Collaborative GAN Sampling

02/02/2019
by   Yuejiang Liu, et al.
10

Generative adversarial networks (GANs) have shown great promise in generating complex data such as images. A standard practice in GANs is to discard the discriminator after training and use only the generator for sampling. However, this loses valuable information of real data distribution learned by the discriminator. In this work, we propose a collaborative sampling scheme between the generator and discriminator for improved data generation. Guided by the discriminator, our approach refines generated samples through gradient-based optimization, shifting the generator distribution closer to the real data distribution. Additionally, we present a practical discriminator shaping method that can further improve the sample refinement process. Orthogonal to existing GAN variants, our proposed method offers a new degree of freedom in GAN sampling. We demonstrate its efficacy through experiments on synthetic data and image generation tasks.

READ FULL TEXT

page 8

page 9

research
11/28/2018

Metropolis-Hastings Generative Adversarial Networks

We introduce the Metropolis-Hastings generative adversarial network (MH-...
research
02/12/2018

Tempered Adversarial Networks

Generative adversarial networks (GANs) have been shown to produce realis...
research
06/02/2023

GANs Settle Scores!

Generative adversarial networks (GANs) comprise a generator, trained to ...
research
11/20/2018

Adversarial Feedback Loop

Thanks to their remarkable generative capabilities, GANs have gained gre...
research
10/16/2018

Discriminator Rejection Sampling

We propose a rejection sampling scheme using the discriminator of a GAN ...
research
05/29/2019

Training Generative Adversarial Networks from Incomplete Observations using Factorised Discriminators

Generative adversarial networks (GANs) have shown great success in appli...
research
10/01/2020

Tabular GANs for uneven distribution

GANs are well known for success in the realistic image generation. Howev...

Please sign up or login with your details

Forgot password? Click here to reset