Update README.md

README.md

@@ -1,14 +1,11 @@
 ---
 license: apache-2.0
----
----
 language: en
 tags:
   - self-supervised-learning
   - echocardiography
   - medical-imaging
   - video-representation
-license: apache-2.0
 datasets:
   - EchoDynamic
   - RVENet
@@ -18,24 +15,58 @@ model_index: deep-learning
 paper: https://arxiv.org/pdf/2506.11777
 ---
 
-# 🫀 DISCOVR (checkpoint: `DISCOVR_399_Adult_Pediatric`)
+# 🫀 DISCOVR — Self-Supervised Echocardiography Representations
 
 **Paper:** *Self-Supervised Learning of Echocardiographic Video Representations via Online Cluster Distillation* — NeurIPS 2025  
 📄 [arXiv:2506.11777](https://arxiv.org/pdf/2506.11777)
 
-**Hugging Face repo:** `Div97/DISCOVR_399_Adult_Pediatric`  
-**This checkpoint:** DISCOVR trained for **400 epochs** on adult and pediatric echocardiography datasets (EchoDynamic, RVENet, EchoNet-Pediatric LVH).  
+---
+
+## 📦 Available Checkpoints
+
+| Epochs | Checkpoint | Hugging Face Repo |
+|:-------:|:------------|:------------------|
+| 200 | `DISCOVR_199_Adult_Pediatric` | [`Div97/DISCOVR_199_Adult_Pediatric`](https://huggingface.co/Div97/DISCOVR_199_Adult_Pediatric) |
+| 300 | `DISCOVR_299_Adult_Pediatric` | [`Div97/DISCOVR_299_Adult_Pediatric`](https://huggingface.co/Div97/DISCOVR_299_Adult_Pediatric) |
+| 400 | `DISCOVR_399_Adult_Pediatric` | [`Div97/DISCOVR_399_Adult_Pediatric`](https://huggingface.co/Div97/DISCOVR_399_Adult_Pediatric) |
+| 600 | `DISCOVR_599_Adult_Pediatric` | [`Div97/DISCOVR_599_Adult_Pediatric`](https://huggingface.co/Div97/DISCOVR_599_Adult_Pediatric) |
+| 800 | `DISCOVR_799_Adult_Pediatric` | [`Div97/DISCOVR_799_Adult_Pediatric`](https://huggingface.co/Div97/DISCOVR_799_Adult_Pediatric) |
+
+> Each checkpoint corresponds to a model trained for **~200, 300, 400, 600, and 800 epochs**, respectively, on **adult and pediatric echocardiography datasets** (EchoDynamic, RVENet, EchoNet-Pediatric-LVH).
 
-> **Short description**  
-> This checkpoint contains the DISCOVR backbone trained with self-supervised online cluster distillation to learn spatio-temporal cardiac video representations. It captures fine-grained anatomical semantics and global temporal dynamics for downstream tasks such as anomaly detection, classification, and segmentation. **Not for clinical use.**
+---
+
+## 🧠 Model Overview
+
+DISCOVR is a self-supervised framework for learning spatio-temporal echocardiographic video representations via **online cluster distillation**.  
+The model learns to capture both fine-grained anatomical semantics and global temporal dynamics, supporting downstream tasks such as:
+- Cardiac view classification  
+- Functional abnormality detection  
+- Video segmentation  
+- Representation learning for medical imaging
+
+**Not for clinical or diagnostic use.**
 
 ---
 
-## 🔖 Quick facts
-- **Model name (repo):** `Div97/DISCOVR_399_Adult_Pediatric`  
-- **Training:** 400 epochs, ViT-Base backbone, 64-frame clips (stride 3)  
-- **Datasets used (training):** EchoDynamic, RVENet, EchoNet-Pediatric LVH  
-- **Intended use:** Research & educational purposes; downstream representation learning for echocardiography  
-- **Not intended for:** Clinical diagnosis, medical decision-making
+## 🔖 Quick Facts
+- **Model family:** `DISCOVR_[199/299/399/599/799]_Adult_Pediatric`  
+- **Architecture:** ViT-Base backbone, 64-frame clips (stride 3)  
+- **Datasets used:** EchoDynamic, RVENet, EchoNet-Pediatric LVH  
+- **Training objective:** Self-supervised online cluster distillation  
+- **Intended use:** Research & education  
+- **Not intended for:** Clinical decision-making or real-world patient care  
 
 ---
+
+## 🧩 Citation
+
+If you use DISCOVR in your work, please cite:
+
+```bibtex
+@inproceedings{divakaran2025discovr,
+  title={Self-Supervised Learning of Echocardiographic Video Representations via Online Cluster Distillation},
+  author={Divakaran, Vignesh and others},
+  booktitle={Advances in Neural Information Processing Systems (NeurIPS)},
+  year={2025}
+}