This video explains the Adaptive Discriminator Augmentation (ADA) technique from researchers at NVIDIA to train GANs with as few as 1,000 examples! This is a strategy to use data augmentation for discriminator overfitting without causing the generator to in turn produce data with these augmentations. Thanks for watching! Please Subscribe!
Paper Links:
Training GANs with Limited Data: https://arxiv.org/pdf/2006.06676.pdf
Image Augmentations for GAN Training: https://arxiv.org/abs/2006.02595
bCR / zCR: https://arxiv.org/pdf/1910.12027.pdf
RandAugment: https://arxiv.org/pdf/1909.13719.pdf
Freeze Discriminator: https://arxiv.org/pdf/2002.10964.pdf
MineGAN (not mentioned, but another interesting paper w.r.t. transfer learning in GANs): https://arxiv.org/pdf/1912.05270.pdf
