arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1902.02102stat.MLcs.CVcs.LG
收藏

BIVA:一个用于生成式建模的隐变量的非常深的层次结构

BIVA: A Very Deep Hierarchy of Latent Variables for Generative Modeling

Corti(Corti公司);Unumed(Unumed公司);Technical University of Denmark(丹麦技术大学)

Lars Maaløe, Marco Fraccaro, Valentin Liévin, Ole Winther

摘要:

随着变分自动编码器(VAE)的引入,概率潜变量模型作为强大的生成模型重新受到关注。然而,它们在测试可能性和生成样本的质量方面的性能已经被没有随机单元的自回归模型所超越。此外,基于流的模型最近被证明是一个有吸引力的替代方案,以及高维数据的规模。在本文中,我们通过构建VAE模型,可以有效地利用一个深层次的随机变量和模型复杂的协方差结构的性能差距。我们介绍了双向推理变分自动编码器(BIVA),其特征在于一个跳跃连接的生成模型和一个由双向随机推理路径形成的推理网络。我们表明,BIVA达到了最先进的测试似然,生成清晰和连贯的自然图像,并使用隐变量的层次结构来捕获数据分布的不同方面。我们观察到,BIVA,在最近的结果相反,可以用于异常检测。我们把这归因于隐变量的层次结构,它能够提取高层次的语义特征。最后,我们将BIVA扩展到半监督分类任务,并证明它通过生成对抗网络实现了最先进的结果。

英文摘要:

With the introduction of the variational autoencoder (VAE), probabilistic latent variable models have received renewed attention as powerful generative models. However, their performance in terms of test likelihood and quality of generated samples has been surpassed by autoregressive models without stochastic units. Furthermore, flow-based models have recently been shown to be an attractive alternative that scales well to high-dimensional data. In this paper we close the performance gap by constructing VAE models that can effectively utilize a deep hierarchy of stochastic variables and model complex covariance structures. We introduce the Bidirectional-Inference Variational Autoencoder (BIVA), characterized by a skip-connected generative model and an inference network formed by a bidirectional stochastic inference path. We show that BIVA reaches state-of-the-art test likelihoods, generates sharp and coherent natural images, and uses the hierarchy of latent variables to capture different aspects of the data distribution. We observe that BIVA, in contrast to recent results, can be used for anomaly detection. We attribute this to the hierarchy of latent variables which is able to extract high-level semantic features. Finally, we extend BIVA to semi-supervised classification tasks and show that it performs comparably to state-of-the-art results by generative adversarial networks.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑