Viet-Anh on Software Logo

What is: Bidirectional GAN?

SourceAdversarial Feature Learning
Year2000
Data SourceCC BY-SA - https://paperswithcode.com

A BiGAN, or Bidirectional GAN, is a type of generative adversarial network where the generator not only maps latent samples to generated data, but also has an inverse mapping from data to the latent representation. The motivation is to make a type of GAN that can learn rich representations for us in applications like unsupervised learning.

In addition to the generator GG from the standard GAN framework, BiGAN includes an encoder EE which maps data x\mathbf{x} to latent representations z\mathbf{z}. The BiGAN discriminator DD discriminates not only in data space (x\mathbf{x} versus G(z)G\left(\mathbf{z}\right)), but jointly in data and latent space (tuples (x,E(x))\left(\mathbf{x}, E\left(\mathbf{x}\right)\right) versus (G(z),z)\left(G\left(z\right), z\right)), where the latent component is either an encoder output E(x)E\left(\mathbf{x}\right) or a generator input z\mathbf{z}.