Blending learning and inference in conditional random fields

MaRDI QIDQ2958602zbMATH OpenFDO

Authors Tamir Hazan, Alexander Schwing, Raquel Urtasun

Publication date 3 February 2017

Full work available at URL http://jmlr.csail.mit.edu/papers/v17/13-260.html

Mathematics Subject Classification ID

Random fields; image analysis (62M40) Learning and adaptive systems in artificial intelligence (68T05) Machine vision and scene understanding (68T45)

Recommendations

• On learning conditional random fields for stereo
• An introduction to conditional random fields
• Conditional random fields for image labeling
• Margin losses for training conditional random fields
• Inference methods for CRFs with co-occurrence statistics

Cites work

• A New Class of Upper Bounds on the Log Partition Function
• Constructing Free-Energy Approximations and Generalized Belief Propagation Algorithms
• Convex Analysis
• Convexity arguments for efficient minimization of the Bethe and Kikuchi free energies
• Estimating the ``wrong graphical model: benefits in the computation-limited setting
• Graphical models, exponential families, and variational inference
• scientific article; zbMATH DE number 1134987 (Why is no real title available?)
• Inexact coordinate descent: complexity and preconditioning
• Introductory lectures on convex optimization. A basic course.
• Large margin methods for structured and interdependent output variables
• Learning to reason
• Norm-Product Belief Propagation: Primal-Dual Message-Passing for Approximate Inference
• Recovering occlusion boundaries from an image
• Relaxation methods for problems with strictly convex separable costs and linear constraints

Cited in

(3)

• On learning conditional random fields for stereo
• A Comparison Study of Conditional Random Fields Toolkits
• Margin losses for training conditional random fields

This page was built for publication: Blending learning and inference in conditional random fields

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2958602)