Abstract 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.


    Access

    Download


    Export, share and cite



    Title :

    Fast Memory-Efficient Generalized Belief Propagation


    Contributors:


    Publication date :

    2006-01-01


    Size :

    13 pages





    Type of media :

    Article/Chapter (Book)


    Type of material :

    Electronic Resource


    Language :

    English




    Fast Memory-Efficient Generalized Belief Propagation

    Kumar, M. P. / Torr, P. H. S. | British Library Conference Proceedings | 2006


    Efficient Belief Propagation for Early Vision

    Felzenszwalb, P. F. / Huttenlocher, D. P. | British Library Online Contents | 2006


    Efficient belief propagation for early vision

    Felzenszwalb, P.F. / Huttenlocher, D.R. | IEEE | 2004


    Efficient Belief Propagation for Early Vision

    Felzenszwalb, P. / Huttenlocher, D. / IEEE Computer Society | British Library Conference Proceedings | 2004


    Nonparametric belief propagation

    Sudderth, E.B. / Ihler, A.T. / Freeman, W.T. et al. | IEEE | 2003