Low-Rank Sparse Coding for Image Classification

Handle URI:
http://hdl.handle.net/10754/556147
Title:
Low-Rank Sparse Coding for Image Classification
Authors:
Zhang, Tianzhu; Ghanem, Bernard ( 0000-0002-5534-587X ) ; Liu, Si; Xu, Changsheng; Ahuja, Narendra
Abstract:
In this paper, we propose a low-rank sparse coding (LRSC) method that exploits local structure information among features in an image for the purpose of image-level classification. LRSC represents densely sampled SIFT descriptors, in a spatial neighborhood, collectively as low-rank, sparse linear combinations of code words. As such, it casts the feature coding problem as a low-rank matrix learning problem, which is different from previous methods that encode features independently. This LRSC has a number of attractive properties. (1) It encourages sparsity in feature codes, locality in codebook construction, and low-rankness for spatial consistency. (2) LRSC encodes local features jointly by considering their low-rank structure information, and is computationally attractive. We evaluate the LRSC by comparing its performance on a set of challenging benchmarks with that of 7 popular coding and other state-of-the-art methods. Our experiments show that by representing local features jointly, LRSC not only outperforms the state-of-the-art in classification accuracy but also improves the time complexity of methods that use a similar sparse linear representation model for feature coding.
KAUST Department:
Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
Publisher:
Institute of Electrical and Electronics Engineers (IEEE)
Journal:
2013 IEEE International Conference on Computer Vision
Conference/Event name:
2013 14th IEEE International Conference on Computer Vision, ICCV 2013
Issue Date:
1-Dec-2013
DOI:
10.1109/ICCV.2013.42
Type:
Conference Paper
Additional Links:
http://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=6751144; http://vcc.kaust.edu.sa/Documents/B.%20Ghanem/papers/LRSC_ICCV2013.pdf
Appears in Collections:
Conference Papers; Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division

Full metadata record

DC FieldValue Language
dc.contributor.authorZhang, Tianzhuen
dc.contributor.authorGhanem, Bernarden
dc.contributor.authorLiu, Sien
dc.contributor.authorXu, Changshengen
dc.contributor.authorAhuja, Narendraen
dc.date.accessioned2015-06-02T14:04:00Zen
dc.date.available2015-06-02T14:04:00Zen
dc.date.issued2013-12-01en
dc.identifier.doi10.1109/ICCV.2013.42en
dc.identifier.urihttp://hdl.handle.net/10754/556147en
dc.description.abstractIn this paper, we propose a low-rank sparse coding (LRSC) method that exploits local structure information among features in an image for the purpose of image-level classification. LRSC represents densely sampled SIFT descriptors, in a spatial neighborhood, collectively as low-rank, sparse linear combinations of code words. As such, it casts the feature coding problem as a low-rank matrix learning problem, which is different from previous methods that encode features independently. This LRSC has a number of attractive properties. (1) It encourages sparsity in feature codes, locality in codebook construction, and low-rankness for spatial consistency. (2) LRSC encodes local features jointly by considering their low-rank structure information, and is computationally attractive. We evaluate the LRSC by comparing its performance on a set of challenging benchmarks with that of 7 popular coding and other state-of-the-art methods. Our experiments show that by representing local features jointly, LRSC not only outperforms the state-of-the-art in classification accuracy but also improves the time complexity of methods that use a similar sparse linear representation model for feature coding.en
dc.publisherInstitute of Electrical and Electronics Engineers (IEEE)en
dc.relation.urlhttp://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=6751144en
dc.relation.urlhttp://vcc.kaust.edu.sa/Documents/B.%20Ghanem/papers/LRSC_ICCV2013.pdfen
dc.rights(c) 2013 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, including reprinting/ republishing this material for advertising or promotional purposes, creating new collective works for resale or redistribution to servers or lists, or reuse of any copyrighted components of this work in other works.en
dc.subjectbowen
dc.subjectimage classificationen
dc.subjectlow-ranken
dc.titleLow-Rank Sparse Coding for Image Classificationen
dc.typeConference Paperen
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Divisionen
dc.identifier.journal2013 IEEE International Conference on Computer Visionen
dc.conference.date1 December 2013 through 8 December 2013en
dc.conference.name2013 14th IEEE International Conference on Computer Vision, ICCV 2013en
dc.conference.locationSydney, NSWen
dc.eprint.versionPost-printen
dc.contributor.institutionAdvanced Digital Sciences Center of Illinois, Singaporeen
dc.contributor.institutionNational University of Singapore, Singaporeen
dc.contributor.institutionInstitute of Automation, Chinese Academy of Sciences, P. R. Chinaen
dc.contributor.institutionUniversity of Illinois at Urbana-Champaign, Urbana, IL USAen
kaust.authorGhanem, Bernarden
All Items in KAUST are protected by copyright, with all rights reserved, unless otherwise indicated.