论文标题
变异自动编码器的差异
Variance Loss in Variational Autoencoders
论文作者
论文摘要
在本文中,我们重点介绍了各种自动编码器的主要问题,这是从不同的网络体系结构和数据集进行的广泛实验中表明的:生成的数据的差异明显低于培训数据的差异。由于通常使用比较(FID)的指标来评估生成模型,该指标比较了(FID),该指标比较了(特征)真实图像与生成的图像的分布,因此差异损失通常会导致分数降级。这个问题在两个阶段的环境中尤其重要,在该环境中,我们使用第二个VAE在第一个VAE的潜在空间中进行采样。小方差在潜在变量的实际分布与第二VAE产生的变量之间产生了不匹配,这阻碍了第二阶段的有益效应。将第二VAE的输出重新归一化,向预期的正常球形分布,我们在产生的样品的质量中突然爆发,也以FID的作证。
In this article, we highlight what appears to be major issue of Variational Autoencoders, evinced from an extensive experimentation with different network architectures and datasets: the variance of generated data is significantly lower than that of training data. Since generative models are usually evaluated with metrics such as the Frechet Inception Distance (FID) that compare the distributions of (features of) real versus generated images, the variance loss typically results in degraded scores. This problem is particularly relevant in a two stage setting, where we use a second VAE to sample in the latent space of the first VAE. The minor variance creates a mismatch between the actual distribution of latent variables and those generated by the second VAE, that hinders the beneficial effects of the second stage. Renormalizing the output of the second VAE towards the expected normal spherical distribution, we obtain a sudden burst in the quality of generated samples, as also testified in terms of FID.