Dropout Induced Noise for Co-Creative GAN Systems

09/10/2019

∙

This paper demonstrates how Dropout can be used in Generative Adversarial Networks to generate multiple different outputs to one input. This method is thought as an alternative to latent space exploration, especially if constraints in the input should be preserved, like in A-to-B translation tasks.

READ FULL TEXT

Dropout Induced Noise for Co-Creative GAN Systems

Precise Recovery of Latent Vectors from Generative Adversarial Networks

Dropout-GAN: Learning from a Dynamic Ensemble of Discriminators

IGAN: Inferent and Generative Adversarial Networks

Controlling the Latent Space of GANs through Reinforcement Learning: A Case Study on Task-based Image-to-Image Translation

Learning to Drop Out: An Adversarial Approach to Training Sequence VAEs

Generative Adversarial Networks with Conditional Neural Movement Primitives for An Interactive Generative Drawing Tool

LocoGAN – Locally Convolutional GAN

Dropout Induced Noise for Co-Creative GAN Systems

Related Research

Precise Recovery of Latent Vectors from Generative Adversarial Networks

Dropout-GAN: Learning from a Dynamic Ensemble of Discriminators

IGAN: Inferent and Generative Adversarial Networks

Controlling the Latent Space of GANs through Reinforcement Learning: A Case Study on Task-based Image-to-Image Translation

Learning to Drop Out: An Adversarial Approach to Training Sequence VAEs

Generative Adversarial Networks with Conditional Neural Movement Primitives for An Interactive Generative Drawing Tool

LocoGAN – Locally Convolutional GAN