Few-shot Image Generation with Mixup-based Distance Learning. (arXiv:2111.11672v2 [cs.CV] UPDATED)

Producing diverse and realistic images with generative models such as GANs
typically requires large scale training with vast amount of images. GANs
trained with limited data can easily memorize few training samples and display
undesirable properties like "stairlike" latent space where interpolation in the
latent space yields discontinuous transitions in the output space. In this
work, we consider a challenging task of pretraining-free few-shot image
synthesis, and seek to train existing generative models with minimal
overfitting and mode collapse. We …

arxiv cv distance learning generation image image generation learning