A Study of Lagrangean Decompositions and Dual Ascent Solvers for Graph Matching

Paul Swoboda, Carsten Rother, Hassan Abu Alhaija, Dagmar Kainmuller, Bogdan Savchynskyy; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, pp. 1607-1616

Abstract


We study the quadratic assignment problem, in computer vision also known as graph matching. Two leading solvers for this problem optimize the Lagrange decomposition duals with sub-gradient and dual ascent (also known as message passing) updates. We explore this direction further and propose several additional Lagrangean relaxations of the graph matching problem along with corresponding algorithms, which are all based on a common dual ascent framework. Our extensive empirical evaluation gives several theoretical insights and suggests a new state-of-the-art anytime solver for the considered problem. Our improvement over state-of-the-art is particularly visible on a new dataset with large-scale sparse problem instances containing more than 500 graph nodes each.

Related Material


[pdf] [Supp] [arXiv]
[bibtex]
@InProceedings{Swoboda_2017_CVPR,
author = {Swoboda, Paul and Rother, Carsten and Abu Alhaija, Hassan and Kainmuller, Dagmar and Savchynskyy, Bogdan},
title = {A Study of Lagrangean Decompositions and Dual Ascent Solvers for Graph Matching},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {July},
year = {2017}
}