Corpus ID: 49276840

One-Shot Unsupervised Cross Domain Translation

@inproceedings{Benaim2018OneShotUC,
  title={One-Shot Unsupervised Cross Domain Translation},
  author={Sagie Benaim and L. Wolf},
  booktitle={NeurIPS},
  year={2018}
}
  • Sagie Benaim, L. Wolf
  • Published in NeurIPS 2018
  • Computer Science
  • Given a single image x from domain A and a set of images from domain B, our task is to generate the analogous of x in B. [...] Key Method Our method follows a two step process. First, a variational autoencoder for domain B is trained. Then, given the new sample x, we create a variational autoencoder for domain A by adapting the layers that are close to the image in order to directly fit x, and only indirectly adapt the other layers. Our experiments indicate that the new method does as well, when trained on one…Expand Abstract

    Figures, Tables, and Topics from this paper.

    Explore Further: Topics Discussed in This Paper

    Bidirectional One-Shot Unsupervised Domain Mapping
    • 8
    • Highly Influenced
    • PDF
    Few-Shot Unsupervised Image-to-Image Translation
    • 110
    • PDF
    ZstGAN: An Adversarial Approach for Unsupervised Zero-Shot Image-to-Image Translation
    • 4
    • PDF
    Modular domain-to-domain translation network
    Learning to Transfer: Unsupervised Meta Domain Translation
    • 2
    • PDF
    Domain Adaptive Image-to-Image Translation
    • 1
    • PDF
    Semi-Supervised Learning for Few-Shot Image-to-Image Translation
    • 1
    • PDF

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 34 REFERENCES
    Unsupervised Cross-Domain Image Generation
    • 547
    • PDF
    Unsupervised Image-to-Image Translation Networks
    • 1,099
    • PDF
    DualGAN: Unsupervised Dual Learning for Image-to-Image Translation
    • 862
    • PDF
    Image-to-Image Translation with Conditional Adversarial Networks
    • 6,290
    • Highly Influential
    • PDF
    One-Sided Unsupervised Domain Mapping
    • 105
    • PDF
    Generative Adversarial Nets
    • 17,848
    • PDF
    Perceptual Losses for Real-Time Style Transfer and Super-Resolution
    • 3,437
    • Highly Influential
    • PDF
    Coupled Generative Adversarial Networks
    • 856
    • Highly Influential
    • PDF