Discriminative Transformation Learning for Fuzzy Sparse Subspace Clustering

Abstract

This paper develops a novel iterative framework for subspace clustering in a learned discriminative feature domain. This framework consists of two modules of fuzzy sparse subspace clustering and discriminative transformation learning. In the first module, fuzzy latent labels containing discriminative information and latent representations capturing the subspace structure will be simultaneously evaluated in a feature domain. Then the linear transforming operator with respect to the feature domain will be successively updated in the second module with the advantages of more discrimination, subspace structure preservation and robustness to outliers. These two modules will be alternatively carried out and both theoretical analysis and empirical evaluations will demonstrate its effectiveness and superiorities. In particular, experimental results on three benchmark databases for subspace clustering clearly illustrate that the proposed framework can achieve significant improvements than other state-of-the-art approaches in terms of clustering accuracy.

IEEE Trans. Cybern. Accept

References in corpus (11)

• Auto-Encoding Variational Bayes
• Robust Recovery of Subspace Structures by Low-Rank Representation
• Kernel methods in machine learning
• Constructing the L2-Graph for Robust Subspace Learning and Subspace Clustering
• Robust subspace clustering
• A Unified Framework for Representation-based Subspace Clustering of Out-of-sample and Large-scale Data
• Compressive Spectral Clustering
• Learning Transformations for Clustering and Classification
• Robust Subspace Clustering via Smoothed Rank Approximation
• Joint Sparse Recovery With Semisupervised MUSIC
• Discriminative Nonlinear Analysis Operator Learning: When Cosparse Model Meets Image Classification

Cited by in corpus (1)

• Scaled Simplex Representation for Subspace Clustering