Upload README.md with huggingface_hub

README.md

@@ -1,8 +1,26 @@
-# RSRefSeg Checkpoints
+# RSRefSeg Model Checkpoints
 
-This repository hosts two SigLIP2 + SAM checkpoints from the “Generalized Referring Expression Segmentation on Aerial Photos” project:
+Trained SigLIP2 + SAM checkpoints for referring expression segmentation on aerial imagery from **[The Aerial-D Dataset](https://huggingface.co/datasets/luisml77/aerial-d)**.
 
-- **`rsrefseg_combined.pt`** — trained on all five datasets (Aerial-D, RefSegRS, RRSIS-D, NWPU-Refer, Urban1960SatSeg) using the RSRefSeg-L configuration with `facebook/sam-vit-large`.
-- **`rsrefseg_aerial-d.pt`** — trained exclusively on the Aerial-D dataset with the standard RSRefSeg (SAM ViT-Base) setup.
+## Models
 
-Both checkpoints expect the same tokenizer/text encoder as the training codebase and can be evaluated with `rsrefseg/test.py`.
+- **`rsrefseg_combined.pt`** — Trained on 5 datasets (Aerial-D + RefSegRS + RRSIS-D + NWPU-Refer + Urban1960SatSeg). Uses RSRefSeg-L with `facebook/sam-vit-large`.
+- **`rsrefseg_aerial-d.pt`** — Trained exclusively on Aerial-D. Uses RSRefSeg-Base with `facebook/sam-vit-base`.
+
+## Usage
+
+```python
+# Load and test with the codebase
+from model import SigLipSamSegmentator
+
+model = SigLipSamSegmentator(checkpoint_path="rsrefseg_combined.pt")
+mask = model.segment(image, "the building in the top left")
+```
+
+See training/evaluation code at **[GitHub](https://github.com/luisml77/aerialseg)**.
+
+## Links
+
+- **[📊 Dataset](https://huggingface.co/datasets/luisml77/aerial-d)** - Aerial-D dataset
+- **[💻 Code](https://github.com/luisml77/aerialseg)** - Training and evaluation scripts
+- **[🌐 Project](https://luispl77.github.io/aerial-d/)** - Project page