Clustering with Normalized Cuts is Clustering with a Hyperplane,” Statistical Learning in Computer Vision

Clustering with Normalized Cuts is Clustering with a Hyperplane,” Statistical Learning in Computer Vision (2004)

Cached

Download Links

by Ali Rahimi , Ben Recht

Venue:	in Statistical Learning in Computer Vision
Citations:	11 - 2 self

BibTeX

@INPROCEEDINGS{Rahimi04clusteringwith,
    author = {Ali Rahimi and Ben Recht},
    title = {Clustering with Normalized Cuts is Clustering with a Hyperplane,” Statistical Learning in Computer Vision},
    booktitle = {in Statistical Learning in Computer Vision},
    year = {2004}
}

Bookmark

OpenURL

Abstract

Abstract. We present a set of clustering algorithms that identify cluster boundaries by searching for a hyperplanar gap in unlabeled data sets. It turns out that the Normalized Cuts algorithm of Shi and Malik [1], originally presented as a graph-theoretic algorithm, can be interpreted as such an algorithm. Viewing Normalized Cuts under this light reveals that it pays more attention to points away from the center of the data set than those near the center of the data set. As a result, it can sometimes split long clusters and display sensitivity to outliers. We derive a variant of Normalized Cuts that assigns uniform weight to all points, eliminating the sensitivity to outliers. 1

Citations

3340	Pattern Classification and Scene Analysis - Duda, Hart - 1973
1824	Normalized cuts and image segmentation - Shi, Malik - 2000
124	Support vector clustering - Ben-Hur, Horn, et al. - 2001
95	Input Space vs. Feature Space in Kernel-Based Methods - Schölkopf, Mika, et al. - 1999
75	J.C.: Support vector method for novelty detection - Scholkopf, Williamson, et al.
47	Meilă M: A Comparison of Spectral Clustering Algorithms - Verma - 2003
15	On semidefinite relaxation for normalized k-cut and connections to spectral clustering - Xing, Jordan - 2003
14	A large scale clustering scheme for kernel k-means - Zhang, Rudnicky - 2002
5	R.P.W.: Outliers and data descriptions. In - Tax, Duin
3	Mercer Kernel Based Clustering in Feature Space - Girolani - 2001