Research map / Learning theory and algorithms / Optimal transport
Elastic Optimal Transport: Theory, Application, and Empirical Evaluation
Pei Yang, Yuhang Zhuang, Qi Tan
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 adaptive-mass ELOT instead of fixed-mass partial OT (m-POT) | domain adaptation · VisDA (unsupervised DA) | accuracy: 73.59 -> 76.32 | Improved |
| use ELOT instead of m-POT | domain adaptation · Office-31 (unsupervised DA) | average accuracy: 88.3 -> 90.5 | Improved |
| use ELOT instead of m-POT | domain adaptation · Office-Home (unsupervised DA) | average accuracy: 70.34 -> 71.75 | Improved |
| use ELOT instead of m-POT | partial domain adaptation · Office-Home (partial DA) | average accuracy: 77.98 -> 79.19 | Improved |
| use ELOT instead of ARPM | partial domain adaptation · DomainNet (partial DA) | average accuracy: 68.8 -> 71.4 | Improved |
| use ELOT instead of unbalanced OT (JUMBOT) | domain adaptation · VisDA (unsupervised DA) | accuracy: 72.50 -> 76.32 | Improved |
| use ELOT instead of Kantorovich OT (DeepJDOT) | domain adaptation · VisDA (unsupervised DA) | accuracy: 68.00 -> 76.32 | Improved |
| increase entropy regularization epsilon from 0 to 0.1 (ablation) | ELOT · VisDA | accuracy: 0.7500 -> 0.7639 | Improved |
| increase entropy regularization epsilon from 0 to 0.1 (ablation) | ELOT · VisDA | transported mass: 0.6111 -> 0.7468 | Mixed |
| raise epsilon to 1 (ablation) | ELOT · VisDA | accuracy | Hurt |
Closest papers by meaning
- Scalable Optimal Transport Methods in Machine Learning: A Contemporary Survey (TPAMI 2024 · similarity 0.89)
- Incorporating Importance Weighting in Optimal Transport Based Domain Alignment (ICML 2026 · similarity 0.88)
- Probability-Polarized Optimal Transport for Unsupervised Domain Adaptation (AAAI 2024 · similarity 0.87)
- Generalized Sobolev Transport for Probability Measures on a Graph (ICML 2024 · similarity 0.86)
- Improving Neural Optimal Transport via Displacement Interpolation (ICLR 2025 · similarity 0.86)
- Safe and Sparse Newton Method for Entropic-Regularized Optimal Transport (NeurIPS 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.
