Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Next revision
Previous revision
manifold_traversal [2016/12/13 16:08]
127.0.0.1 external edit
manifold_traversal [2018/02/15 18:31]
admin
Line 116: Line 116:
 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. 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.
  
 +https://​arxiv.org/​pdf/​1711.01970.pdf ​
 +Optimal transport maps for distribution preserving operations on latent spaces of Generative Models
  
 + In this paper, we show that the latent space operations used in the literature so far induce a distribution mismatch between the resulting outputs and the prior distribution the model was trained on. To address this, we propose to use distribution matching transport maps to ensure that such latent space operations preserve the prior distribution,​ while minimally modifying the original operation. ​
  
 +https://​github.com/​lmcinnes/​umap UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction