Spectral clustering algorithms rely on the spectrum of some data-dependent matrices
to perform clustering and usually a prior knowledge on the number of clusters is
needed.
We consider the setting of performing spectral clustering in a Hilbert space. We
show how spectral clustering, coupled with some preliminary change of representation
in a reproducing kernel Hilbert space, can bring down the representation of classes
to a low-dimensional space and we propose a new algorithm for spectral clustering
that automatically estimates the number of classes.