Research map / Graph learning / Graph algorithms and clustering
A Comparative Study of Graph Matching Algorithms in Computer Vision
Stefan Haller, Lorenz Feineis, Lisa Hutschenreiter, Florian Bernard, Carsten Rother, Dagmar Kainmüller, Paul Swoboda, Bogdan Savchynskyy
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| combine a primal heuristic with a dual optimizer (FM-BCA vs FM alone) with larger allowed performance ratio | FM-BCA · Graph matching fixed-target (451 instances) | solution quality vs run time: performance ratio factor of 3.7 | Improved |
| add dual BCA updates to FW and LAP primal heuristics (ablation) | MP-FW and MP-LAP heuristics · Graph matching fixed-time evaluation | objective value | Improved |
| use tighter relaxations (dd-ls3/4 instead of dd-ls0) on short time budgets | dd-ls0 · Graph matching small problems (1s) | objective value | Hurt |
| use sparse instead of dense pairwise costs (house-sparse vs house-dense) | primal heuristics · house-dense vs house-sparse (1s) | objective value | Improved |
Closest papers by meaning
- A Convex Relaxation for Multi-Graph Matching (CVPR 2019 · similarity 0.90)
- Path Following with Adaptive Path Estimation for Graph Matching (AAAI 2016 · similarity 0.90)
- A Study of Lagrangean Decompositions and Dual Ascent Solvers for Graph Matching (CVPR 2017 · similarity 0.90)
- Towards Optimizing Large-Scale Multi-Graph Matching in Bioimaging (CVPR 2025 · similarity 0.89)
- Learning Partial Graph Matching via Optimal Partial Transport (ICLR 2025 · similarity 0.87)
- Multi-Shape Matching with Cycle Consistency Basis via Functional Maps (AAAI 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
