Corpus ID: 219636053

Training Generative Adversarial Networks with Limited Data

@article{Karras2020TrainingGA,
  title={Training Generative Adversarial Networks with Limited Data},
  author={Tero Karras and Miika Aittala and Janne Hellsten and Samuli Laine and Jaakko Lehtinen and Timo Aila},
  journal={ArXiv},
  year={2020},
  volume={abs/2006.06676}
}
  • Tero Karras, Miika Aittala, +3 authors Timo Aila
  • Published 2020
  • Computer Science, Mathematics
  • ArXiv
  • Training generative adversarial networks (GAN) using too little data typically leads to discriminator overfitting, causing training to diverge. We propose an adaptive discriminator augmentation mechanism that significantly stabilizes training in limited data regimes. The approach does not require changes to loss functions or network architectures, and is applicable both when training from scratch and when fine-tuning an existing GAN on another dataset. We demonstrate, on several datasets, that… CONTINUE READING

    Citations

    Publications citing this paper.
    SHOWING 1-2 OF 2 CITATIONS

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 52 REFERENCES

    Analyzing and Improving the Image Quality of StyleGAN

    VIEW 17 EXCERPTS

    Improved Training of Wasserstein GANs

    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL

    Freeze Discriminator: A Simple Baseline for Fine-tuning GANs

    VIEW 7 EXCERPTS
    HIGHLY INFLUENTIAL

    Generative Adversarial Networks

    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL

    Improved Consistency Regularization for GANs

    VIEW 6 EXCERPTS
    HIGHLY INFLUENTIAL

    PA-GAN: Improving GAN Training by Progressive Augmentation

    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL

    A U-Net Based Discriminator for Generative Adversarial Networks

    VIEW 8 EXCERPTS
    HIGHLY INFLUENTIAL