Robust Subspace Recovery via Bi-Sparsity Pursuit

2014/03/31 by Xiao Bian, Bian, Xiao, Hamid Krim +1 · 1 citation
Computer Science · #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #cs.CV

paper · pdf · doi:10.48550/arxiv.1403.8067

arxiv created 2014/04/20 · arxiv updated 2014/04/22

Abstract

Successful applications of sparse models in computer vision and machine learning imply that in many real-world applications, high dimensional data is distributed in a union of low dimensional subspaces. Nevertheless, the underlying structure may be affected by sparse errors and/or outliers. In this paper, we propose a bi-sparse model as a framework to analyze this problem and provide a novel algorithm to recover the union of subspaces in presence of sparse corruptions. We further show the effectiveness of our method by experiments on both synthetic data and real-world vision data.

Cited by

• Decomposition into Low-rank plus Additive Matrices for Background/Foreground Separation: A Review for a Comparative Evaluation with a Large-Scale Dataset

Related

• Approximate Subspace-Sparse Recovery with Corrupted Data via Constrained ℓ₁-Minimization
• Finding the Sparsest Vectors in a Subspace: Theory, Algorithms, and Applications
• Scaling Law for Recovering the Sparsest Element in a Subspace
• Sparse Subspace Clustering: Algorithm, Theory, and Applications
• Robust Recovery of Subspace Structures by Low-Rank Representation