beta-vae 超越 infogan的无监督学习框架--效果更新

beta-VAE: Learning Basic Visual Concepts with a Constrained Variational Framework

代码： https://github.com/crcrpar/chainer-VAE/blob/master/train_vae.py

论文 http://openreview.net/pdf?id=Sy2fzU9gl 或 https://pan.baidu.com/s/1c2nGmwK

Abstract: Learning an interpretable factorised representation of the independent data generative factors of the world without supervision

is an important precursor for the development of artificial intelligence that is able to learn and reason in the same way that humans do.

We introduce beta-VAE, a new state-of-the-art framework for automated discovery of interpretable factorised latent representations from raw image data in a completely unsupervised manner.

Our approach is a modification of the variational autoencoder (VAE) framework.

We introduce an adjustable hyperparameter beta that balances latent channel capacity and independence constraints with reconstruction accuracy.

We demonstrate that beta-VAE with appropriately tuned beta > 1 qualitatively outperforms VAE (beta = 1), as well as state of the art unsupervised (InfoGAN) and semi-supervised (DC-IGN) approaches to disentangled factor learning on a variety of datasets (celebA, faces and chairs).

Furthermore, we devise a protocol to quantitatively compare the degree of disentanglement learnt by different models, and show that our approach also significantly outperforms all baselines quantitatively.

Unlike InfoGAN, beta-VAE is stable to train, makes few assumptions about the data and relies on tuning a single hyperparameter, which can be directly optimised through a hyper parameter search using weakly labelled data or through heuristic visual inspection for purely unsupervised data.

TL;DR: We introduce beta-VAE, a new state-of-the-art framework for automated discovery of interpretable factorised latent representations from raw image data in a completely unsupervised manner.

相关图：

infogan的缺点：

1 不稳定

2 需要先验知识

3 分布选择和noise latent选择影响后续

4 缺少 principled inference network