RPGAN: GANs Interpretability via Random Routing

12/23/2019
by   Andrey Voynov, et al.
17

In this paper, we introduce Random Path Generative Adversarial Network (RPGAN) – an alternative design of GANs that can serve as a tool for generative model analysis. While the latent space of a typical GAN consists of input vectors, randomly sampled from the standard Gaussian distribution, the latent space of RPGAN consists of random paths in a generator network. As we show, this design allows to understand factors of variation, captured by different generator layers, providing their natural interpretability. With experiments on standard benchmarks, we demonstrate that RPGAN reveals several interesting insights about the roles that different layers play in the image generation process. Aside from interpretability, the RPGAN model also provides competitive generation quality and allows efficient incremental learning on new data.

READ FULL TEXT

page 13

page 14

page 15

page 16

page 17

page 18

page 20

page 21

research
02/15/2018

Inverting The Generator Of A Generative Adversarial Network (II)

Generative adversarial networks (GANs) learn a deep generative model tha...
research
01/15/2021

The Geometry of Deep Generative Image Models and its Applications

Generative adversarial networks (GANs) have emerged as a powerful unsupe...
research
05/10/2021

Learning High-Dimensional Distributions with Latent Neural Fokker-Planck Kernels

Learning high-dimensional distributions is an important yet challenging ...
research
04/02/2018

SyncGAN: Synchronize the Latent Space of Cross-modal Generative Adversarial Networks

Generative adversarial network (GAN) has achieved impressive success on ...
research
05/12/2021

Directional GAN: A Novel Conditioning Strategy for Generative Networks

Image content is a predominant factor in marketing campaigns, websites a...
research
04/12/2018

Blood Vessel Geometry Synthesis using Generative Adversarial Networks

Computationally synthesized blood vessels can be used for training and e...
research
10/19/2021

Latent reweighting, an almost free improvement for GANs

Standard formulations of GANs, where a continuous function deforms a con...

Please sign up or login with your details

Forgot password? Click here to reset