Łukasz Struski, Jacek Tabor, Igor Podolak, Aleksandra Nowak
Published 2019-04-06Version 1
We show how to construct smooth and realistic interpolations for generative models, with arbitrary, not necessarily Gaussian, prior. The crucial idea is based on the construction on the realisticity index of a curve, which maximisation, as we show, leads to a search of a geodesic with respect to the corresponding Riemann structure.
Discriminative Multimodal Learning via Conditional Priors in Generative Models
Unsupervised Meta-Learning through Latent-Space Interpolation in Generative Models
Generative Models For Deep Learning with Very Scarce Data
![QR code for arXiv:1904.03445 [cs.LG]](http://oss.arxitics.com/images/favicon.svg)