arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1904.07099cs.CVcs.AI
收藏

使用自动编码器处理简单几何属性

Processsing Simple Geometric Attributes with Autoencoders

LTCI, Télécom ParisTech, Université Paris Saclay(巴黎-萨克雷大学巴黎高等电信学院LTCI);CNRS MAP5, Université Paris Descartes(法国国家科学研究中心MAP5,巴黎笛卡尔大学)

Alasdair Newson, Andrés Almansa, Yann Gousseau, Saïd Ladjal

摘要:

图像合成是现代深度学习的核心问题,许多最新的架构,如自动编码器和生成对抗网络,在高度复杂的数据上产生了惊人的结果,如人脸或风景的图像。虽然这些结果开辟了广泛的新的,先进的合成应用,也有一个严重缺乏理论理解这些网络如何工作。这导致了广泛的实际问题,例如训练困难,倾向于以很少或没有变化的方式对图像进行采样,以及泛化问题。在本文中,我们建议分析最简单的生成网络,自动编码器,编码和解码两个简单的几何属性:大小和位置的能力。我们认为,为了理解更复杂的任务,有必要首先了解这些网络如何处理简单的属性。对于第一个属性,我们分析的情况下,图像的中心磁盘与可变半径。我们解释了自动编码器如何将这些图像投影到一个潜在的最小维度的空间,即标量。特别是,我们描述了一个封闭形式的解决方案,在一个没有偏见的网络中的解码训练问题,并表明在训练过程中,网络确实找到了这个解决方案。然后,我们研究最好的正则化方法,这些方法可以产生泛化良好的网络。对于第二个属性,位置,我们看看狄拉克δ函数的编码和解码,也称为“独热”向量。我们描述了一个手工制作的过滤器,可以完美地实现编码,并表明网络在训练过程中自然地找到这个过滤器。我们还通过实验表明,如果以适当的方式对数据集进行采样,则可以实现解码。

英文摘要:

Image synthesis is a core problem in modern deep learning, and many recent architectures such as autoencoders and Generative Adversarial networks produce spectacular results on highly complex data, such as images of faces or landscapes. While these results open up a wide range of new, advanced synthesis applications, there is also a severe lack of theoretical understanding of how these networks work. This results in a wide range of practical problems, such as difficulties in training, the tendency to sample images with little or no variability, and generalisation problems. In this paper, we propose to analyse the ability of the simplest generative network, the autoencoder, to encode and decode two simple geometric attributes : size and position. We believe that, in order to understand more complicated tasks, it is necessary to first understand how these networks process simple attributes. For the first property, we analyse the case of images of centred disks with variable radii. We explain how the autoencoder projects these images to and from a latent space of smallest possible dimension, a scalar. In particular, we describe a closed-form solution to the decoding training problem in a network without biases, and show that during training, the network indeed finds this solution. We then investigate the best regularisation approaches which yield networks that generalise well. For the second property, position, we look at the encoding and decoding of Dirac delta functions, also known as `one-hot' vectors. We describe a hand-crafted filter that achieves encoding perfectly, and show that the network naturally finds this filter during training. We also show experimentally that the decoding can be achieved if the dataset is sampled in an appropriate manner.

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。

↑