A unifying approach to hard and probabilistic clustering

Ron Zass*, Amnon Shashua

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

119 Scopus citations

Abstract

We derive the clustering problem from first principles showing that the goal of achieving a probabilistic, or "hard", multi class clustering result is equivalent to the algebraic problem of a completely positive factorization under a doubly stochastic constraint. We show that spectral clustering, normalized cuts, kernel K-means and the various normalizations of the associated affinity matrix are particular instances and approximations of this general principle. We propose an efficient algorithm for achieving a completely positive factorization and extend the basic clustering scheme to situations where partial label information is available.

Original languageAmerican English
Title of host publicationProceedings - 10th IEEE International Conference on Computer Vision, ICCV 2005
Pages294-301
Number of pages8
DOIs
StatePublished - 2005
EventProceedings - 10th IEEE International Conference on Computer Vision, ICCV 2005 - Beijing, China
Duration: 17 Oct 200520 Oct 2005

Publication series

NameProceedings of the IEEE International Conference on Computer Vision
VolumeI

Conference

ConferenceProceedings - 10th IEEE International Conference on Computer Vision, ICCV 2005
Country/TerritoryChina
CityBeijing
Period17/10/0520/10/05

Fingerprint

Dive into the research topics of 'A unifying approach to hard and probabilistic clustering'. Together they form a unique fingerprint.

Cite this