Assumed knowledge of GANs in concatenation section

[vdumoulin]

“This is in fact the approach adopted by the conditional variant of DCGAN [8], a well-recognized class of network architectures for generative adversarial networks (GANs)” Is the reader expected to know what a GAN is? The part is a bit funny because it explains the acronym GAN as though we aren’t familiar, but then doesn’t mention at all what they’re used for, and then doesn’t explain the acronym for DCGAN. I might say:

“Deep convolutional generative adversarial networks (DCGAN) are a popular class of generative model often used to create images. The conditional variant, where a single network can create images from multiple classes, uses exactly this concatenation idea, broadcasting the class label as a feature map and concatenating it to the input of the convolutional and transposed convolutional layers in the generator and discriminator networks”

That said, even this assumes a lot of domain knowledge about what exactly a GAN is, (i.e. what a generator and discriminator network is!) I’d be tempted to do a heavier re-work of the system and actually more concretely explain how it works.

Xavier

[fstrub95]

This section was already refactored -> Do I have to update it again?

As described above, an improvement over this idea would be to concatenate \mathbf{z}z to the input of all layers in the neural network. This is in fact the approach adopted by the conditional variant of DCGAN [4] , a well-recognized class of network architectures for generative adversarial networks (GANs) [5] . The class label is broadcasted as a feature map and is concatenated to the input of convolutional and transposed convolutional layers in the generator and discriminator networks.

[fstrub95]

I update the figure: https://github.com/vdumoulin/distill-film/pull/129/files