Title :
Supervised hierarchical Pitman-Yor process for natural scene segmentation
Author :
Shyr, Alex ; Darrell, Trevor ; Jordan, Michael ; Urtasun, Raquel
Author_Institution :
UC Berkeley, Berkeley, CA, USA
Abstract :
From conventional wisdom and empirical studies of annotated data, it has been shown that visual statistics such as object frequencies and segment sizes follow power law distributions. Previous work has shown that both kinds of power-law behavior can be captured by using a hierarchical Pitman-Yor process prior within a nonparametric Bayesian approach to scene segmentation. In this paper, we add label information into the previously unsupervised model. Our approach exploits the labelled data by adding constraints on the parameter space during the variational learning phase. We evaluate our formulation on the LabelMe natural scene dataset, and show the effectiveness of our approach.
Keywords :
Bayes methods; data visualisation; image segmentation; natural scenes; visual databases; LabelMe natural scene dataset; label information; natural scene segmentation; nonparametric Bayesian approach; power-law behavior; supervised hierarchical Pitman-Yor process; unsupervised model; variational learning phase; visual statistics; Bayesian methods; Computational modeling; Gaussian processes; Graphical models; Image segmentation; Indexes; Optimization;
Conference_Titel :
Computer Vision and Pattern Recognition (CVPR), 2011 IEEE Conference on
Conference_Location :
Providence, RI
Print_ISBN :
978-1-4577-0394-2
DOI :
10.1109/CVPR.2011.5995647