Generative Adversarial Network (GAN) is widely used for instance generation in multiple fields. It models a zero-sum game between a generator network and a discriminator network while using the Jensen-Shannon divergence between the target distribution and the generated one as the optimization goal. We propose an alternative explanation of such a framework using a binary-input channel. We also show that our proposed goal is equivalent to the original Jensen-Shannon divergence while enforcing a tighter performance bound. We then introduce an additional trainable parameter π with only few modification on the vanilla implementation of GAN. We further experiment with our proposed variant of GAN on MNIST and CIFAR-10, producing ∼ 10 less on the Fr´ echet inception distance and ∼ 0.5 more on the inception score.
Use this login method if you
don't
have an
@illinois.edu
email address.
(Oops, I do have one)
IDEALS migrated to a new platform on June 23, 2022. If you created
your account prior to this date, you will have to reset your password
using the forgot-password link below.
