Investigating Under and Overfitting in Wasserstein Generative Adversarial Networks

2019 
We investigate under and overfitting in Generative Adversarial Networks (GANs), using discriminators unseen by the generator to measure generalization. We find that the model capacity of the discriminator has a significant effect on the generator's model quality, and that the generator's poor performance coincides with the discriminator underfitting. Contrary to our expectations, we find that generators with large model capacities relative to the discriminator do not show evidence of overfitting on CIFAR10, CIFAR100, and CelebA.
    • Correction
    • Source
    • Cite
    • Save
    • Machine Reading By IdeaReader
    27
    References
    8
    Citations
    NaN
    KQI
    []