Welcome to the new version of CaltechAUTHORS. Login is currently restricted to library staff. If you notice any issues, please email coda@library.caltech.edu
Published 2005 | Published
Book Section - Chapter Open

Self-Tuning Spectral Clustering

Abstract

We study a number of open issues in spectral clustering: (i) Selecting the appropriate scale of analysis, (ii) Handling multi-scale data, (iii) Clustering with irregular background clutter, and, (iv) Finding automatically the number of groups. We first propose that a 'local' scale should be used to compute the affinity between each pair of points. This local scaling leads to better clustering especially when the data includes multiple scales and when the clusters are placed within a cluttered background. We further suggest exploiting the structure of the eigenvectors to infer automatically the number of groups. This leads to a new algorithm in which the final randomly initialized k-means stage is eliminated.

Additional Information

© 2005 Massachusetts Institute of Technology. Finally, we wish to thank Yair Weiss for providing us his code for spectral clustering. This research was supported by the MURI award number SA3318 and by the Center of Neuromorphic Systems Engineering award number EEC-9402726.

Attached Files

Published - 2619-self-tuning-spectral-clustering.pdf

Files

2619-self-tuning-spectral-clustering.pdf
Files (307.5 kB)
Name Size Download all
md5:4a4d4a8fa502ee71994bdd5ecceaf4f7
307.5 kB Preview Download

Additional details

Created:
August 19, 2023
Modified:
January 13, 2024