Variational autoencoders (VAEs) often suffer from posterior collapse, which is a phenomenon in which the learned latent space becomes uninformative. This is often related to the hyperparameter resembling the data variance. It can be shown that an inappropriate choice of this hyperparameter causes the oversmoothness in the linearly approximated case and can be empirically verified for the general cases. Moreover, determining such appropriate choice becomes infeasible if the data variance is non-uniform or conditional. Therefore, we propose VAE extensions with generalized parameterizations of the data variance and incorporate maximum likelihood estimation into the objective function to adaptively regularize the decoder smoothness. The images generated from proposed VAE extensions show improved Fr\'echet inception distance (FID) on MNIST and CelebA datasets.
翻译:变化式自动对称器(VAEs)经常受到后向崩溃的影响,这是一种被学习到的潜在空间变得缺乏信息化的现象,这往往与数据差异的超参数相关,可以证明,不适当地选择这种超参数会造成线性近似情况下的超光度,并且可以对一般情况进行经验性核查。此外,如果数据差异不统一或有条件,确定这种适当选择是不可行的。因此,我们提议采用数据差异的通用参数扩展VAE,并将最大可能性估计纳入目标功能,以适应性地规范脱密光滑。拟议VAE扩展产生的图像显示,在MNIST和CeebebA数据集上,Fr\'echet 开关距离(FID)有所改善。