Multi-Manifold Clustering
Multi-Manifold Clustering (MMC) is a type of spectral algorithm for clustering data which resides on non-Euclidean spaces and has intersections between different groups. It appears in the following two papers.- Short conference paper: Multi-Manifold Modeling in Non-Euclidean Spaces, X. Wang, K. Slavakis and G. Lerman. AISTATS (2015), Page 1023--1032.
- Journal version (preprint) Riemannian Multi-Manifold Modeling, X. Wang, K. Slavakis and G. Lerman. arXiv e-prints (2014).
Matlab code for Multi-Manifold Clustering: MMC.
For additional short description, see slides.
Data Sets
The following are links to the data sets used in this work: Brodatz texture dataset, Dyntex++ dataset. For use of these data sets, please refer to the original websites for details.
The material presented in this work is supported by Digital Technology Initiative, NSF grants DMS-09-56072, DMS-14-18386 and Eager-13-43860, Doctoral Dissertation Fellowship at UMN and Feinberg Foundation Visiting Faculty Program Fellowship of the Weizmann Institute of Science.
Last Modified Sunday April 23, 2017 The views and opinions expressed in this page are strictly those of the page author.
The contents of this page have not been reviewed or approved by the University of Minnesota.
|