Data Instance Prior for Transfer Learning in GANs

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 . 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 .

Links: PDF - Abstract

Code :


Keywords : data - gans - domain - images - prior -

Leave a Reply

Your email address will not be published. Required fields are marked *