Research map / Graph learning / Graph algorithms and clustering
Adaptively Transforming Graph Matching
Fudong Wang, Nan Xue, Yipeng Zhang, Xiang Bai, Gui-Song Xia
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 outlier removal as pre-processing | GA · PASCAL Cars (with outliers) | accuracy (%): 34.50 -> 61.93 | Improved |
| add outlier removal as pre-processing | SMAC · PASCAL Cars (with outliers) | accuracy (%): 38.53 -> 49.54 | Improved |
| add outlier removal as pre-processing | IPFP-S · PASCAL Cars (with outliers) | accuracy (%): 26.74 -> 65.55 | Improved |
| add outlier removal as pre-processing | MPM · PASCAL Cars (with outliers) | accuracy (%): 58.02 -> 63.44 | Improved |
| add outlier removal as pre-processing | IPFP-S · PASCAL Motorbikes (with outliers) | accuracy (%): 34.90 -> 75.80 | Improved |
| add outlier removal as pre-processing | RRWM · PASCAL Motorbikes (with outliers) | accuracy (%): 65.64 -> 72.61 | Improved |
| add outlier removal as pre-processing | SMAC · PASCAL Motorbikes (with outliers) | accuracy (%): 43.84 -> 52.06 | Improved |
| add convex objective G after minimizing F (ablation) | ATGM · CMU House m=20 n=30, separation 10 | accuracy (%): 59.60 -> 98.25 | Improved |
| add convex objective G after minimizing F (ablation) | ATGM · CMU House m=20 n=30, separation 90 | accuracy (%): 51.39 -> 77.67 | Improved |
| add convex objective G after minimizing F (ablation) | ATGM · CMU House m=25 n=30, separation 90 | accuracy (%): 68.92 -> 89.08 | Improved |
| add convex objective G after minimizing F (ablation) | ATGM · CMU House m=30 n=30, separation 90 | accuracy (%): 99.68 -> 100.00 | Improved |
| increase deformation noise from 0.02 to 0.10 | ATGM · Synthetic, 100 inliers | accuracy (%): 99.10 -> 73.9 | Hurt |
Closest papers by meaning
- Alternating Direction Graph Matching (CVPR 2017 · similarity 0.90)
- Generalizing Graph Matching beyond Quadratic Assignment Model (NeurIPS 2018 · similarity 0.90)
- A Functional Representation for Graph Matching (TPAMI 2019 · similarity 0.90)
- Graph Matching: Relax at Your Own Risk (TPAMI 2016 · similarity 0.89)
- FRAM: Frobenius-Regularized Assignment Matching with Mixed-Precision Computing (NeurIPS 2025 · similarity 0.87)
- Learning Partial Graph Matching via Optimal Partial Transport (ICLR 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.
