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
@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}
}