pith. sign in

arxiv: 1411.4102 · v1 · pith:FOJO6TVMnew · submitted 2014-11-15 · 💻 cs.CV · cs.LG

Anisotropic Agglomerative Adaptive Mean-Shift

classification 💻 cs.CV cs.LG
keywords adaptivebandwidthclusteringmeanmethodologyshiftagglomerationallows
0
0 comments X
read the original abstract

Mean Shift today, is widely used for mode detection and clustering. The technique though, is challenged in practice due to assumptions of isotropicity and homoscedasticity. We present an adaptive Mean Shift methodology that allows for full anisotropic clustering, through unsupervised local bandwidth selection. The bandwidth matrices evolve naturally, adapting locally through agglomeration, and in turn guiding further agglomeration. The online methodology is practical and effecive for low-dimensional feature spaces, preserving better detail and clustering salience. Additionally, conventional Mean Shift either critically depends on a per instance choice of bandwidth, or relies on offline methods which are inflexible and/or again data instance specific. The presented approach, due to its adaptive design, also alleviates this issue - with a default form performing generally well. The methodology though, allows for effective tuning of results.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.