File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Fast low-rank subspace segmentation

TitleFast low-rank subspace segmentation
Authors
KeywordsLocality sensitive hashing
low-rank subspace segmentation
singular value decomposition
Issue Date2014
Citation
IEEE Transactions on Knowledge and Data Engineering, 2014, v. 26, n. 5, p. 1293-1297 How to Cite?
AbstractSubspace segmentation is the problem of segmenting (or grouping) a set of n data points into a number of clusters, with each cluster being a (linear) subspace. The recently established algorithms such as Sparse Subspace Clustering (SSC), Low-Rank Representation (LRR) and Low-Rank Subspace Segmentation (LRSS) are effective in terms of segmentation accuracy, but computationally inefficient as they possess a complexity of O(n3), which is too high to afford for the case where n is very large. In this paper we devise a fast subspace segmentation algorithm with complexity of O(nlog(n)). This is achieved by firstly using partial Singular Value Decomposition (SVD) to approximate the solution of LRSS, secondly utilizing Locality Sensitive Hashing (LSH) to build a sparse affinity graph that encodes the subspace memberships, and finally adopting a fast Normalized Cut (NCut) algorithm to produce the final segmentation results. Besides of high efficiency, our algorithm also has comparable effectiveness as the original LRSS method. Copyright © 2013 IEEE.
Persistent Identifierhttp://hdl.handle.net/10722/326999
ISSN
2023 Impact Factor: 8.9
2023 SCImago Journal Rankings: 2.867
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorZhang, Xin-
dc.contributor.authorSun, Fuchun-
dc.contributor.authorLiu, Guangcan-
dc.contributor.authorMa, Yi-
dc.date.accessioned2023-03-31T05:28:04Z-
dc.date.available2023-03-31T05:28:04Z-
dc.date.issued2014-
dc.identifier.citationIEEE Transactions on Knowledge and Data Engineering, 2014, v. 26, n. 5, p. 1293-1297-
dc.identifier.issn1041-4347-
dc.identifier.urihttp://hdl.handle.net/10722/326999-
dc.description.abstractSubspace segmentation is the problem of segmenting (or grouping) a set of n data points into a number of clusters, with each cluster being a (linear) subspace. The recently established algorithms such as Sparse Subspace Clustering (SSC), Low-Rank Representation (LRR) and Low-Rank Subspace Segmentation (LRSS) are effective in terms of segmentation accuracy, but computationally inefficient as they possess a complexity of O(n3), which is too high to afford for the case where n is very large. In this paper we devise a fast subspace segmentation algorithm with complexity of O(nlog(n)). This is achieved by firstly using partial Singular Value Decomposition (SVD) to approximate the solution of LRSS, secondly utilizing Locality Sensitive Hashing (LSH) to build a sparse affinity graph that encodes the subspace memberships, and finally adopting a fast Normalized Cut (NCut) algorithm to produce the final segmentation results. Besides of high efficiency, our algorithm also has comparable effectiveness as the original LRSS method. Copyright © 2013 IEEE.-
dc.languageeng-
dc.relation.ispartofIEEE Transactions on Knowledge and Data Engineering-
dc.subjectLocality sensitive hashing-
dc.subjectlow-rank subspace segmentation-
dc.subjectsingular value decomposition-
dc.titleFast low-rank subspace segmentation-
dc.typeArticle-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1109/TKDE.2013.114-
dc.identifier.scopuseid_2-s2.0-84901050934-
dc.identifier.volume26-
dc.identifier.issue5-
dc.identifier.spage1293-
dc.identifier.epage1297-
dc.identifier.isiWOS:000337965900020-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats