Header logo is

Deep Graph Matching via Blackbox Differentiation of Combinatorial Solvers



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 Vít Musil and Georg Martius
Journal: Arxiv

Department(s): Autonomous Learning
Bibtex Type: Article (article)

Links: Arxiv


  title = {Deep Graph Matching via Blackbox Differentiation of Combinatorial Solvers},
  author = {Rolinek, Michal and Swoboda, Paul and Zietlow, Dominik and Paulus, Anselm and Musil, Vít and Martius, Georg},
  journal = {Arxiv}