Alternating Direction Graph Matching

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.
Type de document :
Communication dans un congrès
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Jul 2017, Honolulu, United States
Liste complète des métadonnées

Littérature citée [31 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01580824
Contributeur : D. Khuê Lê-Huu <>
Soumis le : samedi 2 septembre 2017 - 20:34:15
Dernière modification le : mercredi 6 septembre 2017 - 01:08:22

Fichier

adgm_cvpr2017.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01580824, version 1
  • ARXIV : 1611.07583

Collections

Citation

D. Khuê Lê-Huu, Nikos Paragios. Alternating Direction Graph Matching. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Jul 2017, Honolulu, United States. 〈hal-01580824〉

Partager

Métriques

Consultations de
la notice

61

Téléchargements du document

6