MDANet: Unsupervised, Mixed-Domain Adaptation for Semantic Segmentation of Remote Sensing Images

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.