Generative Adversarial Networks
Wasserstein GAN
Introduced by Arjovsky et al. in Wasserstein GANWasserstein GAN, or WGAN, is a type of generative adversarial network that minimizes an approximation of the Earth-Mover's distance (EM) rather than the Jensen-Shannon divergence as in the original GAN formulation. It leads to more stable training than original GANs with less evidence of mode collapse, as well as meaningful curves that can be used for debugging and searching hyperparameters.
Source: Wasserstein GAN
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Image Generation | 14 | 16.47% |
| Denoising | 6 | 7.06% |
| Image-to-Image Translation | 4 | 4.71% |
| Time Series Analysis | 4 | 4.71% |
| Synthetic Data Generation | 3 | 3.53% |
| Translation | 3 | 3.53% |
| Image Denoising | 2 | 2.35% |
| EEG | 2 | 2.35% |
| General Classification | 2 | 2.35% |
Convolution
