Dictionary training for sparse representation as generalization of K-means clustering

Recent dictionary training algorithms for sparse representation like K-SVD, MOD, and their variation are reminiscent of K-means clustering, and this letter investigates such algorithms from that viewpoint. It shows: though K-SVD is sequential like K-means, it fails to simplify to K-means by destroyi...

Full description

Saved in:
Bibliographic Details
Main Authors: Sahoo, Sujit Kumar, Makur, Anamitra
Other Authors: School of Electrical and Electronic Engineering
Format: Article
Language:English
Published: 2013
Subjects:
Online Access:https://hdl.handle.net/10356/96655
http://hdl.handle.net/10220/9970
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-96655
record_format dspace
spelling sg-ntu-dr.10356-966552020-03-07T14:02:47Z Dictionary training for sparse representation as generalization of K-means clustering Sahoo, Sujit Kumar Makur, Anamitra School of Electrical and Electronic Engineering DRNTU::Engineering::Electrical and electronic engineering Recent dictionary training algorithms for sparse representation like K-SVD, MOD, and their variation are reminiscent of K-means clustering, and this letter investigates such algorithms from that viewpoint. It shows: though K-SVD is sequential like K-means, it fails to simplify to K-means by destroying the structure in the sparse coefficients. In contrast, MOD can be viewed as a parallel generalization of K-means, which simplifies to K-means without perturbing the sparse coefficients. Keeping memory usage in mind, we propose an alternative to MOD; a sequential generalization of K-means (SGK). While experiments suggest a comparable training performances across the algorithms, complexity analysis shows MOD and SGK to be faster under a dimensionality condition. Accepted version 2013-05-22T06:45:03Z 2019-12-06T19:33:32Z 2013-05-22T06:45:03Z 2019-12-06T19:33:32Z 2013 2013 Journal Article Sahoo, S. K., & Makur, A. (2013). Dictionary Training for Sparse Representation as Generalization of K-Means Clustering. IEEE Signal Processing Letters, 20(6), 587-590. https://hdl.handle.net/10356/96655 http://hdl.handle.net/10220/9970 10.1109/LSP.2013.2258912 171898 en IEEE signal processing letters © 2013 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, 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 component of this work in other works. The published version is available at: [http://dx.doi.org/10.1109/LSP.2013.2258912]. application/pdf
institution Nanyang Technological University
building NTU Library
country Singapore
collection DR-NTU
language English
topic DRNTU::Engineering::Electrical and electronic engineering
spellingShingle DRNTU::Engineering::Electrical and electronic engineering
Sahoo, Sujit Kumar
Makur, Anamitra
Dictionary training for sparse representation as generalization of K-means clustering
description Recent dictionary training algorithms for sparse representation like K-SVD, MOD, and their variation are reminiscent of K-means clustering, and this letter investigates such algorithms from that viewpoint. It shows: though K-SVD is sequential like K-means, it fails to simplify to K-means by destroying the structure in the sparse coefficients. In contrast, MOD can be viewed as a parallel generalization of K-means, which simplifies to K-means without perturbing the sparse coefficients. Keeping memory usage in mind, we propose an alternative to MOD; a sequential generalization of K-means (SGK). While experiments suggest a comparable training performances across the algorithms, complexity analysis shows MOD and SGK to be faster under a dimensionality condition.
author2 School of Electrical and Electronic Engineering
author_facet School of Electrical and Electronic Engineering
Sahoo, Sujit Kumar
Makur, Anamitra
format Article
author Sahoo, Sujit Kumar
Makur, Anamitra
author_sort Sahoo, Sujit Kumar
title Dictionary training for sparse representation as generalization of K-means clustering
title_short Dictionary training for sparse representation as generalization of K-means clustering
title_full Dictionary training for sparse representation as generalization of K-means clustering
title_fullStr Dictionary training for sparse representation as generalization of K-means clustering
title_full_unstemmed Dictionary training for sparse representation as generalization of K-means clustering
title_sort dictionary training for sparse representation as generalization of k-means clustering
publishDate 2013
url https://hdl.handle.net/10356/96655
http://hdl.handle.net/10220/9970
_version_ 1681048074451943424