论文标题
关于变异自动编码器的几何视角
A Geometric Perspective on Variational Autoencoders
论文作者
论文摘要
本文通过采取完全几何学的角度引入了对变量自动编码器框架的新解释。我们认为，香草vae自然地揭示了其潜在空间中的riemannian结构，并且考虑到这些几何方面可以导致更好的插值和改进的生成程序。这种新提出的抽样方法包括从均匀的分布中进行采样，该分布本质地从学习的Riemannian潜在空间中得出，我们表明，使用此方案可以使Vanilla Vae竞争性且比几个基准数据集中更先进的版本更好。由于已知生成模型对训练样品的数量很敏感，因此我们还强调了该方法在低数据状态下的鲁棒性。
This paper introduces a new interpretation of the Variational Autoencoder framework by taking a fully geometric point of view. We argue that vanilla VAE models unveil naturally a Riemannian structure in their latent space and that taking into consideration those geometrical aspects can lead to better interpolations and an improved generation procedure. This new proposed sampling method consists in sampling from the uniform distribution deriving intrinsically from the learned Riemannian latent space and we show that using this scheme can make a vanilla VAE competitive and even better than more advanced versions on several benchmark datasets. Since generative models are known to be sensitive to the number of training samples we also stress the method's robustness in the low data regime.
