Fast kernel sparse representation

Simple item page
dc.contributor.authorLi, Hanxi
dc.contributor.authorGao, Yongsheng
dc.contributor.authorSun, Jun
dc.coverage.spatialNoosa Australia
dc.date.accessioned2015-12-08T22:19:55Z
dc.date.createdDecember 6-8 2011
dc.date.issued2011
dc.date.updated2016-02-24T09:43:07Z
dc.description.abstractTwo efficient algorithms are proposed to seek the sparse representation on high-dimensional Hilbert space. By proving that all the calculations in Orthogonal Match Pursuit (OMP) are essentially inner-product combinations, we modify the OMP algorithm to apply the kernel-trick. The proposed Kernel OMP (KOMP) is much faster than the existing methods, and illustrates higher accuracy in some scenarios. Furthermore, inspired by the success of group-sparsity, we enforce a rigid group-sparsity constraint on KOMP which leads to a noniterative variation. The constrained cousin of KOMP, dubbed as Single-Step KOMP (S-KOMP), merely takes one step to achieve the sparse coefficients. A remarkable improvement (up to 2,750 times) in efficiency is reported for S-KOMP, with only a negligible loss of accuracy.
dc.identifier.isbn9780769545882
dc.identifier.urihttp://hdl.handle.net/1885/31766
dc.publisherIEEE Communications Society
dc.relation.ispartofseriesDigital Image Computing: Techniques and Applications (DICTA 2011)
dc.sourceA Novel Illumination-Invariant Loss for Monocular 3D Pose Estimation
dc.subjectKeywords: Efficient algorithm; High-dimensional; Inner product; Kernel trick; Loss of accuracy; Non-iterative; One step; Orthogonal Matching Pursuit; Single-step; Sparse representation; Algorithms Kernel trick; Orthogonal Matching Pursuit; Sparse Representation
dc.titleFast kernel sparse representation
dc.typeConference paper
local.bibliographicCitation.lastpage77
local.bibliographicCitation.startpage72
local.contributor.affiliationLi, Hanxi, College of Engineering and Computer Science, ANU
local.contributor.affiliationGao, Yongsheng, Griffith University
local.contributor.affiliationSun, Jun, College of Engineering and Computer Science, ANU
local.contributor.authoremailu4704843@anu.edu.au
local.contributor.authoruidLi, Hanxi, u4437149
local.contributor.authoruidSun, Jun, u4704843
local.description.embargo2037-12-31
local.description.notesImported from ARIES
local.description.refereedYes
local.identifier.absfor089999 - Information and Computing Sciences not elsewhere classified
local.identifier.ariespublicationf5625xPUB86
local.identifier.doi10.1109/DICTA.2011.20
local.identifier.scopusID2-s2.0-84863078673
local.identifier.uidSubmittedByf5625
local.type.statusPublished Version

Downloads

Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
01_Li_Fast_kernel_sparse_2011.pdf
Size:
287.43 KB
Format:
Adobe Portable Document Format
Download

Collections

ANU Research Publications

DSpace software copyright © 2002-2024 LYRASIS