Unsupervised domain adaptation for VHR urban scene segmentation via prompted foundation model-based hybrid training joint-optimized network.
(2025)
Journal Article
LYU, S., ZHAO, Q., SUN, Y., CHENG, G., HE, Y., WANG, G., REN, J. and SHI, Z. 2025. Unsupervised domain adaptation for VHR urban scene segmentation via prompted foundation model based hybrid training joint-optimized network. IEEE transactions on geoscience and remote sensing [online], 63, article number 4409117. Available from: https://doi.org/10.1109/tgrs.2025.3564216
Unsupervised Domain Adaptation for Remote Sensing Semantic Segmentation (UDA-RSSeg) is to adapt a model trained on the source domain data to the target domain samples, thereby minimizing the need for annotated data across diverse remote sensing scene... Read More about Unsupervised domain adaptation for VHR urban scene segmentation via prompted foundation model-based hybrid training joint-optimized network..