Generative Models

BigGAN is a type of generative adversarial network that was designed for scaling generation to high-resolution, high-fidelity images. It includes a number of incremental changes and innovations. The baseline and incremental changes are:

  • Using SAGAN as a baseline with spectral norm. for G and D, and using TTUR.
  • Using a Hinge Loss GAN objective
  • Using class-conditional batch normalization to provide class information to G (but with linear projection not MLP.
  • Using a projection discriminator for D to provide class information to D.
  • Evaluating with EWMA of G's weights, similar to ProGANs.

The innovations are:

  • Increasing batch sizes, which has a big effect on the Inception Score of the model.
  • Increasing the width in each layer leads to a further Inception Score improvement.
  • Adding skip connections from the latent variable $z$ to further layers helps performance.
  • A new variant of Orthogonal Regularization.
Source: Large Scale GAN Training for High Fidelity Natural Image Synthesis


Paper Code Results Date Stars