Hierarchical Variational Autoencoders (VAEs) are among the most popular likelihood-based generative models. There is rather a consensus that the top-down hierarchical VAEs allow to effectively learn deep latent structures and avoid problems like the posterior collapse. Here, we show that it is not necessarily the case and the problem of collapsing posteriors remains. To discourage the posterior collapse, we propose a new deep hierarchical VAE with a partly fixed encoder, specifically, we use Discrete Cosine Transform to obtain top latent variables. In a series of experiments, we observe that the proposed modification allows us to achieve better utilization of the latent space. Further, we demonstrate that the proposed approach can be useful for compression and robustness to adversarial attacks.

翻译：等级变化式自动自动转换器(VAE)是最受欢迎的基于概率的基因模型之一。 相反,人们一致认为,自上而下等级的VAE能够有效地学习深层潜伏结构,避免后台崩溃等问题。在这里,我们表明,情况不一定如此,后台崩溃的问题依然存在。为阻止后台崩溃,我们提议一个新的深层VAE,配有部分固定的编码器,具体地说,我们使用Discrete Cosine变异器获取最高潜伏变量。在一系列实验中,我们观察到,拟议的修改使我们能够更好地利用潜伏空间。此外,我们证明,拟议的方法对于压缩和稳健地应对对抗性攻击是有用的。