Generative Models
Progressively Growing GAN
Introduced by Karras et al. in Progressive Growing of GANs for Improved Quality, Stability, and VariationProGAN, or Progressively Growing GAN, is a generative adversarial network that utilises a progressively growing training approach. The idea is to grow both the generator and discriminator progressively: starting from a low resolution, we add new layers that model increasingly fine details as training progresses.
Source: Progressive Growing of GANs for Improved Quality, Stability, and Variation
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Image Generation | 5 | 20.83% |
| Translation | 2 | 8.33% |
| Synthetic Data Generation | 2 | 8.33% |
| Face Generation | 2 | 8.33% |
| Fake Image Detection | 1 | 4.17% |
| Synthetic Image Detection | 1 | 4.17% |
| Denoising | 1 | 4.17% |
| whole slide images | 1 | 4.17% |
| Object Detection | 1 | 4.17% |
1x1 Convolution
Convolution
Dense Connections
Leaky ReLU
Local Response Normalization
WGAN-GP Loss
