MineGAN : Effective Knowledge Transfer from GANs to Target Domains with Few Images
Wang, Yaxing (Centre de Visió per Computador)
Gonzalez-Garcia, Abel (Centre de Visió per Computador)
Berga, David (Centre de Visió per Computador)
Herranz, Luis (Universitat Autònoma de Barcelona)
Khan, Fahad Shahbaz (Cvl. Linköping University)
Weijer, Joost van de (Centre de Visió per Computador)

Publicació:	Seattle IEEE 2020
Descripció:	10 pàg.
Resum:	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. Our code is available at: \url{https://github. com/yaxingwang/MineGAN}.
Ajuts:	Agencia Estatal de Investigación TIN2016-79717-R Agencia Estatal de Investigación RTI2018-102285-A-I00 European Commission 665919
Nota:	Altres ajuts: CERCA Programme/Generalitat de Catalunya
Drets:	Aquest material està protegit per drets d'autor i/o drets afins. Podeu utilitzar aquest material en funció del que permet la legislació de drets d'autor i drets afins d'aplicació al vostre cas. Per a d'altres usos heu d'obtenir permís del(s) titular(s) de drets.
Llengua:	Anglès
Document:	Capítol de llibre ; recerca ; Versió acceptada per publicar
Matèria:	Complex datasets ; Discriminative networks ; Generative model ; High quality ; Knowledge transfer ; Target domain ; Target images ; Training data
Publicat a:	Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Seattle, 13-19 June 2020, p. 9329-9338, ISBN 978-1-7281-7168-5

DOI: 10.1109/CVPR42600.2020.00935

Postprint 11 p, 9.3 MB

El registre apareix a les col·leccions:
Llibres i col·leccions > Capítols de llibres