FakeCLR: Exploring Contrastive Learning for Solving Latent Discontinuity in Data-Efficient GANs. (arXiv:2207.08630v2 [cs.CV] UPDATED)

Data-Efficient GANs (DE-GANs), which aim to learn generative models with a
limited amount of training data, encounter several challenges for generating
high-quality samples. Since data augmentation strategies have largely
alleviated the training instability, how to further improve the generative
performance of DE-GANs becomes a hotspot. Recently, contrastive learning has
shown the great potential of increasing the synthesis quality of DE-GANs, yet
related principles are not well explored. In this paper, we revisit and compare
different contrastive learning strategies in DE-GANs, …

arxiv cv data discontinuity gans learning