Foundation Models for Remote Sensing Semantic Segmentation: A Review of Architectures, Adaptations, and Prospects

Remote sensing image segmentation is a foundational task in Earth observation. With the rapid growth of remote sensing datasets in terms of scale, modality diversity, semantic openness, and spatio-temporal complexity, the field is evolving from task-specific supervised learning toward foundation-model paradigms. Recent advances in foundation models—including Transformer-based architectures, Mamba-based state space models (SSMs), prompt-driven frameworks such as the Segment Anything Model (SAM), and self-supervised or multimodal pre-training—have profoundly reshaped the technical landscape of remote sensing image segmentation. This paper reviews recent progress from the perspectives of dataset evolution, model architectures, and downstream adaptation strategies, covering parameter-efficient fine-tuning, prompt engineering, few-shot and zero-shot learning, open-vocabulary segmentation, and domain adaptation. We further analyze core challenges including the tension between representation generality and remote sensing-specific adaptation, multimodal sensor heterogeneity, and the insufficiency of existing evaluation ecosystems. Finally, we discuss future directions toward remote-sensing-native pre-training, lightweight edge deployment, and unified open-world geospatial foundation models.