Conditional Random Fields Meet Deep Neural Networks for Semantic Segmentation: Combining Probabilistic Graphical Models with Deep Learning for Structured Prediction.
Anurag ArnabShuai ZhengSadeep JayasumanaBernardino Romera-ParedesMåns LarssonAlexander KirillovBogdan SavchynskyyCarsten RotherFredrik KahlPhilip H. S. TorrPublished in: IEEE Signal Process. Mag. (2018)
Keyphrases
- conditional random fields
- probabilistic graphical models
- structured prediction
- graphical models
- markov networks
- superpixels
- exact inference
- probabilistic model
- approximate inference
- parameter learning
- weakly supervised
- hidden markov models
- higher order
- information extraction
- belief propagation
- generative model
- maximum margin
- named entity recognition
- bayesian networks
- markov random field
- random variables
- pairwise
- probabilistic inference
- unsupervised learning
- segmentation method
- machine learning
- semi supervised
- support vector machine
- high dimensional
- image segmentation
- image processing