Diversity-Sensitive Conditional Generative Adversarial Networks

01/25/2019
by   Dingdong Yang, et al.
16

We propose a simple yet highly effective method that addresses the mode-collapse problem in the Conditional Generative Adversarial Network (cGAN). Although conditional distributions are multi-modal (i.e., having many modes) in practice, most cGAN approaches tend to learn an overly simplified distribution where an input is always mapped to a single output regardless of variations in latent code. To address such issue, we propose to explicitly regularize the generator to produce diverse outputs depending on latent codes. The proposed regularization is simple, general, and can be easily integrated into most conditional GAN objectives. Additionally, explicit regularization on generator allows our method to control a balance between visual quality and diversity. We demonstrate the effectiveness of our method on three conditional generation tasks: image-to-image translation, image inpainting, and future video prediction. We show that simple addition of our regularization to existing models leads to surprisingly diverse generations, substantially outperforming the previous approaches for multi-modal conditional generation specifically designed in each individual task.

READ FULL TEXT

page 5

page 6

page 7

page 16

page 17

page 18

page 19

page 22

research
03/13/2019

Mode Seeking Generative Adversarial Networks for Diverse Image Synthesis

Most conditional generation tasks expect diverse outputs given a single ...
research
11/25/2020

How to train your conditional GAN: An approach using geometrically structured latent manifolds

Conditional generative modeling typically requires capturing one-to-many...
research
03/27/2021

Continuous Conditional Generative Adversarial Networks (cGAN) with Generator Regularization

Conditional Generative Adversarial Networks are known to be difficult to...
research
08/11/2019

GAN-Tree: An Incrementally Learned Hierarchical Generative Framework for Multi-Modal Data Distributions

Despite the remarkable success of generative adversarial networks, their...
research
01/10/2020

Unsupervised multi-modal Styled Content Generation

The emergence of deep generative models has recently enabled the automat...
research
01/10/2020

Unsupervised K-modal Styled Content Generation

The emergence of generative models based on deep neural networks has rec...
research
05/04/2020

Transforming and Projecting Images into Class-conditional Generative Networks

We present a method for projecting an input image into the space of a cl...

Please sign up or login with your details

Forgot password? Click here to reset