Parallel and Distributed Graph Cuts by Dual Decomposition
Author
Summary, in English
Graph cuts methods are at the core of many state-of-the-art algorithms in computer vision due to their efficiency in computing globally optimal solutions. In this paper, we solve the maximum flow/minimum cut problem in parallel by splitting the graph into multiple parts and hence, further increase the computational efficacy of graph cuts. Optimality of the solution is guaranteed by dual decomposition, or more specifically, the solutions to the subproblems are constrained to be equal on the overlap with dual variables.
We demonstrate that our approach both allows
(i) faster processing on multi-core computers and
(ii) the capability to handle larger problems by splitting the graph across multiple computers on a distributed network.
Even though our approach does not give a theoretical guarantee of speed-up, an extensive empirical evaluation on several applications with many different data sets consistently shows good performance. An open source C++ implementation of the dual decomposition method is also made publicly available.
We demonstrate that our approach both allows
(i) faster processing on multi-core computers and
(ii) the capability to handle larger problems by splitting the graph across multiple computers on a distributed network.
Even though our approach does not give a theoretical guarantee of speed-up, an extensive empirical evaluation on several applications with many different data sets consistently shows good performance. An open source C++ implementation of the dual decomposition method is also made publicly available.
Department/s
Publishing year
2010
Language
English
Pages
2085-2092
Publication/Series
IEEE Conference on Computer Vision and Pattern Recognition
Full text
Links
Document type
Conference paper
Publisher
IEEE - Institute of Electrical and Electronics Engineers Inc.
Topic
- Computer Vision and Robotics (Autonomous Systems)
- Mathematics
Keywords
- mpi
- supercomputer
- parallel
- graph cuts
Conference name
IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2010
Conference date
2010-06-13 - 2010-06-18
Conference place
San Francisco, United States
Status
Published
Research group
- Mathematical Imaging Group
ISBN/ISSN/Other
- ISSN: 1063-6919
- ISBN: 978-1-4244-6984-0