TY - GEN
T1 - Efficient structured prediction with latent variables for general graphical models
AU - Schwing, Alexander G.
AU - Hazan, Tamir
AU - Pollefeys, Marc
AU - Urtasun, Raquel
PY - 2012
Y1 - 2012
N2 - In this paper we propose a unified framework for structured prediction with latent variables which includes hidden conditional random fields and latent structured support vector machines as special cases. We describe a local entropy approximation for this general formulation using duality, and derive an efficient message passing algorithm that is guaranteed to converge. We demonstrate its effectiveness in the tasks of image segmentation as well as 3D indoor scene understanding from single images, showing that our approach is superior to latent structured support vector machines and hidden conditional random fields.
AB - In this paper we propose a unified framework for structured prediction with latent variables which includes hidden conditional random fields and latent structured support vector machines as special cases. We describe a local entropy approximation for this general formulation using duality, and derive an efficient message passing algorithm that is guaranteed to converge. We demonstrate its effectiveness in the tasks of image segmentation as well as 3D indoor scene understanding from single images, showing that our approach is superior to latent structured support vector machines and hidden conditional random fields.
UR - http://www.scopus.com/inward/record.url?scp=84867113207&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84867113207&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:84867113207
SN - 9781450312851
T3 - Proceedings of the 29th International Conference on Machine Learning, ICML 2012
SP - 959
EP - 966
BT - Proceedings of the 29th International Conference on Machine Learning, ICML 2012
T2 - 29th International Conference on Machine Learning, ICML 2012
Y2 - 26 June 2012 through 1 July 2012
ER -