Data InStance Prior (DISP) in Generative Adversarial Networks

TL;DR

This paper introduces a novel transfer learning approach for GANs that utilizes data instance priors from pre-trained networks to improve image quality and diversity in limited data scenarios.

Contribution

The paper proposes a new transfer learning method for GANs using data instance priors from pre-trained models, enhancing performance with limited data.

Findings

Outperforms state-of-the-art methods in low-data regimes

Improves image quality and diversity in GAN outputs

Effective in large-scale unconditional image generation

Abstract

Recent advances in generative adversarial networks (GANs) have shown remarkable progress in generating high-quality images. However, this gain in performance depends on the availability of a large amount of training data. In limited data regimes, training typically diverges, and therefore the generated samples are of low quality and lack diversity. Previous works have addressed training in low data setting by leveraging transfer learning and data augmentation techniques. We propose a novel transfer learning method for GANs in the limited data domain by leveraging informative data prior derived from self-supervised/supervised pre-trained networks trained on a diverse source domain. We perform experiments on several standard vision datasets using various GAN architectures (BigGAN, SNGAN, StyleGAN2) to demonstrate that the proposed method effectively transfers knowledge to domains with few target images, outperforming existing state-of-the-art techniques in terms of image quality and diversity. We also show the utility of data instance prior in large-scale unconditional image generation.