Improve model card: Add metadata, links, checkpoints, datasets, and usage example for FarSLIP (#1)

- Improve model card: Add metadata, links, checkpoints, datasets, and usage example for FarSLIP (b44a381f78a253b78cf4460026734f881eea176a)


Co-authored-by: Niels Rogge <nielsr@users.noreply.huggingface.co>

README.md

@@ -1,3 +1,92 @@
----
-license: mit
----
+---
+license: mit
+pipeline_tag: zero-shot-image-classification
+library_name: open_clip
+datasets:
+- ZhenShiL/MGRS-200k
+- omlab/RS5M
+tags:
+- remote-sensing
+---
+
+<h1 align="center"> FarSLIP: Discovering Effective CLIP Adaptation for Fine-Grained Remote Sensing Understanding </h1> 
+
+<p align="center">
+    <a href="https://huggingface.co/datasets/ZhenShiL/MGRS-200k">
+        <img alt="Hugging Face Dataset" src="https://img.shields.io/badge/🤗%20Hugging%20Face-Dataset-blue">
+    </a>
+    <a href="https://huggingface.co/ZhenShiL/FarSLIP">
+        <img alt="Hugging Face Model" src="https://img.shields.io/badge/🤗%20Hugging%20Face-Model-yellow">
+    </a>
+    <a href="https://huggingface.co/papers/2511.14901">
+        <img alt="Hugging Face Paper" src="https://img.shields.io/badge/%F0%9F%97%92%20Paper-2511.14901-b31b1b">
+    </a>
+</p>
+
+**Paper**: [FarSLIP: Discovering Effective CLIP Adaptation for Fine-Grained Remote Sensing Understanding](https://huggingface.co/papers/2511.14901)
+**Code**: [https://github.com/NJU-LHRS/FarSLIP](https://github.com/NJU-LHRS/FarSLIP)
+
+## Introduction
+We introduce FarSLIP, a vision-language foundation model for remote sensing (RS) that achieves fine-grained vision-language alignment. FarSLIP demonstrates state-of-the-art performance on both fine-grained and image-level tasks, including open-vocabulary semantic segmentation, zero-shot classification, and image-text retrieval.
+We also construct MGRS-200k, the first multi-granularity image-text dataset for RS. Each image is annotated with both short and long global-level captions, along with multiple object-category pairs.
+
+<figure>
+<div align="center">
+<img src="https://github.com/NJU-LHRS/FarSLIP/raw/main/assets/model.png" width="60%">
+</div>
+</figure>
+
+## Checkpoints
+You can download all our checkpoints from [Huggingface](https://huggingface.co/ZhenShiL/FarSLIP), or selectively download them through the links below.
+
+| Model name  | Architecture | OVSS mIoU (%) | ZSC top-1 accuracy (%) | Download |
+|-------------|--------------|---------------|-------------------------|----------------|
+| FarSLIP-s1  | ViT-B-32     | 29.87         | 58.64                  | [FarSLIP1_ViT-B-32](https://huggingface.co/ZhenShiL/FarSLIP/resolve/main/FarSLIP1_ViT-B-32.pt?download=true) |
+| FarSLIP-s2  | ViT-B-32     | 30.49         | 60.12                  | [FarSLIP2_ViT-B-32](https://huggingface.co/ZhenShiL/FarSLIP/resolve/main/FarSLIP2_ViT-B-32.pt?download=true) |
+| FarSLIP-s1  | ViT-B-16     | 35.44         | 61.89                  | [FarSLIP1_ViT-B-16](https://huggingface.co/ZhenShiL/FarSLIP/resolve/main/FarSLIP1_ViT-B-16.pt?download=true) |
+| FarSLIP-s2  | ViT-B-16     | 35.41         | 62.24                  | [FarSLIP2_ViT-B-16](https://huggingface.co/ZhenShiL/FarSLIP/resolve/main/FarSLIP2_ViT-B-16.pt?download=true) |
+
+## Dataset
+FarSLIP is trained in two stages.
++ In the first stage, we use the [RS5M](https://github.com/om-ai-lab/RS5M) dataset. A quick portal to the RS5M dataset: [link](https://huggingface.co/datasets/omlab/RS5M).
++ In the second stage, we use the proposed MGRS-200k dataset, which is available on [Huggingface](https://huggingface.co/datasets/ZhenShiL/MGRS-200k).
+
+<p align="center">
+  <img src="https://github.com/NJU-LHRS/FarSLIP/raw/main/assets/dataset.png" width="100%">
+  <br>
+  <em>Examples from MGRS-200k</em>
+</p>
+
+## Usage / Testing
+
+Below is a sample usage for zero-shot scene classification, taken directly from the [official GitHub repository](https://github.com/NJU-LHRS/FarSLIP#zero-shot-scene-classification).
+
+### Zero-shot scene classification
++ Please refer to [SkyScript](https://github.com/wangzhecheng/SkyScript?tab=readme-ov-file#download-benchmark-datasets) for scene classification dataset preparation, including 'SkyScript_cls', 'aid', 'eurosat', 'fmow', 'millionaid', 'patternnet', 'rsicb', 'nwpu'.
++ Replace the `BENCHMARK_DATASET_ROOT_DIR` in `tests/test_scene_classification.py` to your own path.
+
++ Run testing (e.g. FarSLIP-s1 with ViT-B-32):
+```
+python -m tests.test_scene_classification --model-arch ViT-B-32 --model-name FarSLIP1 --force-quick-gelu --pretrained checkpoints/FarSLIP1_ViT-B-32.pt
+```
+
+<figure>
+<div align="center">
+<img src="https://github.com/NJU-LHRS/FarSLIP/raw/main/assets/classification.png" width="100%">
+</div>
+<figcaption align="center">
+<em>Comparison of zero-shot classification accuracies (Top-1 acc., %) of different RS-specific CLIP variants across multiple benchmarks.</em>
+</figcaption>
+</figure>
+
+## Citation
+If you find our work is useful, please give us ⭐ in GitHub and consider cite our paper:
+
+```tex
+@article{li2025farslip,
+title={FarSLIP: Discovering Effective CLIP Adaptation for Fine-Grained Remote Sensing Understanding},
+author={Zhenshi Li and Weikang Yu and Dilxat Muhtar and Xueliang Zhang and Pengfeng Xiao and Pedram Ghamisi and Xiao Xiang Zhu},
+journal={arXiv preprint arXiv:2511.14901},
+year={2025}
+}
+```