Fast Memory-Efficient Generalized Belief Propagation

Generalized Belief Propagation (gbp) has proven to be a promising technique for performing inference on Markov random fields (mrfs). However, its heavy computational cost and large memory requirements have restricted its application to problems with small state spaces. We present methods for reducing both run time and storage needed by gbp for a large class of pairwise potentials of the mrf. Further, we show how the problem of subgraph matching can be formulated using this class of mrfs and thus, solved efficiently using our approach. Our results significantly outperform the state-of-the-art method. We also obtain excellent results for the related problem of matching pictorial structures for object recognition.

• Type: Conference
• Year: 2006
• Where: ECCV
• Authors: M. Pawan Kumar, Philip H. S. Torr
• Keywords: Computer Vision, ECCV 2006, Heavy Computational Cost, Large Memory Requirements, Markov Random Fields, Small State Spaces, Subgraph Matching