Unrealistic Feature Suppression for Generative Adversarial Networks

07/23/2021
by   Sanghun Kim, et al.
0

Due to the unstable nature of minimax game between generator and discriminator, improving the performance of GANs is a challenging task. Recent studies have shown that selected high-quality samples in training improve the performance of GANs. However, sampling approaches which discard samples show limitations in some aspects such as the speed of training and optimality of the networks. In this paper we propose unrealistic feature suppression (UFS) module that keeps high-quality features and suppresses unrealistic features. UFS module keeps the training stability of networks and improves the quality of generated images. We demonstrate the effectiveness of UFS module on various models such as WGAN-GP, SNGAN, and BigGAN. By using UFS module, we achieved better Frechet inception distance and inception score compared to various baseline models. We also visualize how effectively our UFS module suppresses unrealistic features through class activation maps.

READ FULL TEXT

page 6

page 7

page 8

research
11/19/2019

A Simple yet Effective Way for Improving the Performance of GANs

This paper presents a simple but effective way that improves the perform...
research
07/05/2022

CEN : Cooperatively Evolving Networks

A finitely repeated game is a dynamic game in which a simultaneous game ...
research
02/12/2018

Tempered Adversarial Networks

Generative adversarial networks (GANs) have been shown to produce realis...
research
11/01/2021

Projected GANs Converge Faster

Generative Adversarial Networks (GANs) produce high-quality images but a...
research
02/07/2018

Stochastic Deconvolutional Neural Network Ensemble Training on Generative Pseudo-Adversarial Networks

The training of Generative Adversarial Networks is a difficult task main...
research
10/13/2019

Implicit competitive regularization in GANs

Generative adversarial networks (GANs) are capable of producing high qua...
research
10/27/2017

Progressive Growing of GANs for Improved Quality, Stability, and Variation

We describe a new training methodology for generative adversarial networ...

Please sign up or login with your details

Forgot password? Click here to reset