Semi-Supervised Learning with Generative Adversarial Networks

Code

• github.com/Soumya1612-Rasha/Keras-GAN_rasha
  none★ 7
• github.com/caio-davi/gGAN
  none★ 3
• github.com/yunjey/mnist-svhn-transfer
  pytorch★ 0
• github.com/tryambak2019/SGAN
  none★ 0

Abstract

We extend Generative Adversarial Networks (GANs) to the semi-supervised context by forcing the discriminator network to output class labels. We train a generative model G and a discriminator D on a dataset with inputs belonging to one of N classes. At training time, D is made to predict which of N+1 classes the input belongs to, where an extra class is added to correspond to the outputs of G. We show that this method can be used to create a more data-efficient classifier and that it allows for generating higher quality samples than a regular GAN.

Reproductions