Generative Adversarial Networks (GANs) and their variants have achieved remarkable success on natural images. However, their performance degrades when applied to remote sensing (RS) images, and the discriminator often suffers from the overfitting problem. In this paper, we examine the differences between natural and RS images and find that the intrinsic dimensions of RS images are much lower than those of natural images. As the discriminator is more susceptible to overfitting on data with lower intrinsic dimension, it focuses excessively on local characteristics of RS training data and disregards the overall structure of the distribution, leading to a faulty generation model. In respond, we propose a novel approach that leverages the real data manifold to constrain the discriminator and enhance the model performance. Specifically, we introduce a learnable information-theoretic measure to capture the real data manifold. Building upon this measure, we propose manifold alignment regularization, which mitigates the discriminator's overfitting and improves the quality of generated samples. Moreover, we establish a unified GAN framework for manifold alignment, applicable to both supervised and unsupervised RS image generation tasks.

翻译：生成对抗网络（GANs）及其变体在自然图像上取得了显著成功。然而，当应用于遥感图像时，其性能下降，且判别器常面临过拟合问题。本文通过分析自然图像与遥感图像的差异，发现遥感图像的本征维度远低于自然图像。由于判别器对低本征维度数据更易过拟合，它会过度关注遥感训练数据的局部特征而忽略其整体分布结构，导致生成模型出现偏差。为此，我们提出一种利用真实数据流形约束判别器以增强模型性能的新方法。具体而言，我们引入可学习的信息论度量来捕获真实数据流形。基于该度量，我们提出流形对齐正则化方法，可缓解判别器过拟合并提升生成样本质量。此外，我们建立了适用于有监督和无监督遥感图像生成任务的统一流形对齐GAN框架。