Image Labeling Based on Graphical Models Using Wasserstein Messages and Geometric Assignment.
Ruben HühnerbeinFabrizio SavarinoFreddie ÅströmChristoph SchnörrPublished in: CoRR (2017)
Keyphrases
- image labeling
- graphical models
- conditional random fields
- map inference
- belief propagation
- probabilistic model
- crf model
- approximate inference
- probabilistic inference
- structured prediction
- random variables
- random fields
- markov networks
- bayesian networks
- belief networks
- graph structure
- knowledge representation
- image segmentation
- maximum entropy
- superpixels
- feature space
- machine learning
- similarity measure
- active contours
- higher order
- image processing