Message passing inference for large scale graphical models with high order potentials

Jian Zhang, Alexander G. Schwing, Raquel Urtasun

Research output: Contribution to journalConference articlepeer-review


To keep up with the Big Data challenge, parallelized algorithms based on dual decomposition have been proposed to perform inference in Markov random fields. Despite this parallelization, current algorithms struggle when the energy has high order terms and the graph is densely connected. In this paper we propose a partitioning strategy followed by a message passing algorithm which is able to exploit pre-computations. It only updates the high-order factors when passing messages across machines. We demonstrate the effectiveness of our approach on the task of joint layout and semantic segmentation estimation from single images, and show that our approach is orders of magnitude faster than current methods.

Original languageEnglish (US)
Pages (from-to)1134-1142
Number of pages9
JournalAdvances in Neural Information Processing Systems
Issue numberJanuary
StatePublished - Jan 1 2014
Externally publishedYes
Event28th Annual Conference on Neural Information Processing Systems 2014, NIPS 2014 - Montreal, Canada
Duration: Dec 8 2014Dec 13 2014

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Information Systems
  • Signal Processing

Fingerprint Dive into the research topics of 'Message passing inference for large scale graphical models with high order potentials'. Together they form a unique fingerprint.

Cite this