Tensor LRR and Sparse Coding-Based Subspace Clustering.

Subspace clustering groups a set of samples (vectors) into clusters by approximating this set with a mixture of several linear subspaces, so that the samples in the same cluster are drawn from the same linear subspace. In majority of existing works on subspace clustering, samples are simply regarded as being independent and identically distributed, that is, arbitrarily ordering samples when necessary. However, this setting ignores sample correlations in their original spatial structure. To address this issue, we propose a tensor low-rank representation (TLRR) for subspace clustering by keeping available spatial information of data. TLRR seeks a lowest-rank representation over all the candidates while maintaining the inherent spatial structures among samples, and the affinity matrix used for spectral clustering is built from the combination of similarities along all data spatial directions. TLRR better captures the global structures of data and provides a robust subspace segmentation from corrupted data. Experimental results on both synthetic and real-world datasets show that TLRR outperforms several established state-of-the-art methods.

Incomplete multi-view clustering (IMC) has recently received widespread attention in the field of clustering analysis. In spite of the great success, we observe that the current IMC approaches are still faced with three common demerits. First, they mostly fail to recover the inherent (especially nonlinear) subspace structure during incomplete clustering procedure. Second, these approaches tend to design the objective function by some specific matrix norms, yet often overlook the high-level correlation embedded in heterogeneous views. Third, many of them follow a two-stage framework, which inevitably leads to the sub-optimal clustering result due to the lack of the ability of joint optimization. To overcome these demerits, we develop a novel approach termed Unified and Tensorized Incomplete Multi-view Kernel Subspace Clustering (UT-IMKSC) in this paper. Specifically, a kernelized incomplete subspace clustering framework is formulated to exploit the inherent subspace structure from multiple views. In this framework, we aim to impute the incomplete kernels and perform incomplete subspace clustering simultaneously, upon which the low-rank tensor representations as well as their affinity matrix can be seamlessly achieved in a one-step manner. This unified formulation enables our approach to recover the latent relationship among observed and unobserved samples, while capturing the high-level correlation for strengthened subspace clustering. To the best of our knowledge, our approach is the first attempt to formulate incomplete multi-view kernel subspace clustering from unified and tensorized perspectives. Extensive experiments are conducted on various incomplete multi-view datasets, which have demonstrated the superiority of our approach over the state-of-the-art.

Multi-view subspace clustering has been an important and powerful tool for partitioning multi-view data, especially multi-view high-dimensional data. Despite great success, most of the existing multi-view subspace clustering methods still suffer from three limitations. First, they often recover the subspace structure in the original space, which can not guarantee the robustness when handling multi-view data with nonlinear structure. Second, these methods mostly regard subspace clustering and affinity matrix learning as two independent steps, which may not well discover the latent relationships among data samples. Third, many of them ignore the different importance of multiple views, whose performance may be badly affected by the low-quality views in multi-view data. To overcome these three limitations, this paper develops a novel subspace clustering method for multi-view data, termed Kernelized Multi-view Subspace Clustering via Auto-weighted Graph Learning (KMSC-AGL). Specifically, the proposed method implicitly maps the multi-view data from linear space into nonlinear space via kernel-induced functions, so as to exploit the nonlinear structure hidden in data. Furthermore, our method aims to enhance the clustering performance by learning a set of view-specific representations and their affinity matrix in a general framework. By integrating the view weighting strategy into this framework, our method can automatically assign the weights to different views, while learning an optimal affinity matrix that is well-adapted to the subsequent spectral clustering. Extensive experiments are conducted on a variety of multi-view data sets, which have demonstrated the superiority of the proposed method.

Nonlinear subspace clustering by functional link neural networks

Multi-view data clustering often aims to utilize various representations or views of original data to improve the clustering performance compared to the single-view clustering approach. Most multi-view subspace clustering methods are proposed to construct the affinity matrix of each view individually and then implement with spectral clustering for multi-view data clustering. The multi-view low-rank sparse subspace clustering (MLRSSC) is an effective and popular clustering algorithm among multi-view subspace clustering. This method can explore the joint subspace representation through creating an affinity matrix integrated of all views of input data. In addition, the low-rank and sparsity constraints are introduced into this method to enhance the clustering results. However, the original MLRSSC uses the mean square error as the fidelity term while not consider the complex noise pollution in real situations. Therefore, we introduce a complex noise modeling approach, i.e., independent and piecewise identically distributed (IPID) noise model, for MLRSSC to improve its performance. The related experimental results confirm that this proposed algorithm surpasses many state-of-the-art subspace clustering methods on several real-world datasets.

In this article, we propose a deep extension of sparse subspace clustering, termed deep subspace clustering with L1-norm (DSC-L1). Regularized by the unit sphere distribution assumption for the learned deep features, DSC-L1 can infer a new data affinity matrix by simultaneously satisfying the sparsity principle of SSC and the nonlinearity given by neural networks. One of the appealing advantages brought by DSC-L1 is that when original real-world data do not meet the class-specific linear subspace distribution assumption, DSC-L1 can employ neural networks to make the assumption valid with its nonlinear transformations. Moreover, we prove that our neural network could sufficiently approximate the minimizer under mild conditions. To the best of our knowledge, this could be one of the first deep-learning-based subspace clustering methods. Extensive experiments are conducted on four real-world data sets to show that the proposed method is significantly superior to 17 existing methods for subspace clustering on handcrafted features and raw data.

Subspace clustering methods based on data self-expression have become very popular for learning from data that lie in a union of low-dimensional linear subspaces. However, the applicability of subspace clustering has been limited because practical visual data in raw form do not necessarily lie in such linear subspaces. On the other hand, while Convolutional Neural Network (ConvNet) has been demonstrated to be a powerful tool for extracting discriminative features from visual data, training such a ConvNet usually requires a large amount of labeled data, which are unavailable in subspace clustering applications. To achieve simultaneous feature learning and subspace clustering, we propose an end-to-end trainable framework, called Self-Supervised Convolutional Subspace Clustering Network (S$^2$ConvSCN), that combines a ConvNet module (for feature learning), a self-expression module (for subspace clustering) and a spectral clustering module (for self-supervision) into a joint optimization framework. Particularly, we introduce a dual self-supervision that exploits the output of spectral clustering to supervise the training of the feature learning module (via a classification loss) and the self-expression module (via a spectral clustering loss). Our experiments on four benchmark datasets show the effectiveness of the dual self-supervision and demonstrate superior performance of our proposed approach.

Subspace clustering is an effective algorithm refer to the problem which separate the data lying on a union of subspaces. Usually the algorithm consists of two steps. First, an affinity matrix is calculated from the self-representation of the data. Second, spectral clustering is used to cluster the data by the affinity matrix. The paper introduces a new method based on the sparse subspace clustering. The new method used a new objective which considered both the sparseness and grouping effect. And the affinity matrix which is calculated from the self-representation of the data is furthered optimized. It proved to be more efficient than existing subspace clustering methods.

Subspace clustering has important and wide applications in computer vision and pattern recognition. It is a challenging task to learn low-dimensional subspace structures due to the possible errors (e.g., noise and corruptions) existing in high-dimensional data. Recent subspace clustering methods usually assume a sparse representation of corrupted errors and correct the errors iteratively. However large corruptions in real-world applications can not be well addressed by these methods. A novel optimization model for robust subspace clustering is proposed in this paper. The objective function of our model mainly includes two parts. The first part aims to achieve a sparse representation of each high-dimensional data point with other data points. The second part aims to maximize the correntropy between a given data point and its low-dimensional representation with other points. Correntropy is a robust measure so that the influence of large corruptions on subspace clustering can be greatly suppressed. An extension of our method with explicit introduction of representation error terms into the model is also proposed. Half-quadratic minimization is provided as an efficient solution to the proposed robust subspace clustering formulations. Experimental results on Hopkins 155 dataset and Extended Yale Database B demonstrate that our method outperforms state-of-the-art subspace clustering methods.

Video co-segmentation refers to the task of jointly segmenting common objects appearing in a given group of videos. In practice, high-dimensional data such as videos can be conceptually thought as being drawn from a union of subspaces corresponding to categories rather than from a smooth manifold. Therefore, segmenting data into respective subspaces --- subspace clustering --- finds widespread applications in computer vision, including co-segmentation. State-of-the-art methods via subspace clustering seek to solve the problem in two steps: First, an affinity matrix is built from data, with appearance features or motion patterns. Second, the data are segmented by applying spectral clustering to the affinity matrix. However, this process is insufficient to obtain an optimal solution since it does not take into account the {\em interdependence} of the affinity matrix with the segmentation. In this work, we present a novel unified video co-segmentation framework inspired by the recent Structured Sparse Subspace Clustering ($\mathrm{S^{3}C}$) based on the {\em self-expressiveness} model. Our method yields more consistent segmentation results. In order to improve the detectability of motion features with missing trajectories due to occlusion or tracked points moving out of frames, we add an extra-dimensional signature to the motion trajectories. Moreover, we reformulate the $\mathrm{S^{3}C}$ algorithm by adding the affine subspace constraint in order to make it more suitable to segment rigid motions lying in affine subspaces of dimension at most $3$. Our experiments on MOViCS dataset show that our framework achieves the highest overall performance among baseline algorithms and demonstrate its robustness to heavy noise.

Graph Regularized Residual Subspace Clustering Network for hyperspectral image clustering

Block-diagonal structure learning for subspace clustering

Nonlinear subspace clustering for image clustering

Attention reweighted sparse subspace clustering

Subspace clustering refers to the problem of clustering high-dimensional data into a union of low-dimensional subspaces. Current subspace clustering approaches are usually based on a two-stage framework. In the first stage, an affinity matrix is generated from data. In the second one, spectral clustering is applied on the affinity matrix. However, the affinity matrix produced by two-stage methods cannot fully reveal the similarity between data points from the same subspace, resulting in inaccurate clustering. Besides, most approaches fail to solve large-scale clustering problems due to poor efficiency. In this paper, we first propose a new scalable sparse method called Iterative Maximum Correlation (IMC) to learn the affinity matrix from data. Then we develop Piecewise Correlation Estimation (PCE) to densify the intra-subspace similarity produced by IMC. Finally we extend our work into a Sparse-Dense Subspace Clustering (SDSC) framework with a dense stage to optimize the affinity matrix for two-stage methods. We show that IMC is efficient for large-scale tasks, and PCE ensures better performance for IMC. We show the universality of our SDSC framework for current two-stage methods as well. Experiments on benchmark data sets demonstrate the effectiveness of our approaches.