Human Annotations Improve GAN Performances

11/15/2019
by   Juanyong Duan, et al.
19

Generative Adversarial Networks (GANs) have shown great success in many applications. In this work, we present a novel method that leverages human annotations to improve the quality of generated images. Unlike previous paradigms that directly ask annotators to distinguish between real and fake data in a straightforward way, we propose and annotate a set of carefully designed attributes that encode important image information at various levels, to understand the differences between fake and real images. Specifically, we have collected an annotated dataset that contains 600 fake images and 400 real images. These images are evaluated by 10 workers from the Amazon Mechanical Turk (AMT) based on eight carefully defined attributes. Statistical analyses have revealed different distributions of the proposed attributes between real and fake images. These attributes are shown to be useful in discriminating fake images from real ones, and deep neural networks are developed to automatically predict the attributes. We further utilize the information by integrating the attributes into GANs to generate better images. Experimental results evaluated by multiple metrics show performance improvement of the proposed model.

READ FULL TEXT

page 1

page 2

page 4

page 5

page 6

page 7

page 9

page 10

research
06/16/2021

Compound Frechet Inception Distance for Quality Assessment of GAN Created Images

Generative adversarial networks or GANs are a type of generative modelin...
research
09/21/2019

IntersectGAN: Learning Domain Intersection for Generating Images with Multiple Attributes

Generative adversarial networks (GANs) have demonstrated great success i...
research
03/19/2020

Leveraging Frequency Analysis for Deep Fake Image Recognition

Deep neural networks can generate images that are astonishingly realisti...
research
02/01/2020

Global Texture Enhancement for Fake Face Detection in the Wild

Generative Adversarial Networks (GANs) can generate realistic fake face ...
research
02/17/2020

Amplifying The Uncanny

Deep neural networks have become remarkably good at producing realistic ...
research
01/09/2021

Exploring Adversarial Fake Images on Face Manifold

Images synthesized by powerful generative adversarial network (GAN) base...
research
07/16/2017

Generative Adversarial Network based on Resnet for Conditional Image Restoration

The GANs promote an adversarive game to approximate complex and jointed ...

Please sign up or login with your details

Forgot password? Click here to reset