Transferring GANs : Generating images from limited data
Wang, Yaxing (Centre de Visió per Computador)
Wu, Chenshen (Centre de Visió per Computador)
Herranz, Luis (Universitat Autònoma de Barcelona)
Weijer, Joost van de (Centre de Visió per Computador)
Gonzalez-Garcia, Abel (Centre de Visió per Computador)
Raducanu, Bogdan (Centre de Visió per Computador)

Publicación:	Cham, Switzerland: Springer, 2018
Resumen:	Transferring knowledge of pre-trained networks to new domains by means of fine-tuning is a widely used practice for applications based on discriminative models. To the best of our knowledge this practice has not been studied within the context of generative deep networks. Therefore, we study domain adaptation applied to image generation with generative adversarial networks. We evaluate several aspects of domain adaptation, including the impact of target domain size, the relative distance between source and target domain, and the initialization of conditional GANs. Our results show that using knowledge from pre-trained networks can shorten the convergence time and can significantly improve the quality of the generated images, especially when target data is limited. We show that these conclusions can also be drawn for conditional GANs even when the pre-trained model was trained without conditioning. Our results also suggest that density is more important than diversity and a dataset with one or few densely sampled classes is a better source model than more diverse datasets such as ImageNet or Places.
Ayudas:	European Commission 665919 Agencia Estatal de Investigación TIN2016-79717-R Ministerio de Economía y Competitividad PCIN-2015-251
Nota:	Altres ajuts: CERCA Programme/Generalitat de Catalunya; GPU support from NVIDIA
Derechos:	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.
Lengua:	Anglès
Título addicional':	Lecture notes in computer science 11210
Documento:	Capítol de llibre ; recerca ; Versió acceptada per publicar
Materia:	Generative adversarial networks ; Transfer learning ; Domain adaptation ; Image generation
Publicado en:	Computer Vision - ECCV 2018: 15th European Conference, Munich, Germany, September 8-14, 2018, Proceedings, Part VI, 2018, p. 220-236, ISBN 978-3-030-01231-1

DOI: 10.1007/978-3-030-01231-1_14

Postprint 22 p, 13.2 MB

El registro aparece en las colecciones:
Libros y colecciones > Capítulos de libros