arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2203.05074cs.LGcs.AIcs.CV
收藏

传递信息论及其在深层生成模型中的应用

The Transitive Information Theory and its Application to Deep Generative Models

School of Computing(计算学院);University of Eastern Finland(东芬兰大学);School of Medicine(医学院)

Trung Ngo, Najwa Laabid, Ville Hautamäki, Merja Heinäniemi

摘要:

巧合的是,变分自编码器(VAE)可以在两个相反的方向上被推动,利用强大的解码器模型来生成逼真的图像,但折叠学习的表示,或者增加正则化系数来解开表示,但最终生成模糊的示例。现有的方法缩小了压缩和重建之间的率失真权衡的问题。我们认为,一个好的重建模型学习高容量的潜伏期,编码更多的细节,但是,它的使用受到两个主要问题的阻碍:先验是随机噪声,这是完全脱离后验,不允许在生成可控性;平均场变分推理不强制执行层次结构,这使得重组这些单位到合理的新的输出不可行的任务。因此,我们开发了一个系统,学习层次结构的解开表示与重组机制的学习表示泛化。这是通过引入最小量的感应偏置来学习VAE的可控先验来实现的。该思想得到了传递信息论的支持,即两个目标变量之间的互信息可以通过第三个变量的互信息交替地最大化,从而绕过了VAE设计中的率失真瓶颈。特别是,我们表明,我们的模型,名为SemafoVAE(灵感来自类似的概念,在计算机科学),可以生成高质量的例子,在一个可控的方式,执行顺利遍历的解开的因素和干预在不同级别的表示层次。

英文摘要:

Paradoxically, a Variational Autoencoder (VAE) could be pushed in two opposite directions, utilizing powerful decoder model for generating realistic images but collapsing the learned representation, or increasing regularization coefficient for disentangling representation but ultimately generating blurry examples. Existing methods narrow the issues to the rate-distortion trade-off between compression and reconstruction. We argue that a good reconstruction model does learn high capacity latents that encode more details, however, its use is hindered by two major issues: the prior is random noise which is completely detached from the posterior and allow no controllability in the generation; mean-field variational inference doesn't enforce hierarchy structure which makes the task of recombining those units into plausible novel output infeasible. As a result, we develop a system that learns a hierarchy of disentangled representation together with a mechanism for recombining the learned representation for generalization. This is achieved by introducing a minimal amount of inductive bias to learn controllable prior for the VAE. The idea is supported by here developed transitive information theory, that is, the mutual information between two target variables could alternately be maximized through the mutual information to the third variable, thus bypassing the rate-distortion bottleneck in VAE design. In particular, we show that our model, named SemafoVAE (inspired by the similar concept in computer science), could generate high-quality examples in a controllable manner, perform smooth traversals of the disentangled factors and intervention at a different level of representation hierarchy.

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。

↑