论文标题
使用SAR图像的Infogan中潜在代码的分析解释
Analytical Interpretation of Latent Codes in InfoGAN with SAR Images
论文作者
论文摘要
生成的对抗网络（GAN）可以合成丰富的光真逼真的合成孔径雷达（SAR）图像。最近的一些甘斯（例如Infogan）甚至能够通过引入潜在代码来编辑合成图像的特定属性。这对于SAR图像合成至关重要，因为实际SAR图像中的目标由于成像机理而具有不同的性质。尽管Infogan在操纵性能中取得了成功，但仍然缺乏对这些潜在代码如何影响合成特性的明确解释，因此编辑特定特性通常依赖于经验试验，不可靠且耗时。在本文中，我们表明潜在代码被散布，以非线性方式影响SAR图像的性质。通过引入一些潜在代码的属性估计器，我们能够提供一个完全分析的非线性模型，以分解潜在代码和不同属性之间的纠缠因果关系。定性和定量实验结果进一步表明，可以通过潜在代码来计算这些性质，而具有所需的特性可以估计令人满意的潜在代码。在这种情况下，属性可以按照我们的期望来操纵潜在代码。
Generative Adversarial Networks (GANs) can synthesize abundant photo-realistic synthetic aperture radar (SAR) images. Some recent GANs (e.g., InfoGAN), are even able to edit specific properties of the synthesized images by introducing latent codes. It is crucial for SAR image synthesis since the targets in real SAR images are with different properties due to the imaging mechanism. Despite the success of InfoGAN in manipulating properties, there still lacks a clear explanation of how these latent codes affect synthesized properties, thus editing specific properties usually relies on empirical trials, unreliable and time-consuming. In this paper, we show that latent codes are disentangled to affect the properties of SAR images in a non-linear manner. By introducing some property estimators for latent codes, we are able to provide a completely analytical nonlinear model to decompose the entangled causality between latent codes and different properties. The qualitative and quantitative experimental results further reveal that the properties can be calculated by latent codes, inversely, the satisfying latent codes can be estimated given desired properties. In this case, properties can be manipulated by latent codes as we expect.
