Hyperspherical Variational Auto-Encoders

Hyperspherical VAE: 为隐变量引入vMF分布.

A Batch Normalized Inference Network Keeps the KL Vanishing Away

BN-VAE: 通过批量归一化缓解KL散度消失问题.

Variational Inference of Disentangled Latent Concepts from Unlabeled Observations

DIP-VAE: 分离推断先验VAE.

Structured Disentangled Representations

HFVAE：通过层级分解VAE实现结构化解耦表示.

Disentangling by Factorising

FactorVAE：通过分解特征表示的分布进行解耦.

Sliced-Wasserstein Autoencoder: An Embarrassingly Simple Generative Model

SWAE：引入Sliced-Wasserstein距离构造VAE.