Title
Subspace segmentation by dense block and sparse representation.
Abstract
Subspace segmentation is a fundamental topic in computer vision and machine learning. However, the success of many popular methods is about independent subspace segmentation instead of the more flexible and realistic disjoint subspace segmentation. Focusing on the disjoint subspaces, we provide theoretical and empirical evidence of inferior performance for popular algorithms such as LRR. To solve these problems, we propose a novel dense block and sparse representation (DBSR) for subspace segmentation and provide related theoretical results. DBSR minimizes a combination of the 1,1-norm and maximum singular value of the representation matrix, leading to a combination of dense block and sparsity. We provide experimental results for synthetic and benchmark data showing that our method can outperform the state-of-the-art.
Year
DOI
Venue
2016
10.1016/j.neunet.2015.11.011
Neural Networks
Keywords
Field
DocType
2-norm,Disjoint,LRR,Subspace segmentation
Subspace segmentation,Singular value,Scale-space segmentation,Disjoint sets,Matrix (mathematics),Artificial intelligence,Mathematical optimization,Pattern recognition,Sparse approximation,Linear subspace,Norm (mathematics),Mathematics,Machine learning
Journal
Volume
Issue
ISSN
75
C
1879-2782
Citations 
PageRank 
References 
10
0.45
36
Authors
6
Name
Order
Citations
PageRank
Kewei Tang1996.72
David B. Dunson2108080.82
Zhixun Su363932.10
Risheng Liu483359.64
Jie Zhang51127.99
Jiangxin Dong6272.34