Fast Approximate Energy Minimization with Label Costs

被引：54

作者：

Delong, Andrew ^{[1
]}

Osokin, Anton ^{[2
]}

Isack, Hossam N. ^{[1
]}

Boykov, Yuri ^{[1
]}

机构：

[1] Univ Western Ontario, Dept Comp Sci, London, ON N6A 3K7, Canada

[2] Moscow MV Lomonosov State Univ, Dept Comp Math & Cybernetics, Moscow 117234, Russia

来源：

2010 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) | 2010年

基金：

加拿大自然科学与工程研究理事会;

关键词：

D O I：

10.1109/CVPR.2010.5539897

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

The alpha-expansion algorithm [4] has had a significant impact in computer vision due to its generality, effectiveness, and speed. Thus far it can only minimize energies that involve unary, pairwise, and specialized higher-order terms. Our main contribution is to extend alpha-expansion so that it can simultaneously optimize "label costs" as well. An energy with label costs can penalize a solution based on the set of labels that appear in it. The simplest special case is to penalize the number of labels in the solution. Our energy is quite general, and we prove optimality bounds for our algorithm. A natural application of label costs is multi-model fitting, and we demonstrate several such applications in vision: homography detection, motion segmentation, and unsupervised image segmentation. Our C++/MATLAB implementation is publicly available.

引用

页码：2173 / 2180

页数：8

共 50 条

[21] Fast Postprocessing for Difficult Discrete Energy Minimization Problems
Akhter, Ijaz
Cheong, Loong Fah
Hartley, Richard
2020 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV), 2020, : 3462 - 3471
[22] Fast Energy Minimization using Learned State Filters
Guillaumin, Matthieu
Van Gool, Luc
Ferrari, Vittorio
2013 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2013, : 1682 - 1689
[23] Consolidation of Hydrophobic Transition Criteria by Using an Approximate Energy Minimization Approach
Patankar, Neelesh A.
LANGMUIR, 2010, 26 (11) : 8941 - 8945
[24] Fast multi-label SVM training based on approximate extreme points
Sun, Zhongwei
Guo, Zhongwen
Liu, Chao
Jiang, Mingxing
Wang, Xi
INTELLIGENT DATA ANALYSIS, 2018, 22 (05) : 1079 - 1099
[25] BDD Minimization for Approximate Computing
Soeken, Mathias
Grosse, Daniel
Chandrasekharan, Arun
Drechsler, Rolf
2016 21ST ASIA AND SOUTH PACIFIC DESIGN AUTOMATION CONFERENCE (ASP-DAC), 2016, : 474 - 479
[26] Approximate BDD Minimization by Weighted A*
Ebendt, Ruediger
Drechsler, Rolf
ISCAS: 2009 IEEE INTERNATIONAL SYMPOSIUM ON CIRCUITS AND SYSTEMS, VOLS 1-5, 2009, : 2974 - +
[27] On Approximate Horn Formula Minimization
Bhattacharya, Amitava
DasGupta, Bhaskar
Mubayi, Dhruv
Turan, Gyoergy
AUTOMATA, LANGUAGES AND PROGRAMMING, PT I, 2010, 6198 : 438 - +
[28] Fast energy-minimization-based imaging and vision techniques
Salerno, E
REAL-TIME IMAGING, 2001, 7 (01) : 1 - 2
[29] On Approximate Minimization of Fuzzy Automata
Belohlavek, R.
Krupka, M.
JOURNAL OF MULTIPLE-VALUED LOGIC AND SOFT COMPUTING, 2009, 15 (2-3) : 125 - 135
[30] Reducing industrial energy costs - Engineering fast paybacks
Richards, FJ
ENERGY & ENVIRONMENTAL VISIONS FOR THE NEW MILLENNIUM, 1998, : 37 - 40

← 1 2 3 4 5 →