Update README.md

README.md

@@ -1,3 +1,48 @@
----
-license: cc-by-nc-4.0
----
+---
+license: cc-by-nc-4.0
+---
+
+# FSFM-3C Models (Pre-trained Vision Transformers)
+
+A self-supervised pre-training framework to learn a transferable facial representation that boosts various face security tasks.
+- **Paper:** [FSFM: A Generalizable Face Security Foundation Model via Self-Supervised Facial Representation Learning](https://arxiv.org/abs/2412.12032)
+- **Repository:** [github](TODO)
+- **Projeact:** [this https URL](https://fsfm-3c.github.io/)
+
+## Environment
+Git clone our repository, creating a python environment and activate it via the following command: 
+```bash
+conda create -n fsfm3c python=3.9
+conda activate fsfm3c
+pip install -r requirements.txt
+
+## Model Loading
+```python
+import models_vit
+from huggingface_hub import hf_hub_download
+CKPT_SAVE_PATH = [your checkpoint storage path]
+CKPT_NAME = [checkpoint name]
+hf_hub_download(local_dir=CKPT_SAVE_PATH,
+                repo_id='FSFM-3C/model_v1',
+                filename=CKPT_NAME)
+model = models_vit.__dict__['vit_base_patch16'](
+    num_classes=2,
+    drop_path_rate=0.1,
+    global_pool=True,
+)
+checkpoint = torch.load(os.path.join(CKPT_SAVE_PATH, CKPT_NAME), map_location='cpu')
+model.load_state_dict(checkpoint['model'])
+```
+
+## Downstream Use
+Face security tasks such as deepfake detection, face anti-spoofing, and diffusion facial forgery detection.
+
+## BibTeX entry and citation info
+
+```bibtex
+@article{wang2024fsfm,
+  title={FSFM: A Generalizable Face Security Foundation Model via Self-Supervised Facial Representation Learning},
+  author={Wang, Gaojian and Lin, Feng and Wu, Tong and Liu, Zhenguang and Ba, Zhongjie and Ren, Kui},
+  journal={arXiv preprint arXiv:2412.12032},
+  year={2024}
+}