We propose a principled account on multiclass spectral clustering. Given a discrete clustering formulation, we first solve a relaxed continuous optimization problem by eigen-decomposition. We clarify the role of eigenvectors as a generator of all optimal solutions through orthonormal transforms. We then solve an optimal discretization problem, which seeks a discrete solution closest to the continuous optima. The discretization is efficiently computed in an iterative fashion using singular value decomposition and nonmaximum suppression. The resulting discrete solutions are nearly global-optimal. Our method is robust to random initialization and converges faster than other clustering methods. Experiments on real image segmentation are reported.
Multiclass spectral clustering
01.01.2003
534501 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Multiclass Spectral Clustering
British Library Conference Proceedings | 2003
|Tiefergelegt - Fahrbericht Setra Multiclass NF
Kraftfahrwesen | 2007
|Multi ( C ) Klassentreffen - Setra Multiclass
Kraftfahrwesen | 2016
|Verpackungs Kuenstler: Setra Multiclass NF
Kraftfahrwesen | 2006
|