Research map / Learning theory and algorithms / Optimal transport
Wasserstein of Wasserstein Loss for Learning Generative Models
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 |
|---|---|---|---|
| Replace L2 gradient penalty with Wasserstein-2 pixel-graph gradient penalty (WWGAN) | WGAN-GP discriminator · CIFAR-10 vertical translation perturbation | normalized total variation and zero-crossings of discriminator output: TV 5.36 -> 4.02; zero-crossings 7.07 -> 0.65 | Helped |
| Replace L2 gradient penalty with Wasserstein-2 pixel-graph gradient penalty (WWGAN) | WGAN-GP training · CelebA training time per epoch | epoch wall-clock time (s): 218.1 s vs 236.9 s | No clear effect |
| Replace L2 gradient penalty with Wasserstein-2 pixel-graph gradient penalty (WWGAN) | WGAN-GP training · CelebA FID | FID | No clear effect |
| Replace L2 gradient penalty with Wasserstein-2 pixel-graph gradient penalty (WWGAN) | WGAN-GP discriminator · CIFAR-10 salt-and-pepper noise robustness | discriminator value stability on noisy images | Helped |
Closest papers by meaning
- Banach Wasserstein GAN (NeurIPS 2018 · similarity 0.93)
- A Two-Step Computation of the Exact GAN Wasserstein Distance (ICML 2018 · similarity 0.92)
- Generative Modeling Using the Sliced Wasserstein Distance (CVPR 2018 · similarity 0.91)
- Learning Wasserstein Embeddings (ICLR 2018 · similarity 0.91)
- Max-Sliced Wasserstein Distance and Its Use for GANs (CVPR 2019 · similarity 0.90)
- A New Robust Partial p-Wasserstein-Based Metric for Comparing Distributions (ICML 2024 · similarity 0.87)
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.