Representation learning with deep extreme learning machines for efficient image set classification

Handle URI:
http://hdl.handle.net/10754/622242
Title:
Representation learning with deep extreme learning machines for efficient image set classification
Authors:
Uzair, Muhammad; Shafait, Faisal; Ghanem, Bernard ( 0000-0002-5534-587X ) ; Mian, Ajmal
Abstract:
Efficient and accurate representation of a collection of images, that belong to the same class, is a major research challenge for practical image set classification. Existing methods either make prior assumptions about the data structure, or perform heavy computations to learn structure from the data itself. In this paper, we propose an efficient image set representation that does not make any prior assumptions about the structure of the underlying data. We learn the nonlinear structure of image sets with deep extreme learning machines that are very efficient and generalize well even on a limited number of training samples. Extensive experiments on a broad range of public datasets for image set classification show that the proposed algorithm consistently outperforms state-of-the-art image set classification methods both in terms of speed and accuracy.
KAUST Department:
Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division; Electrical Engineering Program; Visual Computing Center (VCC)
Citation:
Uzair M, Shafait F, Ghanem B, Mian A (2016) Representation learning with deep extreme learning machines for efficient image set classification. Neural Computing and Applications. Available: http://dx.doi.org/10.1007/s00521-016-2758-x.
Publisher:
Springer Nature
Journal:
Neural Computing and Applications
Issue Date:
9-Dec-2016
DOI:
10.1007/s00521-016-2758-x
Type:
Article
ISSN:
0941-0643; 1433-3058
Sponsors:
This work was supported by the Australian Research Council (ARC) Grant DP110102399 and UWA Research Collaboration Award 2014.
Additional Links:
http://link.springer.com/article/10.1007%2Fs00521-016-2758-x
Appears in Collections:
Articles; Electrical Engineering Program; Visual Computing Center (VCC); Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division

Full metadata record

DC FieldValue Language
dc.contributor.authorUzair, Muhammaden
dc.contributor.authorShafait, Faisalen
dc.contributor.authorGhanem, Bernarden
dc.contributor.authorMian, Ajmalen
dc.date.accessioned2017-01-02T08:42:40Z-
dc.date.available2017-01-02T08:42:40Z-
dc.date.issued2016-12-09en
dc.identifier.citationUzair M, Shafait F, Ghanem B, Mian A (2016) Representation learning with deep extreme learning machines for efficient image set classification. Neural Computing and Applications. Available: http://dx.doi.org/10.1007/s00521-016-2758-x.en
dc.identifier.issn0941-0643en
dc.identifier.issn1433-3058en
dc.identifier.doi10.1007/s00521-016-2758-xen
dc.identifier.urihttp://hdl.handle.net/10754/622242-
dc.description.abstractEfficient and accurate representation of a collection of images, that belong to the same class, is a major research challenge for practical image set classification. Existing methods either make prior assumptions about the data structure, or perform heavy computations to learn structure from the data itself. In this paper, we propose an efficient image set representation that does not make any prior assumptions about the structure of the underlying data. We learn the nonlinear structure of image sets with deep extreme learning machines that are very efficient and generalize well even on a limited number of training samples. Extensive experiments on a broad range of public datasets for image set classification show that the proposed algorithm consistently outperforms state-of-the-art image set classification methods both in terms of speed and accuracy.en
dc.description.sponsorshipThis work was supported by the Australian Research Council (ARC) Grant DP110102399 and UWA Research Collaboration Award 2014.en
dc.publisherSpringer Natureen
dc.relation.urlhttp://link.springer.com/article/10.1007%2Fs00521-016-2758-xen
dc.subjectExtreme learning machineen
dc.subjectImage set classificationen
dc.subjectRepresentation learningen
dc.subjectFace recognitionen
dc.titleRepresentation learning with deep extreme learning machines for efficient image set classificationen
dc.typeArticleen
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Divisionen
dc.contributor.departmentElectrical Engineering Programen
dc.contributor.departmentVisual Computing Center (VCC)en
dc.identifier.journalNeural Computing and Applicationsen
dc.contributor.institutionCOMSATS Institute of Information Technology, Wah Cantonment, Pakistanen
dc.contributor.institutionComputer Science and Software Engineering, The University of Western Australia, Crawley, Australiaen
dc.contributor.institutionNational University of Science and Technology, Islamabad, Pakistanen
kaust.authorGhanem, Bernarden
All Items in KAUST are protected by copyright, with all rights reserved, unless otherwise indicated.