Research map / Label-efficient and robust learning / Domain adaptation and generalization
Regularized Wasserstein Means for Aligning Distributional Data
Liang Mi, Wen Zhang, Yalin Wang
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 |
|---|---|---|---|
| Add class-label triplet regularization to Wasserstein mean updates | Wasserstein means for Office-31 W → A with Decaf-fc6 · Office-31 W → A, Decaf-fc6 | classification accuracy (%): 33.9±2.1 -> 36.4±2.7 | Improved |
| Add class-label triplet regularization to Wasserstein mean updates | Wasserstein means for Office-31 W → A with Decaf-fc7 · Office-31 W → A, Decaf-fc7 | classification accuracy (%): 35.8±1.5 -> 43.2±2.6 | Improved |
| Use class-label triplet regularization rather than unregularized Wasserstein means | Wasserstein means for Office-31 W → A with Decaf-fc6 · Office-31 W → A, Decaf-fc6 | classification accuracy (%): 32.7±2.3 -> 36.4±2.7 | Improved |
| Use class-label triplet regularization rather than unregularized Wasserstein means | Wasserstein means for Office-31 W → A with Decaf-fc7 · Office-31 W → A, Decaf-fc7 | classification accuracy (%): 34.6±2.2 -> 43.2±2.6 | Improved |
| Add a rigid-transformation prior to Wasserstein mean updates | RWM for two-moons point-set registration · Two moons, rotated domains | transformation recovery | Mixed |
| Add topology, length, and curvature regularization to Wasserstein means | RWM for skeleton layout · Human shape point cloud | topology preservation | Improved |
| Use OT-based correspondences instead of nearest-neighbor correspondences | RWM for point-set registration · Stanford Bunny point sets | transformation recovery | Improved |
Closest papers by meaning
- Fast Alignment of Embeddings: Computational Guarantees for Anisotropic Procrustes-Wasserstein (NeurIPS 2026 · similarity 0.86)
- The Wasserstein Transform (ICML 2019 · similarity 0.86)
- Slicing Wasserstein over Wasserstein via Functional Optimal Transport (ICLR 2026 · similarity 0.86)
- Fourier Sliced-Wasserstein Embedding for Multisets and Measures (ICLR 2025 · similarity 0.85)
- Aligning Embeddings and Geometric Random Graphs: Informational Results and Computational Approaches for the Procrustes-Wasserstein Problem (NeurIPS 2024 · similarity 0.85)
- Joint Metric Space Embedding by Unbalanced Optimal Transport with Gromov–Wasserstein Marginal Penalization (ICML 2025 · similarity 0.84)
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.
