Research map / Image generation / GANs
Parallel Optimal Transport GAN
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 |
|---|---|---|---|
| Add latent-space optimal-transport regularization to WGAN-GP | WGAN-GP · CIFAR-10 | Inception Score: 6.58±0.06 -> 6.87±0.04 | Helped |
| Add latent-space optimal-transport regularization to WGAN-GP | WGAN-GP · Oxford Flowers | Inception Score: 3.42±0.04 -> 3.53±0.03 | Helped |
| Add latent-space optimal-transport regularization to WGAN-GP | WGAN-GP · CUB Birds | Inception Score: 4.51±0.04 -> 4.78±0.04 | Helped |
| Add latent-space optimal-transport regularization to WGAN-GP | WGAN-GP · CIFAR-10 | FID: 34.4 -> 32.5 | Helped |
| Add latent-space optimal-transport regularization to WGAN-GP | WGAN-GP · Oxford Flowers | FID: 98.7 -> 65.7 | Helped |
| Add latent-space optimal-transport regularization to WGAN-GP | WGAN-GP · CUB Birds | FID: 70.4 -> 58.6 | Helped |
| Add latent-space optimal-transport regularization | WGAN-GP · 8 Gaussian Ring (2D) | Reverse-KL divergence: 0.0046±0.0004 -> 0.0020±0.0002 | Helped |
| Add latent-space optimal-transport regularization | WGAN-GP · Gaussian Ball (3D) | Reverse-KL divergence: 0.9438±0.0044 -> 0.7428±0.0038 | Helped |
Closest papers by meaning
- On the Convergence and Robustness of Training GANs with Regularized Optimal Transport (NeurIPS 2018 · similarity 0.93)
- Improving GANs Using Optimal Transport (ICLR 2018 · similarity 0.93)
- Projected GANs Converge Faster (NeurIPS 2021 · similarity 0.90)
- A Large-Scale Study on Regularization and Normalization in GANs (ICML 2019 · similarity 0.90)
- MS$^3$D: A RG Flow-Based Regularization for GAN Training with Limited Data (ICML 2024 · similarity 0.90)
- Discriminator optimal transport (NeurIPS 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.