Research map / Graph learning / Graph algorithms and clustering
Proxy Graph Matching with Proximal Matching Networks
Hao-Ru Tan, Chuang Wang, Si-Tong Wu, Tie-Qiang Wang, Xu-Yao Zhang, Cheng-Lin Liu
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 DPGM to DGFL (ablation) | DGFL · PASCAL-PF, original coordinates | matching accuracy (%): 88.5 -> 93.5 | Improved |
| Add DPGM to DGFL (ablation) | DGFL · PASCAL-PF, rotated coordinates | matching accuracy (%): 69.9 -> 70.6 | No clear effect |
| Add GRCM to DGFL (ablation) | DGFL · PASCAL-PF, original coordinates | matching accuracy (%): 88.5 -> 80.7 | Hurt |
| Add GRCM to DGFL (ablation) | DGFL · PASCAL-PF, rotated coordinates | matching accuracy (%): 69.9 -> 80.6 | Improved |
| Add DPGM and GRCM to DGFL (ablation) | DGFL · PASCAL-PF, original coordinates | matching accuracy (%): 88.5 -> 90.6 | Improved |
| Add DPGM and GRCM to DGFL (ablation) | DGFL · PASCAL-PF, rotated coordinates | matching accuracy (%): 69.9 -> 90.0 | Improved |
| Use the full method rather than DGMC | PASCAL-PF · PASCAL-PF, original coordinates | matching accuracy (%): 95.7 vs. 90.6 | Hurt |
| Use the full method rather than DGMC | PASCAL-PF · PASCAL-PF, rotated coordinates | matching accuracy (%): 24.5 -> 90.0 | Improved |
Closest papers by meaning
- Ensemble Quadratic Assignment Network for Graph Matching (IJCV 2024 · similarity 0.89)
- Stochastic Iterative Graph Matching (ICML 2021 · similarity 0.89)
- Combinatorial Learning of Robust Deep Graph Matching: An Embedding Based Approach (TPAMI 2020 · similarity 0.88)
- Deep Graphical Feature Learning for the Feature Matching Problem (ICCV 2019 · similarity 0.88)
- FC-GNN: Recovering Reliable and Accurate Correspondences from Interferences (CVPR 2024 · similarity 0.86)
- SG-PGM: Partial Graph Matching Network with Semantic Geometric Fusion for 3D Scene Graph Alignment and Its Downstream Tasks (CVPR 2024 · 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.
