MineGAN: effective knowledge transfer from GANs to target domains with few images

by   Yaxing Wang, et al.

One of the attractive characteristics of deep neural networks is their ability to transfer knowledge obtained in one domain to other related domains. As a result, high-quality networks can be trained in domains with relatively little training data. This property has been extensively studied for discriminative networks but has received significantly less attention for generative models.Given the often enormous effort required to train GANs, both computationally as well as in the dataset collection, the re-use of pretrained GANs is a desirable objective. We propose a novel knowledge transfer method for generative models based on mining the knowledge that is most beneficial to a specific target domain, either from a single or multiple pretrained GANs. This is done using a miner network that identifies which part of the generative distribution of each pretrained GAN outputs samples closest to the target domain. Mining effectively steers GAN sampling towards suitable regions of the latent space, which facilitates the posterior finetuning and avoids pathologies of other methods such as mode collapse and lack of flexibility. We perform experiments on several complex datasets using various GAN architectures (BigGAN, Progressive GAN) and show that the proposed method, called MineGAN, effectively transfers knowledge to domains with few target images, outperforming existing methods. In addition, MineGAN can successfully transfer knowledge from multiple pretrained GANs.


page 6

page 8

page 12

page 13

page 14

page 15

page 16

page 17


MineGAN++: Mining Generative Models for Efficient Knowledge Transfer to Limited Data Domains

GANs largely increases the potential impact of generative models. Theref...

GAN Cocktail: mixing GANs without dataset access

Today's generative models are capable of synthesizing high-fidelity imag...

Resolution Dependant GAN Interpolation for Controllable Image Synthesis Between Domains

GANs can generate photo-realistic images from the domain of their traini...

Transferring GANs: generating images from limited data

Transferring the knowledge of pretrained networks to new domains by mean...

RadialGAN: Leveraging multiple datasets to improve target-specific predictive models using Generative Adversarial Networks

Training complex machine learning models for prediction often requires a...

Ensembling Off-the-shelf Models for GAN Training

The advent of large-scale training has produced a cornucopia of powerful...

When, Why, and Which Pretrained GANs Are Useful?

The literature has proposed several methods to finetune pretrained GANs ...

Please sign up or login with your details

Forgot password? Click here to reset