Generative adversarial networks (GANs) have achieved remarkable progress in the natural image field. However, when applying GANs in the remote sensing (RS) image generation task, we discover an extraordinary phenomenon: the GAN model is more sensitive to the size of training data for RS image generation than for natural image generation. In other words, the generation quality of RS images will change significantly with the number of training categories or samples per category. In this paper, we first analyze this phenomenon from two kinds of toy experiments and conclude that the amount of feature information contained in the GAN model decreases with reduced training data. Based on this discovery, we propose two innovative adjustment schemes, namely Uniformity Regularization (UR) and Entropy Regularization (ER), to increase the information learned by the GAN model at the distributional and sample levels, respectively. We theoretically and empirically demonstrate the effectiveness and versatility of our methods. Extensive experiments on the NWPU-RESISC45 and PatternNet datasets show that our methods outperform the well-established models on RS image generation tasks.

翻译：生成对抗网络（GANs）在自然图像领域取得了显著进展。然而，当我们将GAN应用于遥感（RS）图像生成任务时，发现了一个异常现象：在遥感图像生成中，GAN模型对训练数据规模比自然图像生成更为敏感。换言之，遥感图像的生成质量会随训练类别数量或每类训练样本数量的变化而发生显著改变。本文首先通过两类简易实验分析该现象，得出GAN模型包含的特征信息量随训练数据减少而降低的结论。基于这一发现，我们提出两种创新性调整方案——均匀性正则化（UR）和熵正则化（ER），分别从分布层面和样本层面增加GAN模型学习的信息量。我们从理论和实证层面证明了方法的有效性和普适性。在NWPU-RESISC45和PatternNet数据集上的大量实验表明，本方法在遥感图像生成任务上优于现有成熟模型。