Research map / Graph learning / Graph algorithms and clustering
Determinant Regularization for Gradient-Efficient Graph Matching
Tianshu Yu, Junchi Yan, Baoxin Li
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 determinant regularization in the continuous matching objective | DetGM · Caltech-101 natural images | accuracy (%): 76.69 -> 77.44 | Improved |
| Use determinant regularization for gradient-based continuation | DetGM · Synthetic graph matching: deformation, outliers, and edge density | accuracy | Improved |
| Use the spectral increment sub-gradient instead of the geometric sub-gradient (ablation) | DetGM · CMU house | accuracy | No clear effect |
| Use the geometric sub-gradient instead of the spectral increment sub-gradient (ablation) | DetGM · Synthetic graph matching | accuracy | No clear effect |
| Use determinant-based continuous optimization rather than BPF | DetGM · Pascal dataset | running time: over 2,000 seconds vs around 60 seconds | Improved |
Closest papers by meaning
- Multi-Graph Matching via Affinity Optimization with Graduated Consistency Regularization (TPAMI 2016 · similarity 0.90)
- Graph Matching: Relax at Your Own Risk (TPAMI 2016 · similarity 0.88)
- Learning Partial Graph Matching via Optimal Partial Transport (ICLR 2025 · similarity 0.87)
- FRAM: Frobenius-Regularized Assignment Matching with Mixed-Precision Computing (NeurIPS 2025 · similarity 0.86)
- Bipartite Matching in Massive Graphs: A Tight Analysis of EDCS (ICML 2024 · similarity 0.86)
- 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.
