English

Deep Graph Matching via Blackbox Differentiation of Combinatorial Solvers

Machine Learning 2024-12-16 v2 Machine Learning

Abstract

Building on recent progress at the intersection of combinatorial optimization and deep learning, we propose an end-to-end trainable architecture for deep graph matching that contains unmodified combinatorial solvers. Using the presence of heavily optimized combinatorial solvers together with some improvements in architecture design, we advance state-of-the-art on deep graph matching benchmarks for keypoint correspondence. In addition, we highlight the conceptual advantages of incorporating solvers into deep learning architectures, such as the possibility of post-processing with a strong multi-graph matching solver or the indifference to changes in the training setting. Finally, we propose two new challenging experimental setups. The code is available at https://github.com/martius-lab/blackbox-deep-graph-matching

Keywords

Cite

@article{arxiv.2003.11657,
  title  = {Deep Graph Matching via Blackbox Differentiation of Combinatorial Solvers},
  author = {Michal Rolínek and Paul Swoboda and Dominik Zietlow and Anselm Paulus and Vít Musil and Georg Martius},
  journal= {arXiv preprint arXiv:2003.11657},
  year   = {2024}
}

Comments

ECCV 2020 conference paper

R2 v1 2026-06-23T14:27:29.599Z