International Journal of Computer Vision

, Volume 103, Issue 2, pp 213–225

Inference Methods for CRFs with Co-occurrence Statistics

  • Ľubor Ladický
  • Chris Russell
  • Pushmeet Kohli
  • Philip H. S. Torr

DOI: 10.1007/s11263-012-0583-y

Cite this article as:
Ladický, Ľ., Russell, C., Kohli, P. et al. Int J Comput Vis (2013) 103: 213. doi:10.1007/s11263-012-0583-y


The Markov and Conditional random fields (CRFs) used in computer vision typically model only local interactions between variables, as this is generally thought to be the only case that is computationally tractable. In this paper we consider a class of global potentials defined over all variables in the CRF. We show how they can be readily optimised using standard graph cut algorithms at little extra expense compared to a standard pairwise field. This result can be directly used for the problem of class based image segmentation which has seen increasing recent interest within computer vision. Here the aim is to assign a label to each pixel of a given image from a set of possible object classes. Typically these methods use random fields to model local interactions between pixels or super-pixels. One of the cues that helps recognition is global object co-occurrence statistics, a measure of which classes (such as chair or motorbike) are likely to occur in the same image together. There have been several approaches proposed to exploit this property, but all of them suffer from different limitations and typically carry a high computational cost, preventing their application on large images. We find that the new model we propose produces a significant improvement in the labelling compared to just using a pairwise model and that this improvement increases as the number of labels increases.


Conditional random fields Object class segmentation Optimization 

Copyright information

© Springer Science+Business Media New York 2012

Authors and Affiliations

  • Ľubor Ladický
    • 1
  • Chris Russell
    • 2
  • Pushmeet Kohli
    • 3
  • Philip H. S. Torr
    • 4
  1. 1.University of OxfordOxfordUK
  2. 2.Queen Mary College, University of LondonLondonUK
  3. 3.Microsoft ResearchCambridgeUK
  4. 4.Oxford Brookes UniversityOxfordUK

Personalised recommendations