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, an extraordinary phenomenon is observed: 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. Then we establish a structural causal model (SCM) of the data generation process and interpret the generated data as the counterfactuals. Based on this SCM, we theoretically prove that the quality of generated images is positively correlated with the amount of feature information. This provides insights for enriching the feature information learned by the GAN model during training. Consequently, 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 three RS datasets and two natural datasets show that our methods outperform the well-established models on RS image generation tasks. The source code is available at https://github.com/rootSue/Causal-RSGAN.

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，当将GAN应用于遥感（RS）图像生成任务时，观察到一种异常现象：用于遥感图像生成的GAN模型对训练数据规模的敏感性显著高于自然图像生成。换言之，遥感图像的生成质量会随训练类别数或每类样本数量的变化而发生显著改变。本文首先通过两类玩具实验分析这一现象，得出GAN模型中包含的特征信息量随训练数据减少而降低的结论。随后，我们构建了数据生成过程的结构因果模型（SCM），并将生成数据解释为反事实。基于该SCM，我们从理论上证明生成图像质量与特征信息量呈正相关，这为在训练过程中丰富GAN模型学习的特征信息提供了启示。因此，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。我们从理论和实证两方面证明了方法的有效性和通用性。在三个遥感数据集和两个自然数据集上的大量实验表明，我们的方法在遥感图像生成任务上优于现有成熟模型。源代码已发布于 https://github.com/rootSue/Causal-RSGAN。