Unbiased Auxiliary Classifier GANs with MINE

by   Ligong Han, et al.
Rutgers University

Auxiliary Classifier GANs (AC-GANs) are widely used conditional generative models and are capable of generating high-quality images. Previous work has pointed out that AC-GAN learns a biased distribution. To remedy this, Twin Auxiliary Classifier GAN (TAC-GAN) introduces a twin classifier to the min-max game. However, it has been reported that using a twin auxiliary classifier may cause instability in training. To this end, we propose an Unbiased Auxiliary GANs (UAC-GAN) that utilizes the Mutual Information Neural Estimator (MINE) to estimate the mutual information between the generated data distribution and labels. To further improve the performance, we also propose a novel projection-based statistics network architecture for MINE. Experimental results on three datasets, including Mixture of Gaussian (MoG), MNIST and CIFAR10 datasets, show that our UAC-GAN performs better than AC-GAN and TAC-GAN. Code can be found on the project website.


Fast-converging Conditional Generative Adversarial Networks for Image Synthesis

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

cGANs with Auxiliary Discriminative Classifier

Conditional generative models aim to learn the underlying joint distribu...

Coupled Generative Adversarial Network for Continuous Fine-grained Action Segmentation

We propose a novel conditional GAN (cGAN) model for continuous fine-grai...

Teaching a GAN What Not to Learn

Generative adversarial networks (GANs) were originally envisioned as uns...

Lift3D: Synthesize 3D Training Data by Lifting 2D GAN to 3D Generative Radiance Field

This work explores the use of 3D generative models to synthesize trainin...

Twin Auxiliary Classifiers GAN

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

Out-of-Sample Testing for GANs

We propose a new method to evaluate GANs, namely EvalGAN. EvalGAN relies...

Please sign up or login with your details

Forgot password? Click here to reset