Robust Conditional GAN from Uncertainty-Aware Pairwise Comparisons

11/21/2019
by   Ligong Han, et al.
24

Conditional generative adversarial networks have shown exceptional generation performance over the past few years. However, they require large numbers of annotations. To address this problem, we propose a novel generative adversarial network utilizing weak supervision in the form of pairwise comparisons (PC-GAN) for image attribute editing. In the light of Bayesian uncertainty estimation and noise-tolerant adversarial training, PC-GAN can estimate attribute rating efficiently and demonstrate robust performance in noise resistance. Through extensive experiments, we show both qualitatively and quantitatively that PC-GAN performs comparably with fully-supervised methods and outperforms unsupervised baselines.

READ FULL TEXT

page 5

page 6

page 7

page 12

page 13

page 14

page 15

research
03/29/2018

Dihedral angle prediction using generative adversarial networks

Several dihedral angles prediction methods were developed for protein st...
research
07/01/2020

Estimation with Uncertainty via Conditional Generative Adversarial Networks

Conventional predictive Artificial Neural Networks (ANNs) commonly emplo...
research
02/28/2019

GAN Based Image Deblurring Using Dark Channel Prior

A conditional general adversarial network (GAN) is proposed for image de...
research
07/12/2018

CT-GAN: Conditional Transformation Generative Adversarial Network for Image Attribute Modification

We propose a novel, fully-convolutional conditional generative model cap...
research
12/11/2017

Eye In-Painting with Exemplar Generative Adversarial Networks

This paper introduces a novel approach to in-painting where the identity...
research
04/08/2020

Inpainting via Generative Adversarial Networks for CMB data analysis

In this work, we propose a new method to inpaint the CMB signal in regio...
research
07/21/2020

Garment Design with Generative Adversarial Networks

The designers' tendency to adhere to a specific mental set and heavy emo...

Please sign up or login with your details

Forgot password? Click here to reset