Deep Graph Matching via Blackbox Differentiation of Combinatorial Solvers

Code

• github.com/martius-lab/blackbox-deep-graph-matching
  OfficialIn paperpytorch★ 90
• github.com/Thinklab-SJTU/ThinkMatch
  pytorch★ 877
• github.com/martius-lab/blackbox-backprop
  pytorch★ 351
• github.com/LPMP/LPMP
  pytorch★ 67
• github.com/q3erf/topo_bbgm
  pytorch★ 0

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

Tasks

Benchmark Results

Reproductions