Research map / Learning theory and algorithms / Optimal transport
Sliced Wasserstein Kernel for Persistence Diagrams
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 the Sliced Wasserstein kernel instead of PWG | Persistence-diagram classification · Orbit | accuracy (%): 77.7±1.2 -> 83.7±0.5 | Helped |
| Use the Sliced Wasserstein kernel instead of PSS | Persistence-diagram classification · Texture | accuracy (%): 98.8± 0.0 -> 96.1±0.4 | Hurt |
| Use the Sliced Wasserstein kernel instead of PSS | Persistence-diagram classification · Human | accuracy (%): 68.5±2.0 -> 74.0±0.2 | Helped |
| Use the Sliced Wasserstein kernel instead of PSS | Persistence-diagram classification · Airplane | accuracy (%): 65.4±2.4 -> 72.6±0.2 | Helped |
| Use the Sliced Wasserstein kernel instead of PWG | Persistence-diagram classification · Ant | accuracy (%): 87.4±0.5 -> 92.3±0.2 | Helped |
| Use the Sliced Wasserstein kernel instead of PWG | Persistence-diagram classification · Bird | accuracy (%): 72.0±1.2 -> 67.0±0.5 | Hurt |
| Use the Sliced Wasserstein kernel instead of PSS | Persistence-diagram classification · FourLeg | accuracy (%): 67.0±2.5 -> 73.0±0.4 | Helped |
| Use the Sliced Wasserstein kernel instead of PWG | Persistence-diagram classification · Octopus | accuracy (%): 78.6±1.3 -> 85.2±0.5 | Helped |
| Use the Sliced Wasserstein kernel instead of PWG | Persistence-diagram classification · Fish | accuracy (%): 79.8±0.5 -> 75.0±0.4 | Hurt |
| Approximate the Sliced Wasserstein kernel with 10 directions | Sliced Wasserstein kernel on 3D shape segmentation · 3D shape segmentation | accuracy | No clear effect |
| Approximate the Sliced Wasserstein kernel with 6 directions | Sliced Wasserstein kernel on Orbit · Orbit | accuracy | No clear effect |
| Approximate the Sliced Wasserstein distance using sampled directions | Sliced Wasserstein kernel on Texture · Texture | accuracy | No clear effect |
Closest papers by meaning
- Persistence Fisher Kernel: A Riemannian Manifold Kernel for Persistence Diagrams (NeurIPS 2018 · similarity 0.93)
- A Class of Topological Pseudodistances for Fast Comparison of Persistence Diagrams (AAAI 2024 · similarity 0.92)
- Wasserstein convergence of Cech persistence diagrams for samplings of submanifolds (NeurIPS 2024 · similarity 0.91)
- PERSISTENCE SPHERES: BI-CONTINUOUS REPRESENTATIONS OF PERSISTENCE DIAGRAMS. (ICLR 2026 · similarity 0.89)
- Statistical and Computational Guarantees of Kernel Max-Sliced Wasserstein Distances (ICML 2025 · similarity 0.85)
- Tree-Sliced Wasserstein Distance: A Geometric Perspective (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.