Paper Info
Title
A Markov random field-regulated Pitman-Yor process prior for spatially constrained data clustering
Abstract
In this work, we propose a Markov random field-regulated Pitman-Yor process (MRF-PYP) prior for nonparametric clustering of data with spatial interdependencies. The MRF-PYP is constructed by imposing a Pitman-Yor process over the distribution of the latent variables that allocate data points to clusters (model states), the discount hyperparameter of which is regulated by an additionally postulated simplified (pointwise) Markov random field (Gibbsian) distribution with a countably infinite number of states. Further, based on the stick-breaking construction of the Pitman-Yor process, we derive an efficient truncated variational Bayesian algorithm for model inference. We examine the efficacy of our approach by considering an unsupervised image segmentation application using a real-world dataset. We show that our approach completely outperforms related methods from the field of Bayesian nonparametrics, including the recently proposed infinite hidden Markov random field model and the Dirichlet process prior.
Year
DOI
Venue
2013
10.1016/j.patcog.2012.11.026
Pattern Recognition
Keywords
Field
DocType
bayesian nonparametrics,markov random field,model inference,markov random field model,pitman-yor process,data point,dirichlet process,model state,countably infinite number,random field-regulated pitman-yor process,pattern recognition,computer science,pitman yor process,clustering
Pattern recognition,Hidden Markov random field,Markov random field,Markov model,Markov chain,Artificial intelligence,Variable-order Markov model,Hidden Markov model,Pitman–Yor process,Machine learning,Mathematics,Markov renewal process
Journal
Volume
Issue
ISSN
46
6
0031-3203
Citations 
PageRank 
References 
5
0.41
19
Authors
1
Name
Order
Citations
PageRank
Sotirios P. Chatzis125024.25