Conditional Image Generation with One-Vs-All Classifier

by   XiangRui Xu, et al.

This paper explores conditional image generation with a One-Vs-All classifier based on the Generative Adversarial Networks (GANs). Instead of the real/fake discriminator used in vanilla GANs, we propose to extend the discriminator to a One-Vs-All classifier (GAN-OVA) that can distinguish each input data to its category label. Specifically, we feed certain additional information as conditions to the generator and take the discriminator as a One-Vs-All classifier to identify each conditional category. Our model can be applied to different divergence or distances used to define the objective function, such as Jensen-Shannon divergence and Earth-Mover (or called Wasserstein-1) distance. We evaluate GAN-OVAs on MNIST and CelebA-HQ datasets, and the experimental results show that GAN-OVAs make progress toward stable training over regular conditional GANs. Furthermore, GAN-OVAs effectively accelerate the generation process of different classes and improves generation quality.


page 5

page 6

page 7


Fast-converging Conditional Generative Adversarial Networks for Image Synthesis

Building on top of the success of generative adversarial networks (GANs)...

Guiding GANs: How to control non-conditional pre-trained GANs for conditional image generation

Generative Adversarial Networks (GANs) are an arrange of two neural netw...

DuDGAN: Improving Class-Conditional GANs via Dual-Diffusion

Class-conditional image generation using generative adversarial networks...

JGAN: A Joint Formulation of GAN for Synthesizing Images and Labels

Image generation with explicit condition or label generally works better...

Measure-conditional Discriminator with Stationary Optimum for GANs and Statistical Distance Surrogates

We propose a simple but effective modification of the discriminators, na...

Class-Distinct and Class-Mutual Image Generation with GANs

We describe a new problem called class-distinct and class-mutual (DM) im...

Twin Auxiliary Classifiers GAN

Conditional generative models enjoy remarkable progress over the past fe...

Please sign up or login with your details

Forgot password? Click here to reset