Efficient parallel message computation for MAP inference

Abstract : First order Markov Random Fields (MRFs) have become a predominant tool in Computer Vision over the past decade. Such a success was mostly due to the development of efficient optimization algorithms both in terms of speed as well as in terms of optimality properties. Message passing algorithms are among the most popular methods due to their good performance for a wide range of pairwise potential functions (PPFs). Their main bottleneck is computational complexity. In this paper, we revisit message computation as a distance transformation using a more formal setting than [8] to generalize it to arbitrary PPFs. The method is based on [20] yielding accurate results for a specific class of PPFs and in most other cases a close approximation. The proposed algorithm is parallel and thus enables us to fully take advantage of the computational power of parallel processing architectures. The proposed scheme coupled with an efficient belief propagation algorithm [8] and implemented on a massively parallel coprocessor provides results as accurate as state of the art inference methods, though is in general one order of magnitude faster in terms of speed.
Type de document :
Communication dans un congrès
International Conference on Computer Vision, Nov 2011, Barcelone, Spain. pp.1379 - 1386, 2011
Liste complète des métadonnées

Littérature citée [25 références]  Voir  Masquer  Télécharger

Contributeur : Stavros Alchatzidis <>
Soumis le : jeudi 5 septembre 2013 - 13:06:14
Dernière modification le : jeudi 7 février 2019 - 17:29:11
Document(s) archivé(s) le : vendredi 6 décembre 2013 - 04:19:25


Fichiers produits par l'(les) auteur(s)


  • HAL Id : hal-00858394, version 1



Stavros Alchatzidis, Aristeidis Sotiras, Nikos Paragios. Efficient parallel message computation for MAP inference. International Conference on Computer Vision, Nov 2011, Barcelone, Spain. pp.1379 - 1386, 2011. 〈hal-00858394〉



Consultations de la notice


Téléchargements de fichiers