Multi-view Subspace Clustering

By Hongchang Gao, Feiping Nie, Xuelong Li, Heng Huang. IEEE International Conference on Computer Vision, 2015

543 citations recorded by the source corpus.

For many computer vision applications, the data sets distribute on certain low-dimensional subspaces. Subspace clustering is to find such underlying subspaces and cluster the data points correctly. In this paper, we propose a novel multi-view subspace clustering method. The proposed method performs clustering on the subspace representation of each view simultaneously. Meanwhile, we propose to use a common cluster structure to guarantee the consistence among different views. In addition, an efficient algorithm is proposed to solve the problem. Experiments on four benchmark data sets have been performed to validate our proposed method. The promising results demonstrate the effectiveness of our method.

Subfields: Atmospheric Science, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/2b2639ef3220e13dee1a9b477572711a3f2d06e6

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Atmospheric Science

1. Dacheng Tao

In Computer Vision and Pattern Recognition

1. Dacheng Tao
2. Yun Raymond Fu
3. Luc Van Gool
4. Lei Zhang
5. Ming-Hsuan Yang
6. Yi Yang
7. Ling Shao
8. Xiaogang Wang

Citations in the corpus

• Deep Clustering via Joint Convolutional Autoencoder Embedding and Relative Entropy Minimization (2017, background): “There is a large number of clustering algorithms in literature, which can be grouped into different perspectives, such as hierarchical [9, 51], centroid-based [20, 3, 27], graphbased [38, 28, 48, 25], sequential (temporal) [11, 37, 66], regression model based [7, 47], and subspace clustering models ”
• Multi-Task Multi-View Clustering (2016, methodology): “The multi-view subspace clustering method in [47] performs clustering on the subspace representation of each view simultaneously and uses a common cluster structure to guarantee the consistence among different views.”
• Fast Parameter-Free Multi-View Subspace Clustering With Consensus Anchor Guidance (2021, background): “[30] think it is unreasonable to align multi-view graphs into a unified one directly since the magnitude of Si is different.”
• Multiview Spectral Clustering via Structured Low-Rank Matrix Factorization (2017, background): “…the complementary information from multi-views, the critical issue of multi-view clustering is to achieve the multi-view clustering agreement/consensus [ Xu et al. , 2013; Gui et al. , 2014; Gao et al. , 2015 ] to yield a substantial superior clustering performance over the single view paradigm.”
• On Unifying Multi-view Self-Representations for Clustering by Tensor Multi-rank Minimization (2016, methodology): “Besides CCA, the recent proposed subspace clustering methods [22], [54] resorted to explore the relationship between samples with self-representation ( e.”
• Large-scale Multi-view Subspace Clustering in Linear Time (2019, methodology): “Basically, for multi-view data (Gao et al. 2015; Cao et al. 2015; Kang et al. 2019c) (2) With different forms of f , Eq.”
• Scalable Multi-view Subspace Clustering with Unified Anchors (2021, methodology): “Multi-view Subspace Clustering (MVSC) [8] proposes an efficient multi-view subspace clustering method and verifies its effectiveness.”
• Incomplete Multiview Spectral Clustering With Adaptive Graph Learning (2020, background): “differences in magnitude, structures, and dimensions owing to the diversity of missing views, it is impossible to directly learn a unified graph or representation for all views [30].”
• Multi-View Clustering via Deep Matrix Factorization (2017, methodology): “proposed to perform clustering on the subspace representation of each view simultaneously guided by a common cluster structure for the consistence across different views (Gao et al. 2015).”
• Pattern Recognition (2018, unknown): “Cross-view means probe and gallery are in different viewpoints.”
• A Survey on Multi-View Clustering (2017, unknown): “[80] merged these two steps in subspace clustering and enforced a common indicator matrix across different views.”
• Structured Graph Learning for Scalable Subspace Clustering: From Single View to Multiview (2021, unknown): “[51] learned multiple graphs and let them correspond to a unique cluster”
• Latent Multi-view Subspace Clustering (2017, methodology): “Therefore, the multi-view subspace clustering methods have been proposed [3, 31, 9], in which each data point is described with information from multiple sources of features.”
• GMC: Graph-Based Multi-View Clustering (2020, methodology): “The other related multi-view clustering methods can be roughly classified into three categories: co-training style clustering [19], [26], [27], [28], multi-kernel clustering [29], [30], [31], [32], and multi-view subspace clustering [33], [34], [35], [36], [37], [38], [39], [40], [41], [42], [43].”
• Generalized Latent Multi-View Subspace Clustering (2020, methodology): “The second group are the self-representation-based methods [15], [16], [17].”