MaGNET: Uniform Sampling from Deep Generative Network Manifolds Without Retraining. (arXiv:2110.08009v3 [cs.LG] UPDATED)

Web: http://arxiv.org/abs/2110.08009

Deep Generative Networks (DGNs) are extensively employed in Generative
Adversarial Networks (GANs), Variational Autoencoders (VAEs), and their
variants to approximate the data manifold and distribution. However, training
samples are often distributed in a non-uniform fashion on the manifold, due to
costs or convenience of collection. For example, the CelebA dataset contains a
large fraction of smiling faces. These inconsistencies will be reproduced when
sampling from the trained DGN, which is not always preferred, e.g., for
fairness or data augmentation. In …

arxiv deep network uniform