The Bures Metric for Taming Mode Collapse in Generative Adversarial Networks

by   Hannes De Meulemeester, et al.
KU Leuven

Generative Adversarial Networks (GANs) are performant generative methods yielding high-quality samples. However, under certain circumstances, the training of GANs can lead to mode collapse or mode dropping, i.e. the generative models not being able to sample from the entire probability distribution. To address this problem, we use the last layer of the discriminator as a feature map to study the distribution of the real and the fake data. During training, we propose to match the real batch diversity to the fake batch diversity by using the Bures distance between covariance matrices in feature space. The computation of the Bures distance can be conveniently done in either feature space or kernel space in terms of the covariance and kernel matrix respectively. We observe that diversity matching reduces mode collapse substantially and has a positive effect on the sample quality. On the practical side, a very simple training procedure, that does not require additional hyperparameter tuning, is proposed and assessed on several datasets.


page 6

page 8

page 16

page 17

page 18

page 19

page 20


Training Generative Adversarial Networks Via Turing Test

In this article, we introduce a new mode for training Generative Adversa...

An empirical study on evaluation metrics of generative adversarial networks

Evaluating generative adversarial networks (GANs) is inherently challeng...

The Vendi Score: A Diversity Evaluation Metric for Machine Learning

Diversity is an important criterion for many areas of machine learning (...

Mixed batches and symmetric discriminators for GAN training

Generative adversarial networks (GANs) are pow- erful generative models ...

microbatchGAN: Stimulating Diversity with Multi-Adversarial Discrimination

We propose to tackle the mode collapse problem in generative adversarial...

Removal of Batch Effects using Generative Adversarial Networks

Many biological data analysis processes like Cytometry or Next Generatio...

Revisiting the Evaluation of Image Synthesis with GANs

A good metric, which promises a reliable comparison between solutions, i...

Please sign up or login with your details

Forgot password? Click here to reset