Research map / Graph learning / Graph algorithms and clustering
Robust Multi-Object Matching via Iterative Reweighting of the Graph Connection Laplacian
Yunpeng Shi, Shaohan Li, Gilad Lerman
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 |
|---|---|---|---|
| Use IRGCL-P instead of PPM | Permutation synchronization · Willow Car | relative estimation error: 0.11 -> 0.091 | Improved |
| Use IRGCL-S instead of IRLS | Permutation synchronization · Willow Duck | relative estimation error: 0.19 -> 0.19 | No clear effect |
| Use IRGCL-S instead of IRLS | Permutation synchronization · Willow Face | relative estimation error: 0.042 -> 0.039 | Improved |
| Use IRGCL-P instead of PPM | Permutation synchronization · Willow Motorbike | relative estimation error: 0.44 -> 0.33 | Improved |
| Use IRGCL-P instead of MALS | Permutation synchronization · Willow Winebottle | relative estimation error: 0.22 -> 0.21 | Improved |
| Use power iterations instead of spectral WLS (ablation) | IRGCL · Willow datasets | relative estimation error: Car: 0.14 -> 0.091; Duck: 0.19 -> 0.21; Face: 0.039 -> 0.051; Motorbike: 0.42 -> 0.33; Winebottle: 0.22 -> 0.21 | Mixed |
| Use the initial estimate without iterative reweighting (ablation) | IRGCL · Willow datasets | relative estimation error: Car: 0.14 -> 0.091; Duck: 0.19 -> 0.19; Face: 0.039 -> 0.039; Motorbike: 0.41 -> 0.33; Winebottle: 0.22 -> 0.21 | Mixed |
| Use IRGCL-S and IRGCL-P rather than least-squares baselines | Permutation synchronization · Local Biased and Local Adversarial corruption models | matching error | Improved |
| Use standard IRLS-Cauchy reweighting instead of IRGCL | Permutation synchronization · Willow datasets | relative estimation error | Hurt |
Closest papers by meaning
- Multi-Graph Matching via Affinity Optimization with Graduated Consistency Regularization (TPAMI 2016 · similarity 0.88)
- A Convex Relaxation for Multi-Graph Matching (CVPR 2019 · similarity 0.87)
- A Comparative Study of Graph Matching Algorithms in Computer Vision (ECCV 2022 · similarity 0.87)
- HiPPI: Higher-Order Projected Power Iterations for Scalable Multi-Matching (ICCV 2019 · similarity 0.87)
- Multiple Graph Matching and Clustering via Decayed Pairwise Matching Composition (AAAI 2020 · similarity 0.86)
- Learning Partial Graph Matching via Optimal Partial Transport (ICLR 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.
