Hierarchical Kernel Stick-Breaking Process for Multi-Task Image Analysis

Abstract

The kernel stick-breaking process (KSBP) is employed to segment general imagery, imposing the condition that patches (small blocks of pixels) that are spatially proximate are more likely to be associated with the same cluster (segment). The number of clusters is not set a priori and is inferred from the hierarchical Bayesian model. Further, KSBP is integrated with a shared Dirichlet process prior to simultaneously model multiple images, inferring their inter-relationships. This latter application may be useful for sorting and learning relationships between multiple images. The Bayesian inference algorithm is based on a hybrid of variational Bayesian analysis and local sampling. In addition to providing details on the model and associated inference framework, example results are presented for several image-analysis problems.

Cite

Text

An et al. "Hierarchical Kernel Stick-Breaking Process for Multi-Task Image Analysis." International Conference on Machine Learning, 2008. doi:10.1145/1390156.1390159

Markdown

[An et al. "Hierarchical Kernel Stick-Breaking Process for Multi-Task Image Analysis." International Conference on Machine Learning, 2008.](https://mlanthology.org/icml/2008/an2008icml-hierarchical/) doi:10.1145/1390156.1390159

BibTeX

@inproceedings{an2008icml-hierarchical,
  title     = {{Hierarchical Kernel Stick-Breaking Process for Multi-Task Image Analysis}},
  author    = {An, Qi and Wang, Chunping and Shterev, Ivo and Wang, Eric and Carin, Lawrence and Dunson, David B.},
  booktitle = {International Conference on Machine Learning},
  year      = {2008},
  pages     = {17-24},
  doi       = {10.1145/1390156.1390159},
  url       = {https://mlanthology.org/icml/2008/an2008icml-hierarchical/}
}