Sage-Tips

What is the difference between GAN and conditional GAN?

In GAN, there is no control over modes of the data to be generated. The conditional GAN changes that by adding the label y as an additional parameter to the generator and hopes that the corresponding images are generated. We also add the labels to the discriminator input to distinguish real images better.

What are the different types of Gans?

This tutorial is divided into three parts; they are:

• Foundation. Generative Adversarial Network (GAN) Deep Convolutional Generative Adversarial Network (DCGAN)
• Extensions. Conditional Generative Adversarial Network (cGAN)
• Advanced. Wasserstein Generative Adversarial Network (WGAN)

What is the difference between conditional and unconditional GANs?

Conditional GANs train on a labeled data set and let you specify the label for each generated instance. For example, an unconditional MNIST GAN would produce random digits, while a conditional MNIST GAN would let you specify which digit the GAN should generate.

What is conditional image generation?

Conditional image generation is the task of generating diverse images using class label information. Simultaneously, the generator tries to generate realistic images that deceive the authenticity and have a low contrastive loss.

What is conditional GAN?

Conditional GAN (CGAN) is a GAN variant in which both the Generator and the Discriminator are conditioned on auxiliary data such as a class label during training.

What is the Wasserstein Gan?

The Wasserstein GAN (WGAN) is a GAN variant which uses the 1-Wasserstein distance, rather than the JS-Divergence, to measure the difference between the model and target distributions. This seemingly simple change has big consequences!

What is the difference between Gan and lsgan?

Another point to note is that the loss function is setup more similarly to the original GAN, but where the original GAN uses a log loss, the LSGAN uses an L2 loss (which equates to minimizing the Pearson X² divergence).

What is the objective function of the original Gan?

The objective function of our original GAN is essentially the minimization of something called the Jensen Shannon Divergence (JSD). Specifically it is: The JSD is derived from the Kullbach-Liebler Divergence (KLD) that we mentioned in the previous post.

How competitive is rwgan parameterized with KL divergence?

They specifically show that RWGAN parameterized with KL divergence is extremely competitive against other state-of-the-art GANs, but with better convergence properties than even the regular WGAN. They also open their framework up to defining new loss functions and thus new cost functions for designing a GAN scheme.