Improved Consistency Regularization for GANs

This video explores a new technique for using the same Consistency Regularization headlining advances in Unsupervised Learning such as FixMatch and SimCLR to the GAN framework! This achieves large improvements in FID scores generating ImageNet images! Paper Links: Improved Consistency Regularization for GANs: https://arxiv.org/pdf/2002.04724.pdf Robert Luxemburg's StyleGAN2 Interpolation Loop: https://www.youtube.com/watch?v=6E1_dgYlifc BigGAN Paper: https://arxiv.org/pdf/1809.11096.pdf BigBiGAN: https://arxiv.org/pdf/1907.02544.pdf StyleGAN2: https://arxiv.org/pdf/1912.04958.pdf Unsupervised Data Augmentation: https://arxiv.org/pdf/1904.12848.pdf FixMatch: https://arxiv.org/pdf/2001.07685.pdf SimCLR: https://arxiv.org/pdf/2002.05709.pdf Conditional GANs: https://arxiv.org/pdf/1411.1784.pdf Thanks for watching! Please Subscribe!