Few-Shot Unsupervised Image-to-Image Translation

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

Tutkimustuotos: Artikkeli kirjassa/konferenssijulkaisussaConference contributionScientificvertaisarvioitu

4 Sitaatiot (Scopus)
16 Lataukset (Pure)

Abstrakti

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
AlkuperäiskieliEnglanti
OtsikkoProceedings of the International Conference on Computer Vision (ICCV2019)
KustantajaIEEE
ISBN (elektroninen)9781728148038
DOI - pysyväislinkit
TilaJulkaistu - helmikuuta 2020
OKM-julkaisutyyppiA4 Artikkeli konferenssijulkaisuussa
TapahtumaIEEE International Conference on Computer Vision - Seoul, Etelä-Korea
Kesto: 27 lokakuuta 20192 marraskuuta 2019
http://iccv2019.thecvf.com/

Julkaisusarja

NimiProceedings of the IEEE International Conference on Computer Vision
Vuosikerta2019-October
ISSN (elektroninen)1550-5499

Conference

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

Sormenjälki Sukella tutkimusaiheisiin 'Few-Shot Unsupervised Image-to-Image Translation'. Ne muodostavat yhdessä ainutlaatuisen sormenjäljen.

  • Siteeraa tätä

    Liu, M-Y., Huang, X., Mallya, A., Karras, T., Aila, T., Lehtinen, J., & Kautz, J. (2020). Few-Shot Unsupervised Image-to-Image Translation. teoksessa Proceedings of the International Conference on Computer Vision (ICCV2019) (Proceedings of the IEEE International Conference on Computer Vision; Vuosikerta 2019-October). IEEE. https://doi.org/10.1109/ICCV.2019.01065