Back to Search
Start Over
Memory Efficient Max Flow for Multi-Label Submodular MRFs.
- Source :
-
IEEE Transactions on Pattern Analysis & Machine Intelligence . Apr2019, Vol. 41 Issue 4, p886-900. 15p. - Publication Year :
- 2019
-
Abstract
- Multi-label submodular Markov Random Fields (MRFs) have been shown to be solvable using max-flow based on an encoding of the labels proposed by Ishikawa, in which each variable $X_i$ is represented by $\ell$ nodes (where $\ell$ is the number of labels) arranged in a column. However, this method in general requires $2\;\ell ^2$ edges for each pair of neighbouring variables. This makes it inapplicable to realistic problems with many variables and labels, due to excessive memory requirement. In this paper, we introduce a variant of the max-flow algorithm that requires much less storage. Consequently, our algorithm makes it possible to optimally solve multi-label submodular problems involving large numbers of variables and labels on a standard computer. [ABSTRACT FROM AUTHOR]
- Subjects :
- *MEMORY
*SUBMODULAR functions
*MATROIDS
*ENCODING
*MODULATION coding
Subjects
Details
- Language :
- English
- ISSN :
- 01628828
- Volume :
- 41
- Issue :
- 4
- Database :
- Academic Search Index
- Journal :
- IEEE Transactions on Pattern Analysis & Machine Intelligence
- Publication Type :
- Academic Journal
- Accession number :
- 135140485
- Full Text :
- https://doi.org/10.1109/TPAMI.2018.2819675