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.
Document type :
Conference papers
Complete list of metadatas

Cited literature [32 references]  Display  Hide  Download

https://hal.inria.fr/hal-01580824
Contributor : D. Khuê Lê-Huu <>
Submitted on : Friday, February 23, 2018 - 5:01:02 PM
Last modification on : Thursday, February 7, 2019 - 5:29:18 PM
Long-term archiving on : Friday, May 25, 2018 - 11:59:00 AM

File

adgm_cvpr2017.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01580824, version 2
  • ARXIV : 1611.07583

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-01580824v2⟩

Share

Metrics

Record views

175

Files downloads

196