelearning AT chenhu deepgrassmannianmultiviewsubspaceclusteringwithcontrastivelearning AT xiaojunwu deepgrassmannianmultiviewsubspaceclusteringwithcontrastivelearning AT yingfangbao deepgrassmannianmultiviewsubspaceclusteringwithcontrastivelearning |