Few-Shot Unsupervised Image-to-Image Translation

Tutkimustuotos: Artikkeli kirjassa/konferenssijulkaisussavertaisarvioitu

Tutkijat

  • Ming-Yu Liu
  • Xun Huang
  • Arun Mallya
  • Tero Karras
  • Timo Aila
  • Jaakko Lehtinen
  • Jan Kautz

Organisaatiot

  • NVIDIA Corporation

Kuvaus

Unsupervised image-to-image translation methods learn to map images in a given class to an analogous image in a different class, drawing on unstructured (non-registered) datasets of images. While remarkably successful, current methods require access to many images in both source and destination classes at training time. We argue this greatly limits their use. Drawing inspiration from the human capability of picking up the essence of a novel object from a small number of examples and generalizing from there, we seek a few-shot, unsupervised image-to-image translation algorithm that works on previously unseen target classes that are specified, at test time, only by a few example images. Our model achieves this few-shot generation capability by coupling an adversarial training scheme with a novel network design. Through extensive experimental validation and comparisons to several baseline methods on benchmark datasets, we verify the effectiveness of the proposed framework. Our implementation and datasets are available at https://github.com/NVlabs/FUNIT

Yksityiskohdat

AlkuperäiskieliEnglanti
OtsikkoProceedings of the International Conference on Computer Vision (ICCV2019)
TilaHyväksytty/In press - lokakuuta 2019
OKM-julkaisutyyppiA4 Artikkeli konferenssijulkaisuussa
TapahtumaIEEE International Conference on Computer Vision - Seoul, Etelä-Korea
Kesto: 27 lokakuuta 20192 marraskuuta 2019
http://iccv2019.thecvf.com/

Conference

ConferenceIEEE International Conference on Computer Vision
LyhennettäICCV
MaaEtelä-Korea
KaupunkiSeoul
Ajanjakso27/10/201902/11/2019
www-osoite

ID: 40342569