Iteratively Reweighted Graph Cut for Multi-label MRFs with Non-convex Priors.
Thalaiyasingam AjanthanRichard I. HartleyMathieu SalzmannHongdong LiPublished in: CoRR (2014)
Keyphrases
- multi label
- labeling problems
- graph cuts
- markov random field
- convex relaxation
- multi label classification
- globally optimal
- energy minimization
- energy function
- belief propagation
- binary classification
- image annotation
- spatial coherence
- object segmentation
- image segmentation
- shape prior
- max flow
- text categorization
- multiple labels
- segmentation algorithm
- image classification
- potts model
- clique potentials
- maximum a posteriori
- loopy belief propagation
- min cut
- class labels
- higher order
- interactive segmentation
- active learning
- machine learning
- graphical models
- object detection