2012
DOI: 10.1007/978-3-642-33715-4_2
|View full text |Cite
|
Sign up to set email alerts
|

Generic Cuts: An Efficient Algorithm for Optimal Inference in Higher Order MRF-MAP

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1

Citation Types

0
36
0

Year Published

2013
2013
2016
2016

Publication Types

Select...
4
2
1

Relationship

0
7

Authors

Journals

citations
Cited by 14 publications
(36 citation statements)
references
References 19 publications
0
36
0
Order By: Relevance
“…The primal-dual technique of [2] can exactly minimize any binary (two-label) function with n variables and k-th order submodular potentials in O(2 k n 3 ). While this is better than the most general case, it is still exponential in k. Ramalingam et al [23] present a technique to transform certain submodular multi-label functions into binary submodular pairwise functions which can then be minimized exactly using graph-cuts.…”
Section: Related Workmentioning
confidence: 99%
See 2 more Smart Citations
“…The primal-dual technique of [2] can exactly minimize any binary (two-label) function with n variables and k-th order submodular potentials in O(2 k n 3 ). While this is better than the most general case, it is still exponential in k. Ramalingam et al [23] present a technique to transform certain submodular multi-label functions into binary submodular pairwise functions which can then be minimized exactly using graph-cuts.…”
Section: Related Workmentioning
confidence: 99%
“…A very popular such class are pairwise functions, involving only terms depending either on one or two variables [6,15,16]. The optimization of higher-order functions is still an open, highly challenging problem [2,17,19,23,26,34].…”
Section: Introductionmentioning
confidence: 99%
See 1 more Smart Citation
“…Although their importance was long understood and there were earlier attempts on utilizing them [5,18,21], their use [9,27] and research into minimization of various classes of higherorder MRF energies [1,6,8,11,12,17,20,24,25,26] have intensified significantly in the past few years. While there are useful higher-order MRF energies with specific forms that can be efficiently minimized [15,16], minimization of general higher-order energy is needed to utilize sophisticated priors, especially if it is learned from data as in the case of Fields of Experts (FoEs) [23].…”
Section: Introductionmentioning
confidence: 99%
“…,Zeng et al [2011],Komodakis and Paragios [2012],Kumar and Koller [2010],Torresani et al [2013],Batra et al [2012],Strandmark et al [2011], Vicente et al [2009], Pock et al [2009], Woodford et al [2009], Hane et al [2013], Glocker et al [2008a], Khandelwal et al [2016], Wang et al [2009], Besbes et al [2009], Glocker et al [2008b], Wang et al [2010], Zhou and Komodakis [2014], Conejo et al [2014], Spyropoulos et al [2014], Heibel et al [2009], Vakalopoulou et al [2015], Glocker et al [2011], Pock et al [2008], Fix et al [2014],Arora et al [2012].…”
mentioning
confidence: 99%