Research map / Image generation / GANs
Graphical Generative Adversarial Networks
Chongxuan LI, Max Welling, Jun Zhu, Bo Zhang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 global discriminator with local factor discriminators | GMGAN · MNIST | ACC: 91.62 ($\pm 1.91$) -> 93.03 ($\pm 1.65$) | Improved |
| Replace the global discriminator with local factor discriminators | GMGAN · CIFAR10 | IS: 5.41 ($\pm 0.08$) -> 5.94 ($\pm 0.06$) | Improved |
| Replace the global discriminator with local factor discriminators | GMGAN · MNIST | MSE: 0.056 ($\pm 0.001$) -> 0.044 ($\pm 0.001$) | Improved |
| Replace the global discriminator with local factor discriminators | GMGAN · CIFAR10 | ACC: 22.63 ($\pm 1.09$) -> 25.14 ($\pm 2.38$) | Improved |
| Use the structured local algorithm rather than the global baseline | SSGAN · Moving MNIST, T=16; 3D chairs, T=31 | video generation quality | Improved |
| Use the Markov structure to generate sequences beyond the training length | SSGAN · 3D chairs | generated sequence length: 31 -> 200 | Improved |
Closest papers by meaning
- MGAN: Training Generative Adversarial Nets with Multiple Generators (ICLR 2018 · similarity 0.88)
- On the Statistical Properties of Generative Adversarial Models for Low Intrinsic Data Dimension (JMLR 2025 · similarity 0.88)
- Structure-preserving GANs (ICML 2022 · similarity 0.88)
- Bayesian GAN (NeurIPS 2017 · similarity 0.88)
- Structured Generative Adversarial Networks (NeurIPS 2017 · similarity 0.88)
- MCGAN: Enhancing GAN Training with Regression-Based Generator Loss (AAAI 2025 · 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.
