Research map / Label-efficient and robust learning / Self-supervised and contrastive
Self-Supervised Bidirectional Learning for Graph Matching
Read the paperCheck 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 |
|---|---|---|---|
| Use IA-SSGM instead of the strongest reported baseline | Graph matching · PASCALVOC OUTLIER | matching accuracy (%): 41.7 -> 62.8 | Helped |
| Use IA-SSGM instead of the strongest reported baseline | Graph matching · CUB2011 OUTLIER | matching accuracy (%): 70.8 -> 85.6 | Helped |
| Use IA-SSGM instead of the strongest reported baseline | Graph matching · IMC-PT-SPARSEGM OUTLIER | matching accuracy (%): 67.9 -> 69.0 | Helped |
| Add GCL loss to matching-loss-only training (ablation) | IA-SSGM · PASCALVOC INLIER | matching accuracy (%): 60.9 -> 61.1 | Helped |
| Add GCL loss to matching-loss-only training (ablation) | IA-SSGM · CUB2011 OUTLIER | matching accuracy (%): 64.5 -> 76.5 | Helped |
| Add consistency loss to matching-loss-only training (ablation) | IA-SSGM · PASCALVOC INLIER | matching accuracy (%): 60.9 -> 62.7 | Helped |
| Add consistency loss to matching-loss-only training (ablation) | IA-SSGM · CUB2011 OUTLIER | matching accuracy (%): 64.5 -> 56.2 | Hurt |
| Add consistency loss and GCL loss together (ablation) | IA-SSGM · PASCALVOC OUTLIER | matching accuracy (%): 59.4 -> 62.8 | Helped |
| Add consistency loss and GCL loss together (ablation) | IA-SSGM · IMC-PT-SPARSEGM OUTLIER | matching accuracy (%): 51.5 -> 69.0 | Helped |
Closest papers by meaning
- IA-GM: A Deep Bidirectional Learning Method for Graph Matching (AAAI 2021 · similarity 0.94)
- Deep Learning of Partial Graph Matching via Differentiable Top-K (CVPR 2023 · similarity 0.88)
- Learning Partial Graph Matching via Optimal Partial Transport (ICLR 2025 · similarity 0.87)
- Revocable Deep Reinforcement Learning with Affinity Regularization for Outlier-Robust Graph Matching (ICLR 2023 · similarity 0.87)
- Discrete Cycle-Consistency Based Unsupervised Deep Graph Matching (AAAI 2024 · similarity 0.87)
- M3C: A Framework towards Convergent, Flexible, and Unsupervised Learning of Mixture Graph Matching and Clustering (ICLR 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.