2. StackedGAN
In the same spirit as InfoGAN, StackedGAN proposes a method for disentangling latent representations for conditioning generator outputs. However, StackedGAN uses a different approach to the problem. Instead of learning how to condition the noise to produce the desired output, StackedGAN breaks down a GAN into a stack of GANs. Each GAN is trained independently in the usual discriminator-adversarial manner with its own latent code.
Figure 6.2.1 shows us how StackedGAN works in the context of hypothetical celebrity face generation, assuming that the Encoder network has been trained to classify celebrity faces:
Figure 6.2.1: The basic idea of StackedGAN in the context of celebrity face generation. Assuming that there is a hypothetical deep encoder network that can perform classification on celebrity faces, a StackedGAN simply inverts the process of the encoder
The Encoder network is composed of a stack of simple encoders, Encoderi where i = 0 ...
