Name
Abstract | ||
|---|---|---|
Mean shift clustering is a powerful nonparametric technique that does not require prior knowledge of the number of clusters and does not constrain the shape of the clusters. However, being completely unsupervised, its performance suffers when the original distance metric fails to capture the underlying cluster structure. Despite recent advances in semi-supervised clustering methods, there has been little effort towards incorporating supervision into mean shift. We propose a semi-supervised framework for kernel mean shift clustering (SKMS) that uses only pairwise constraints to guide the clustering procedure. The points are first mapped to a high-dimensional kernel space where the constraints are imposed by a linear transformation of the mapped points. This is achieved by modifying the initial kernel matrix by minimizing a log det divergence-based objective function. We show the advantages of SKMS by evaluating its performance on various synthetic and real datasets while comparing with state-of-the-art semi-supervised clustering algorithms. |
Year | DOI | Venue |
|---|---|---|
2014 | 10.1109/TPAMI.2013.190 | Pattern Analysis and Machine Intelligence, IEEE Transactions |
Keywords | Field | DocType |
learning (artificial intelligence),matrix algebra,pattern clustering,clustering procedure,initial kernel matrix,linear transformation,nonparametric technique,real datasets,semisupervised Kernel mean shift clustering,semisupervised clustering methods,semisupervised framework,synthetic datasets,underlying cluster structure,Algorithms,Applications,Clustering,Computer vision,Computing Methodologies,Pattern Recognition,Semi-supervised kernel clustering,Similarity measures,log det Bregman divergence,mean shift clustering | k-medians clustering,Fuzzy clustering,Clustering high-dimensional data,CURE data clustering algorithm,Data stream clustering,Correlation clustering,Pattern recognition,Computer science,Artificial intelligence,Constrained clustering,Cluster analysis | Journal |
Volume | Issue | ISSN |
36 | 6 | 0162-8828 |
Citations | PageRank | References |
34 | 0.92 | 28 |
Authors | ||
4 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Saket Anand | 1 | 87 | 9.36 |
| Sushil Mittal | 2 | 34 | 0.92 |
| Oncel Tuzel | 3 | 2023 | 91.90 |
| Peter Meer | 4 | 9531 | 835.61 |