Alternating Direction Graph Matching - Archive ouverte HAL Access content directly
Conference Papers Year :

Alternating Direction Graph Matching

(1, 2) , (1, 2)
1
2

Abstract

In this paper, we introduce a graph matching method that can account for constraints of arbitrary order, with arbitrary potential functions. Unlike previous decomposition approaches that rely on the graph structures, we introduce a decomposition of the matching constraints. Graph matching is then reformulated as a non-convex non-separable optimization problem that can be split into smaller and much-easier-to-solve subproblems, by means of the alternating direction method of multipliers. The proposed framework is modular, scalable, and can be instantiated into different variants. Two instantiations are studied exploring pairwise and higher-order constraints. Experimental results on widely adopted benchmarks involving synthetic and real examples demonstrate that the proposed solutions outperform existing pairwise graph matching methods, and competitive with the state of the art in higher-order settings.
Fichier principal
Vignette du fichier
adgm_cvpr2017.pdf (1.74 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01580824 , version 1 (02-09-2017)
hal-01580824 , version 2 (23-02-2018)

Identifiers

Cite

Ð.Khuê Lê-Huu, Nikos Paragios. Alternating Direction Graph Matching. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Jul 2017, Honolulu, United States. ⟨10.1109/cvpr.2017.522⟩. ⟨hal-01580824v2⟩
228 View
142 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More