Research map / Graph learning / Graph algorithms and clustering
Deep Graph Matching Under Quadratic Constraint
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 quadratic constraint to PCA | PCA · Pascal VOC Keypoints | accuracy (%): 63.8 -> 64.8 | Helped |
| Add quadratic constraint to PCA | PCA · Willow Object Class | accuracy (%): 90.2 -> 92.3 | Helped |
| Add quadratic constraint to GMN | GMN · Pascal VOC Keypoints | accuracy (%): 57.4 -> 58.8 | Helped |
| Add quadratic constraint to GMN | GMN · Willow Object Class | accuracy (%): 76.2 -> 82.5 | Hurt |
| Replace two-layer GCN refinement with two-layer SplineCNN refinement | qc-DGM · Pascal VOC Keypoints | accuracy (%): 69.3 -> 70.3 | Helped |
| Replace two-layer GCN refinement with two-layer SplineCNN refinement | qc-DGM · Willow Object Class | accuracy (%): 96.0 -> 97.7 | Helped |
| Add unary geometric prior to raw CNN attributes (ablation) | qc-DGM1 · Pascal VOC Keypoints | accuracy: 67.8 -> 68.3 | Helped |
| Add pairwise structure context (ablation) | qc-DGM1 · Pascal VOC Keypoints | accuracy: 68.3 -> 68.5 | Helped |
| Add quadratic constrained-optimization (ablation) | qc-DGM1 · Pascal VOC Keypoints | accuracy: 68.5 -> 69.3 | Helped |
| Use false-matching loss instead of cross-entropy-type losses | deep graph matching · Pascal VOC Keypoints | training stability | Helped |
| Use false-matching loss instead of the compared cross-entropy-type losses | deep graph matching · Pascal VOC Keypoints | overfitting | Helped |
| Replace similar graph topology with completely different topology | GMN · Pascal VOC Keypoints and Willow Object Class | accuracy: 57.4 -> 60.0; 76.2 -> 88.4 | Hurt |
Closest papers by meaning
- Deep Learning of Graph Matching (CVPR 2018 · similarity 0.91)
- Learning deep graph matching with channel-independent embedding and Hungarian attention (ICLR 2020 · similarity 0.88)
- Deep Learning of Partial Graph Matching via Differentiable Top-K (CVPR 2023 · similarity 0.88)
- IA-GM: A Deep Bidirectional Learning Method for Graph Matching (AAAI 2021 · similarity 0.88)
- Learning Partial Graph Matching via Optimal Partial Transport (ICLR 2025 · similarity 0.87)
- Discrete Cycle-Consistency Based Unsupervised Deep Graph Matching (AAAI 2024 · 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.