Learning to Generate Samples from Noise through Infusion Training-猫眼课题宝

DOI：

发表时间：

2017-03

期刊：

ArXiv

影响因子：

通讯作者：

中科院分区：

其他

文献类型：

作者：

Florian Bordes;S. Honari;Pascal Vincent

在这项工作中，我们研究了一种新的训练过程，以学习生成模型作为马尔可夫链的转移算子，这样，当重复应用于非结构化随机噪声样本时，它会将其降噪为与训练集中的目标分布相匹配的样本。学习这种渐进式去噪操作的新训练过程涉及从与用于在没有去噪目标的情况下生成的模型链略有不同的链中进行采样。在训练链中，我们从训练目标示例中注入信息，我们希望链以高概率到达。由此学习的转换算子能够在少量步骤中产生质量和变化的样本。实验结果表明，与基本生成对抗网生成的样本相比，

In this work, we investigate a novel training procedure to learn a generative model as the transition operator of a Markov chain, such that, when applied repeatedly on an unstructured random noise sample, it will denoise it into a sample that matches the target distribution from the training set. The novel training procedure to learn this progressive denoising operation involves sampling from a slightly different chain than the model chain used for generation in the absence of a denoising target. In the training chain we infuse information from the training target example that we would like the chains to reach with a high probability. The thus learned transition operator is able to produce quality and varied samples in a small number of steps. Experiments show competitive results compared to the samples generated with a basic Generative Adversarial Net

Learning to Generate Samples from Noise through Infusion Training

文献摘要

被引文献

相似文献