Research map / Learning theory and algorithms / Optimal transport
Max-Sliced Wasserstein Distance and Its Use for GANs
Check 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 |
|---|---|---|---|
| Replace the baseline GAN objective with max-sliced Wasserstein distance, using nearest-neighbor retrieval | Unsupervised word translation · MUSE language pairs | P@1: 79.1 -> 79.6 (en-es); 69.6 -> 69.6 (de-en) | Helped |
| Replace the baseline GAN objective with max-sliced Wasserstein distance, using CSLS retrieval | Unsupervised word translation · MUSE language pairs | P@1: 81.7 -> 82.0 (en-es); 31.4 -> 31.9 (zh-en) | Helped |
| Use one max-selected projection direction instead of randomly sampled sliced-Wasserstein projections | GAN image generation · CelebA-HQ and LSUN Bedrooms, 256x256 | qualitative sample quality | Helped |
Closest papers by meaning
- Generative Modeling Using the Sliced Wasserstein Distance (CVPR 2018 · similarity 0.94)
- A Two-Step Computation of the Exact GAN Wasserstein Distance (ICML 2018 · similarity 0.92)
- Sliced Wasserstein Generative Models (CVPR 2019 · similarity 0.91)
- Banach Wasserstein GAN (NeurIPS 2018 · similarity 0.90)
- On the Convergence and Robustness of Training GANs with Regularized Optimal Transport (NeurIPS 2018 · similarity 0.90)
- Wasserstein of Wasserstein Loss for Learning Generative Models (ICML 2019 · similarity 0.90)
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.