DigGAN: Discriminator gradIent Gap Regularization for GAN Training with Limited Data

11/27/2022
by   Tiantian Fang, et al.
0

Generative adversarial nets (GANs) have been remarkably successful at learning to sample from distributions specified by a given dataset, particularly if the given dataset is reasonably large compared to its dimensionality. However, given limited data, classical GANs have struggled, and strategies like output-regularization, data-augmentation, use of pre-trained models and pruning have been shown to lead to improvements. Notably, the applicability of these strategies is 1) often constrained to particular settings, e.g., availability of a pretrained GAN; or 2) increases training time, e.g., when using pruning. In contrast, we propose a Discriminator gradIent Gap regularized GAN (DigGAN) formulation which can be added to any existing GAN. DigGAN augments existing GANs by encouraging to narrow the gap between the norm of the gradient of a discriminator's prediction w.r.t. real images and w.r.t. the generated samples. We observe this formulation to avoid bad attractors within the GAN loss landscape, and we find DigGAN to significantly improve the results of GAN training when limited data is available. Code is available at <https://github.com/AilsaF/DigGAN>.

READ FULL TEXT

page 2

page 8

page 9

page 15

page 16

page 17

page 18

research
11/10/2020

Towards a Better Global Loss Landscape of GANs

Understanding of GAN training is still very limited. One major challenge...
research
12/16/2021

Ensembling Off-the-shelf Models for GAN Training

The advent of large-scale training has produced a cornucopia of powerful...
research
11/04/2018

Improving GAN with neighbors embedding and gradient matching

We propose two new techniques for training Generative Adversarial Networ...
research
03/17/2021

Training GANs with Stronger Augmentations via Contrastive Discriminator

Recent works in Generative Adversarial Networks (GANs) are actively revi...
research
04/29/2023

LD-GAN: Low-Dimensional Generative Adversarial Network for Spectral Image Generation with Variance Regularization

Deep learning methods are state-of-the-art for spectral image (SI) compu...
research
12/10/2020

SSD-GAN: Measuring the Realness in the Spatial and Spectral Domains

This paper observes that there is an issue of high frequencies missing i...
research
05/30/2019

Adversarial Sub-sequence for Text Generation

Generative adversarial nets (GAN) has been successfully introduced for g...

Please sign up or login with your details

Forgot password? Click here to reset