The imaging process of optical remote sensing images (RSIs) is easily affected by external conditions. Therefore, RSIs under different imaging conditions often show color differences, resulting in feature distribution differences between the source and target domains, hindering the migration of semantic segmentation models between domains. Currently, most domain adaptation (DA) methods are for single-source and single-target domains. Here, we proposed a novel and concise method, coined mixed-DA network (MDANet), for the adaptation of patch images of multisource and multitarget domains and for reducing the distribution differences of different patch images by projecting them onto the virtual center of a mixed domain. MDANet is a lightweight and self-supervised network that can be grafted with any semantic segmentation model. Our method significantly improved the segmentation accuracy of semantic segmentation models and showed higher stability and competitiveness than the existing methods.

中文翻译：

---

众包服务用户：为自己工作并获得奖励


光学遥感图像（RSI）的成像过程容易受到外界条件的影响。因此，不同成像条件下的RSI经常表现出颜色差异，导致源域和目标域之间的特征分布差异，阻碍语义分割模型在域之间的迁移。目前，大多数域适应（DA）方法都是针对单源和单目标域的。在这里，我们提出了一种新颖而简洁的方法，即混合DA网络（MDANet），用于适应多源和多目标域的补丁图像，并通过将不同补丁图像投影到混合DA网络的虚拟中心来减少不同补丁图像的分布差异。领域。 MDANet 是一个轻量级的自监督网络，可以与任何语义分割模型嫁接。我们的方法显着提高了语义分割模型的分割精度，并且比现有方法表现出更高的稳定性和竞争力。