This repo provides the weights for LandSegmenter, a task-specific Foundation Model (FM) for Land Use and Land Cover (LULC) mapping, characterized by high flexibility in both inputs (multi-band, multi-resolution imagery) and outputs (customizable category definitions), supporting both zero-shot inference and fine-tuning.
LandSegmenter is the first LULC FM trained with LAS, designed with high flexibility to handle diverse input modalities and customizable category settings. It builds on
SAM2's backbone for robust multi-scale spatial representation, further enhanced by multispectral features from
DOFA and high-frequency components for refined structural details. A text-based prompter derived from
GeoRSCLIP, which takes class names as inputs, further strengthens its semantic understanding, enabling concept-aware and adaptable segmentation across heterogeneous data sources
Please refer to the GitHub repository for implementation details.
