Research map / Image generation / GANs
Generalization and Equilibrium in Generative Adversarial Nets (GANs)
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 |
|---|---|---|---|
| Add a 5-component mixture to DCGAN | DCGAN · CIFAR-10 | Inception Score: 7.16$\pm$0.10 -> 7.72$\pm$0.09 | Helped |
| Add a 5-component mixture to Wasserstein GAN | Wasserstein GAN · CIFAR-10 | Inception Score: 3.82$\pm$0.06 -> 4.04$\pm$0.07 | Helped |
| Use a 5-component mixture instead of a 5x-size single DCGAN | DCGAN · CIFAR-10 | Inception Score: 7.34$\pm$0.07 -> 7.72$\pm$0.09 | Helped |
| Apply mixtures to the upper and bottom S-GAN generators separately | S-GAN · CIFAR-10 | Inception Score | Hurt |
| Use a mixture of generators and discriminators | DCGAN · CIFAR-10 training | Inception Score | Helped |
| Use a mixture of generators and discriminators | Wasserstein GAN · CIFAR-10 training | Wasserstein objective | Mixed |
Closest papers by meaning
- Do GANs always have Nash equilibria? (ICML 2020 · similarity 0.89)
- Improving Generalization and Stability of Generative Adversarial Networks (ICLR 2019 · similarity 0.89)
- On the Discrimination-Generalization Tradeoff in GANs (ICLR 2018 · similarity 0.89)
- Many Paths to Equilibrium: GANs Do Not Need to Decrease a Divergence At Every Step (ICLR 2018 · similarity 0.89)
- Finding Mixed Nash Equilibria of Generative Adversarial Networks (ICML 2019 · similarity 0.88)
- The Numerics of GANs (NeurIPS 2017 · similarity 0.88)
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.