We introduce several techniques for sampling and visualizing the latent
spaces of generative models. Replacing linear interpolation with spherical
linear interpolation prevents diverging from a model's prior distribution and
produces sharper samples. J-Diagrams and MINE grids are introduced as
visualizations of manifolds created by analogies and nearest neighbors. We
demonstrate two new techniques for deriving attribute vectors: bias-corrected
vectors with data replication and synthetic vectors with data augmentation.
Binary classification using attribute vectors is presented as a technique
supporting quantitative analysis of the latent space. Most techniques are
intended to be independent of model type and examples are shown on both
Variational Autoencoders and Generative Adversarial Networks.

介绍了几种用于采样和可视化生成模型的潜在空间的技术，包括通过球面线性插值代替线性插值以防止背离模型先验分布并生成更清晰的样本，使用 J-Diagrams 和 MINE grids 可视化类比和最近邻创造的流形，提出使用数据复制的偏差校正向量和使用数据增广的合成向量来推导属性向量的两种新技术，提出使用属性向量进行二元分类以支持潜在空间的定量分析，这些技术大多数都是独立于模型类型的，演示了变分自编码器和生成对抗网络的示例。