Research map / Graph learning / Graph algorithms and clustering
Zero-Assignment Constraint for Graph Matching With Outliers
Fudong Wang, Nan Xue, Jin-Gang Yu, Gui-Song Xia
Check 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 regularization instead of the explicit cardinality constraint (ablation) | ZAC graph matching · PASCAL | matching accuracy | Improved |
| Use regularization instead of the explicit cardinality constraint (ablation) | ZAC graph matching · PASCAL | running time: 0.18 -> 0.53 (0 outliers); 0.56 -> 1.36 (20 outliers) | Hurt |
| Use zero-assignment-based outlier identification and removal | ZAC and ZACR · PASCAL | precision | Improved |
| Use zero-assignment-based graph matching | ZAC and ZACR · VGG | recall | Improved |
| Use zero-assignment-based graph matching | ZAC and ZACR · Rigid deformable graph matching, 100% outliers | average error: GLS: 0.044; CPD: 0.135; ZAC: 0.006; ZACR: 0.006 | Improved |
| Use zero-assignment-based graph matching | ZAC and ZACR · Non-rigid deformable graph matching, 100% outliers | average error: GLS: 0.092; CPD: 0.083; ZAC: 0.032; ZACR: 0.032 | Improved |
Closest papers by meaning
- Learning With Partial and Noisy Correspondence in Graph Matching (TPAMI 2026 · similarity 0.88)
- A Continuation Method for Graph Matching Based Feature Correspondence (TPAMI 2019 · similarity 0.88)
- A Comparative Study of Graph Matching Algorithms in Computer Vision (ECCV 2022 · similarity 0.87)
- Deep Learning of Partial Graph Matching via Differentiable Top-K (CVPR 2023 · similarity 0.87)
- Revocable Deep Reinforcement Learning with Affinity Regularization for Outlier-Robust Graph Matching (ICLR 2023 · similarity 0.87)
- Robust Graph Matching when Nodes are Corrupt (ICML 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.
