Efficient parallel message computation for MAP inferenceReport as inadecuate

Efficient parallel message computation for MAP inference - Download this document for free, or read online. Document in PDF available to download.

1 GALEN - Organ Modeling through Extraction, Representation and Understanding of Medical Image Content Inria Saclay - Ile de France, Ecole Centrale Paris 2 CVN - Centre de vision numérique

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.

Author: Stavros Alchatzidis - Aristeidis Sotiras - Nikos Paragios -

Source: https://hal.archives-ouvertes.fr/


Related documents