Linear Discriminant Generative Adversarial Networks

07/25/2017
by   Zhun Sun, et al.
0

We develop a novel method for training of GANs for unsupervised and class conditional generation of images, called Linear Discriminant GAN (LD-GAN). The discriminator of an LD-GAN is trained to maximize the linear separability between distributions of hidden representations of generated and targeted samples, while the generator is updated based on the decision hyper-planes computed by performing LDA over the hidden representations. LD-GAN provides a concrete metric of separation capacity for the discriminator, and we experimentally show that it is possible to stabilize the training of LD-GAN simply by calibrating the update frequencies between generators and discriminators in the unsupervised case, without employment of normalization methods and constraints on weights. In the class conditional generation tasks, the proposed method shows improved training stability together with better generalization performance compared to WGAN that employs an auxiliary classifier.

READ FULL TEXT

page 8

page 10

page 12

research
03/29/2018

Dihedral angle prediction using generative adversarial networks

Several dihedral angles prediction methods were developed for protein st...
research
06/19/2018

Versatile Auxiliary Classifier with Generative Adversarial Network (VAC+GAN), Multi Class Scenarios

Conditional generators learn the data distribution for each class in a m...
research
03/02/2017

Generalization and Equilibrium in Generative Adversarial Nets (GANs)

We show that training of generative adversarial network (GAN) may not ha...
research
11/05/2019

Biconditional Generative Adversarial Networks for Multiview Learning with Missing Views

In this paper, we present a conditional GAN with two generators and a co...
research
02/05/2019

Perturbative GAN: GAN with Perturbation Layers

Perturbative GAN, which replaces convolution layers of existing convolut...
research
07/21/2021

cGANs with Auxiliary Discriminative Classifier

Conditional generative models aim to learn the underlying joint distribu...
research
03/06/2019

Conditional GANs For Painting Generation

We examined the use of modern Generative Adversarial Nets to generate no...

Please sign up or login with your details

Forgot password? Click here to reset