Unsupervised domain adaptation (UDA) aims to enable autonomous vehicles to understand complex road information without semantic labels. However, traditional UDA methods face challenges under adverse conditions, leading to suboptimal segmentation. These methods grapple with two core problems: distinguishing visually similar classes and misclassifying sudden dynamic classes in the target domain. To tackle these issues, we introduce Adaptive Masking and Structure-Constraint Learning (AMSC), comprising: (1) Adaptive Masking module for context leverage. (2) Structure-Constraint Learning to address structural loss from masking. Through these modules, we effectively tackle the aforementioned challenges. Simulation results showcase AMSC's state-of-the-art UDA performance, achieving a mIoU of 73.2 on Cityscapes to ACDC, a standard benchmark for normal-to-adverse semantic segmentation in UDA.