Back to Search Start Over

Deep Sparse Subspace Clustering

Authors :
Peng, Xi
Feng, Jiashi
Xiao, Shijie
Lu, Jiwen
Yi, Zhang
Yan, Shuicheng
Publication Year :
2017

Abstract

In this paper, we present a deep extension of Sparse Subspace Clustering, termed Deep Sparse Subspace Clustering (DSSC). Regularized by the unit sphere distribution assumption for the learned deep features, DSSC 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 DSSC is: when original real-world data do not meet the class-specific linear subspace distribution assumption, DSSC can employ neural networks to make the assumption valid with its hierarchical nonlinear transformations. To the best of our knowledge, this is among the first deep learning based subspace clustering methods. Extensive experiments are conducted on four real-world datasets to show the proposed DSSC is significantly superior to 12 existing methods for subspace clustering.<br />Comment: The initial version is completed at the beginning of 2015

Details

Database :
arXiv
Publication Type :
Report
Accession number :
edsarx.1709.08374
Document Type :
Working Paper