Sciweavers

Share
CVPR
2011
IEEE

Learning Message-Passing Inference Machines for Structured Prediction

8 years 6 months ago
Learning Message-Passing Inference Machines for Structured Prediction
Nearly every structured prediction problem in computer vision requires approximate inference due to large and complex dependencies among output labels. While graphical models provide a clean separation between modeling and inference, learning these models with approximate inference is not well understood. Furthermore, even if a good model is learned, predictions are often inaccurate due to approximations. In this work, instead of performing inference over a graphical model, we instead consider the inference procedure as a composition of predictors. Specifically, we focus on message-passing algorithms, such as Belief Propagation, and show how they can be viewed as procedures that sequentially predict label distributions at each node over a graph. Given labeled graphs, we can then train the sequence of predictors to output the correct labelings. The result no longer corresponds to a graphical model but simply defines an inference procedure, with strong theoretical properties, that can ...
Stephane Ross, Daniel Munoz, J. Andrew Bagnell
Added 08 Apr 2011
Updated 29 Apr 2011
Type Journal
Year 2011
Where CVPR
Authors Stephane Ross, Daniel Munoz, J. Andrew Bagnell
Comments (0)
books