Efficient structured prediction with latent variables for general graphical models

Alexander G. Schwing, Tamir Hazan, Marc Pollefeys, Raquel Urtasun

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

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.

Original languageEnglish (US)
Title of host publicationProceedings of the 29th International Conference on Machine Learning, ICML 2012
Pages959-966
Number of pages8
StatePublished - Oct 10 2012
Externally publishedYes
Event29th International Conference on Machine Learning, ICML 2012 - Edinburgh, United Kingdom
Duration: Jun 26 2012Jul 1 2012

Publication series

NameProceedings of the 29th International Conference on Machine Learning, ICML 2012
Volume1

Other

Other29th International Conference on Machine Learning, ICML 2012
CountryUnited Kingdom
CityEdinburgh
Period6/26/127/1/12

ASJC Scopus subject areas

  • Human-Computer Interaction
  • Education

Fingerprint Dive into the research topics of 'Efficient structured prediction with latent variables for general graphical models'. Together they form a unique fingerprint.

  • Cite this

    Schwing, A. G., Hazan, T., Pollefeys, M., & Urtasun, R. (2012). Efficient structured prediction with latent variables for general graphical models. In Proceedings of the 29th International Conference on Machine Learning, ICML 2012 (pp. 959-966). (Proceedings of the 29th International Conference on Machine Learning, ICML 2012; Vol. 1).