Research map / Image generation / GANs
A Closer Look at the Optimization Landscapes of Generative Adversarial Networks
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 WGAN-GP instead of NSGAN | GAN trained on MNIST · MNIST | Inception score: 8.97 -> 9.46 | Helped |
| Use WGAN-GP instead of NSGAN | GAN trained on CIFAR10 · CIFAR10 | Inception score: 7.33 -> 7.65 | Helped |
| Replace Adam with ExtraAdam | GAN training on MNIST and CIFAR10 · MNIST and CIFAR10 | Inception score | Helped |
| Use standard gradient descent instead of extragradient | GAN trained on MoG · MoG | gradient norm stability | Hurt |
| Replace discriminator batch normalization with spectral normalization | DCGAN on MNIST · MNIST | training stability | Helped |
Closest papers by meaning
- The Numerics of GANs (NeurIPS 2017 · similarity 0.90)
- Finding Mixed Nash Equilibria of Generative Adversarial Networks (ICML 2019 · similarity 0.90)
- TRAINING GENERATIVE ADVERSARIAL NETWORKS VIA PRIMAL-DUAL SUBGRADIENT METHODS: A LAGRANGIAN PERSPECTIVE ON GAN (ICLR 2018 · similarity 0.89)
- Optimizing the Latent Space of Generative Networks (ICML 2018 · similarity 0.89)
- Many Paths to Equilibrium: GANs Do Not Need to Decrease a Divergence At Every Step (ICLR 2018 · similarity 0.89)
- Generative Multi-Adversarial Networks (ICLR 2017 · similarity 0.89)
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.