资源分类
》 资源 》论文》Disentangling by Factorising

Disentangling by Factorising

2020-03-16 | |  42 |   32 |   0

Abstract

We define and address the problem of unsupervised learning of disentangled representations on data generated from independent factors of variation. We propose FactorVAE, a method that disentangles by encouraging the distribution of representations to be factorial and hence independen across the dimensions. We show that it improves upon ?-VAE by providing a better trade-off between disentanglement and reconstruction quality. Moreover, we highlight the problems of a commonly used disentanglement metric and introduce a new metric that does not suffer from them.

上一篇：Learning to Act in Decentralized Partially Observable MDPs

下一篇：Learning in Integer Latent Variable Models with Nested Automatic Differentiation

用户评价
全部评价

热门资源

  • The Variational S...

    Unlike traditional images which do not offer in...

  • Learning to Predi...

    Much of model-based reinforcement learning invo...

  • Stratified Strate...

    In this paper we introduce Stratified Strategy ...

  • A Mathematical Mo...

    Direct democracy, where each voter casts one vo...

  • Rating-Boosted La...

    The performance of a recommendation system reli...