Research map / Graph learning / Graph algorithms and clustering
A Functional Representation for Graph Matching
Fudong Wang, Nan Xue, Yipeng Zhang, Gui-Song Xia, Marcello Pelillo
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 preprocessing (ablation) | GA · PASCAL Cars | average accuracy (%): 34.50 -> 66.14 | Improved |
| add outlier-removal preprocessing (ablation) | GA · PASCAL Motorbikes | average accuracy (%): 45.97 -> 70.60 | Improved |
| add outlier-removal preprocessing (ablation) | PM · PASCAL Cars | average accuracy (%): 37.04 -> 64.21 | Improved |
| add outlier-removal preprocessing (ablation) | PM · PASCAL Motorbikes | average accuracy (%): 43.56 -> 64.26 | Improved |
| add outlier-removal preprocessing (ablation) | SM · PASCAL Cars | average accuracy (%): 38.04 -> 67.72 | Improved |
| add outlier-removal preprocessing (ablation) | SM · PASCAL Motorbikes | average accuracy (%): 47.13 -> 70.75 | Improved |
| use FRGM-E (Euclidean space) instead of FRGM-G | FRGM · Synthetic, 1000 inliers, noise 0.10 | running time (s): 1810.42 -> 191.76 | Improved |
| use FRGM-E instead of FRGM-G | FRGM · Synthetic, 100 inliers, noise 0.10 | average accuracy (%): 72.16 -> 75.76 | Improved |
| increase edge density of k-nn graph from 10% to 100% (ablation) | FRGM-G · 3D face | average accuracy | Improved |
| increase noise sigma from 0.02 to 0.10 (ablation) | FRGM-G · Synthetic, 1000 inliers | average accuracy (%): 88.16 -> 24.23 | Hurt |
| replace FGM-D with FRGM-G | matching baseline · 3D face (25,50) | average accuracy (%): 46.81 -> 76.14 | Improved |
Closest papers by meaning
- Adaptively Transforming Graph Matching (ECCV 2018 · similarity 0.90)
- Factorized Graph Matching (TPAMI 2016 · similarity 0.89)
- A Comparative Study of Graph Matching Algorithms in Computer Vision (ECCV 2022 · similarity 0.88)
- A Continuation Method for Graph Matching Based Feature Correspondence (TPAMI 2019 · similarity 0.87)
- Binary Constraint Preserving Graph Matching (CVPR 2017 · similarity 0.86)
- Multi-Shape Matching with Cycle Consistency Basis via Functional Maps (AAAI 2025 · similarity 0.85)
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.
