Deep Graph Matching via Blackbox Differentiation of Combinatorial Solvers

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 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.

Cite

Text

Rolínek et al. "Deep Graph Matching via Blackbox Differentiation of Combinatorial Solvers." Proceedings of the European Conference on Computer Vision (ECCV), 2020. doi:10.1007/978-3-030-58604-1_25

Markdown

[Rolínek et al. "Deep Graph Matching via Blackbox Differentiation of Combinatorial Solvers." Proceedings of the European Conference on Computer Vision (ECCV), 2020.](https://mlanthology.org/eccv/2020/rolinek2020eccv-deep/) doi:10.1007/978-3-030-58604-1_25

BibTeX

@inproceedings{rolinek2020eccv-deep,
  title     = {{Deep Graph Matching via Blackbox Differentiation of Combinatorial Solvers}},
  author    = {Rolínek, Michal and Swoboda, Paul and Zietlow, Dominik and Paulus, Anselm and Musil, Vít and Martius, Georg},
  booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
  year      = {2020},
  doi       = {10.1007/978-3-030-58604-1_25},
  url       = {https://mlanthology.org/eccv/2020/rolinek2020eccv-deep/}
}