Research map / Graph learning / Graph algorithms and clustering
Fusion Moves for Graph Matching
Lisa Hutschenreiter, Stefan Haller, Lorenz Feineis, Carsten Rother, Dagmar Kainmüller, 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 |
|---|---|---|---|
| add qpbo-i fusion (ablation) | dd-ls0 · worms | average best energy: -43824.08 -> -48347.09 | Improved |
| add qpbo-i fusion (ablation) | dd-ls0 · pairs | average best energy: -63453.77 -> -65936.89 | Improved |
| add qpbo-i fusion (ablation) | bca-greedy · pairs | average best energy: -62696.28 -> -66005.55 | Improved |
| add qpbo-i fusion (ablation) | bca-greedy · worms | average best energy: -48454.89 -> -48465.28 | Improved |
| add qpbo-i fusion (ablation) | bca-greedy · worms | instances solved to optimality: 9 -> 27 | Improved |
| add qpbo-i fusion (ablation) | dd-ls0 · worms | time to best (s): 492.00 -> 428.79 | Improved |
| add qpbo-i fusion (ablation) | dd-ls0 · opengm | average best energy: 31.42 -> 26.18 | Improved |
| fusion generally (ablation) | all proposal generators · 8 datasets | energy and time | Improved |
| use greedy heuristic instead of LAP for BCA primal proposals (ablation) | bca · pairs | fused solution energy | Improved |
| use approximate qpbo-i instead of exact ILP for fusion (ablation) | fusion · datasets | runtime: 10--50 times faster | Improved |
| tighten relaxation (dd-ls3, dd-ls4 vs dd-ls0) (ablation) | dual subgradient with fusion · datasets | final energy | No clear effect |
| bca-lap proposals with fusion vs dd-ls0 proposals with fusion (ablation) | fusion · exemplary instances | fused energy | No clear effect |
Closest papers by meaning
- A Convex Relaxation for Multi-Graph Matching (CVPR 2019 · similarity 0.89)
- Incremental Multi-graph Matching via Diversity and Randomness based Graph Clustering (ECCV 2018 · similarity 0.89)
- A Comparative Study of Graph Matching Algorithms in Computer Vision (ECCV 2022 · similarity 0.89)
- Towards Optimizing Large-Scale Multi-Graph Matching in Bioimaging (CVPR 2025 · similarity 0.87)
- Learning Partial Graph Matching via Optimal Partial Transport (ICLR 2025 · similarity 0.86)
- FRAM: Frobenius-Regularized Assignment Matching with Mixed-Precision Computing (NeurIPS 2025 · similarity 0.86)
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.
