Adversarial Training
DiffAugment
Introduced by Zhao et al. in Differentiable Augmentation for Data-Efficient GAN TrainingDifferentiable Augmentation (DiffAugment) is a set of differentiable image transformations used to augment data during GAN training. The transformations are applied to the real and generated images. It enables the gradients to be propagated through the augmentation back to the generator, regularizes the discriminator without manipulating the target distribution, and maintains the balance of training dynamics. Three choices of transformation are preferred by the authors in their experiments: Translation, CutOut, and Color.
Source: Differentiable Augmentation for Data-Efficient GAN Training
Papers
| Paper | Code | Results | Date | Stars |
|---|
ColorJitter
Cutout
