Abstract

Markov and Conditional random fields ( C R Fs) used in computer vi- sion typically model only local interactions between variables, as this is compu- tationally tractable. In this paper we consider a class of global potentials defined over all variables in the C R F. We show how they can be readily optimised us- ing 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 segmen- tation 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 ob- ject 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 mo- torbike) 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 ap- plication on large images. We find that the new model we propose produces an improvement in the labelling compared to just using a pairwise model.