Structured Sparse Subspace Clustering: A Joint Affinity Learning and Subspace Clustering Framework
arXiv:1610.05211 · doi:10.1109/TIP.2017.2691557
Abstract
Subspace clustering refers to the problem of segmenting data drawn from a union of subspaces. State-of-the-art approaches for solving this problem follow a two-stage approach. In the first step, an affinity matrix is learned from the data using sparse or low-rank minimization techniques. In the second step, the segmentation is found by applying spectral clustering to this affinity. While this approach has led to state-of-the-art results in many applications, it is sub-optimal because it does not exploit the fact that the affinity and the segmentation depend on each other. In this paper, we propose a joint optimization framework --- Structured Sparse Subspace Clustering (SC) --- for learning both the affinity and the segmentation. The proposed SC framework is based on expressing each data point as a structured sparse linear combination of all other data points, where the structure is induced by a norm that depends on the unknown segmentation. Moreover, we extend the proposed SC framework into Constrained Structured Sparse Subspace Clustering (CSC) in which available partial side-information is incorporated into the stage of learning the affinity. We show that both the structured sparse representation and the segmentation can be found via a combination of an alternating direction method of multipliers with spectral clustering. Experiments on a synthetic data set, the Extended Yale B data set, the Hopkins 155 motion segmentation database, and three cancer data sets demonstrate the effectiveness of our approach.
14 pages, 6 figures
References in corpus (3)
Cited by in corpus (30)
- Enhanced Latent Multi-view Subspace Clustering
- On Geometric Analysis of Affine Sparse Subspace Clustering
- Active Orthogonal Matching Pursuit for Sparse Subspace Clustering
- Simultaneous Subspace Clustering and Cluster Number Estimating based on Triplet Relationship
- Evolutionary Self-Expressive Models for Subspace Clustering
- Doubly Stochastic Subspace Clustering
- Multiple Flat Projections for Cross-manifold Clustering
- Neither Global Nor Local: A Hierarchical Robust Subspace Clustering For Image Data
- Structured Graph Learning for Scalable Subspace Clustering: From Single-view to Multi-view
- Self-Supervised Convolutional Subspace Clustering Network
- Online Structural Change-point Detection of High-dimensional Streaming Data via Dynamic Sparse Subspace Learning
- Towards Clustering-friendly Representations: Subspace Clustering via Graph Filtering
- Self-Expressive Subspace Clustering to Recognize Motion Dynamics of a Multi-Joint Coordination for Chronic Ankle Instability
- Restricted Connection Orthogonal Matching Pursuit For Sparse Subspace Clustering
- Stochastic Sparse Subspace Clustering
- Residual Encoder-Decoder Network for Deep Subspace Clustering
- Sparse-Dense Subspace Clustering
- Scaled Simplex Representation for Subspace Clustering
- Minimal Sample Subspace Learning: Theory and Algorithms
- Self-supervised Symmetric Nonnegative Matrix Factorization
- Clustering-aware Graph Construction: A Joint Learning Perspective
- Joint Featurewise Weighting and Lobal Structure Learning for Multi-view Subspace Clustering
- Rectified Euler k-means and Beyond
- Neural Ordinary Differential Equation Model for Evolutionary Subspace Clustering and Its Applications
- CoSeNet: A Novel Approach for Optimal Segmentation of Correlation Matrices
- Weighted Sparse Subspace Representation: A Unified Framework for Subspace Clustering, Constrained Clustering, and Active Learning
- Is an Affine Constraint Needed for Affine Subspace Clustering?
- Learning a Self-Expressive Network for Subspace Clustering
- Three-Stage Subspace Clustering Framework with Graph-Based Transformation and Optimization
- Learning Deep Representation with Energy-Based Self-Expressiveness for Subspace Clustering