论文标题
在反散射的潜在空间中对非线性依赖性建模
Modelling nonlinear dependencies in the latent space of inverse scattering
论文作者
论文摘要
Angles和Mallat在2018年提出的反向散射问题涉及训练深层神经网络以颠倒应用于图像的散射变换。训练了这样的网络后，可以将其用作生成模型，因为我们可以从散射系数的主要成分的分布中进行采样。为此，Angles和Mallat只是使用独立高斯人的样品。但是，如本文所示，实际上，感兴趣的分布远非正常，并且在不同系数之间可能存在不可忽略的依赖关系。这激发了使用模型进行此分布，从而允许变量之间的非线性依赖关系。在本文中，探索了两个这样的模型，即变异自动编码器和一个生成对抗网络。我们证明获得的结果在某些数据集上可能非常现实，并且看起来比角度和Mallat产生的结果更好。进行的荟萃分析还显示了与现有图像的现有生成模型相比，就其训练过程的效率而言，这种构建的生成模型的实践优势明显。
The problem of inverse scattering proposed by Angles and Mallat in 2018, concerns training a deep neural network to invert the scattering transform applied to an image. After such a network is trained, it can be used as a generative model given that we can sample from the distribution of principal components of scattering coefficients. For this purpose, Angles and Mallat simply use samples from independent Gaussians. However, as shown in this paper, the distribution of interest can actually be very far from normal and non-negligible dependencies might exist between different coefficients. This motivates using models for this distribution that allow for non-linear dependencies between variables. Within this paper, two such models are explored, namely a Variational AutoEncoder and a Generative Adversarial Network. We demonstrate the results obtained can be extremely realistic on some datasets and look better than those produced by Angles and Mallat. The conducted meta-analysis also shows a clear practical advantage of such constructed generative models in terms of the efficiency of their training process compared to existing generative models for images.
