Header logo is

Deep Graph Matching via Blackbox Differentiation of Combinatorial Solvers


Conference Paper


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.

Author(s): Michal Rolinek and Paul Swoboda and Dominik Zietlow and Anselm Paulus and Vit Musil and Georg Martius
Book Title: Computer Vision – ECCV 2020
Year: 2020
Month: August
Publisher: Springer International Publishing

Department(s): Autonomous Learning
Bibtex Type: Conference Paper (inproceedings)
Paper Type: Conference

Event Place: Glasgow, UK

Address: Cham
Eprint: https://arxiv.org/abs/2003.11657

Links: Code


  title = {Deep Graph Matching via Blackbox Differentiation of Combinatorial Solvers},
  author = {Rolinek, Michal and Swoboda, Paul and Zietlow, Dominik and Paulus, Anselm and Musil, Vit and Martius, Georg},
  booktitle = {Computer Vision -- ECCV 2020},
  publisher = {Springer International Publishing},
  address = {Cham},
  month = aug,
  year = {2020},
  eprint = {https://arxiv.org/abs/2003.11657},
  month_numeric = {8}