TC SemiSAM Checkpoints
This repository hosts the official pre-trained and fine-tuned model checkpoints for the paper SMART (arXiv:2603.00881).
Model source
- Kind
- Other
- File size
- 856 MB–9.89 GB
- Version
- vRevision c8843a6
- Updated
- Sep 27, 2026
- Downloads
- 0
- Tasks
- Image segmentation
- Source
- Hugging Face
Source description
SMART: Semi-supervised Medical Adaptive vessel Representation Toolkit
Hugging Face Paper arXiv GitHub
This repository hosts the official pre-trained and fine-tuned model checkpoints for the paper SMART (arXiv:2603.00881).
SMART is a semi-supervised video vessel segmentation framework built on SAM3 (Segment Anything Model 3). It features a Mean Teacher architecture and text prompt support, specifically designed for efficient coronary angiography vessel segmentation.
🗂️ Model Weights Overview
We provide all necessary weights to reproduce our experiments, from the original baselines to our final semi-supervised checkpoints:
| Filename | Size | Description |
|---|---|---|
sam2.1_hiera_large.pt | 898 MB | Original SAM 2.1 Hiera Large baseline weights. |
sam3_original.pt | 3.45 GB | Original SAM 3 baseline weights. |
sam3_1p_finetune_checkpoint_100.pt | 10.1 GB | Supervised fine-tuning checkpoint trained using only 1% labeled data (100 epochs). |
semi_sam3_5labeled_checkpoint_final.pt | 10.6 GB | Final SMART checkpoint trained via semi-supervised learning (Mean Teacher) with 5% labeled data. |
bpe_simple_vocab_16e6.txt.gz | 1.36 MB | BPE vocabulary file required for the text prompt tokenizer. |
🚀 How to Use
You can easily download these weights using the huggingface_hub library and integrate them directly into the SMART training/inference pipeline.
1. Install Dependencies
pip install huggingface_hub torch torchvision
2. Download and Load Checkpoints
Here is an example of how to download the final SMART checkpoint and load it into your PyTorch environment:
from huggingface_hub import hf_hub_download
import torch
# 1. Download the final semi-supervised checkpoint
ckpt_path = hf_hub_download(
repo_id="ly17/TC-SemiSAM-checkpoints",
filename="semi_sam3_5labeled_checkpoint_final.pt"
)
print(f"Weights downloaded to: {ckpt_path}")
# 2. Load the state dict
# state_dict = torch.load(ckpt_path, map_location="cpu")
# model.load_state_dict(state_dict)
3. Text Prompt Setup
When running inference with our SMART model, please ensure you use the following default text prompt as specified in our methodology:
TEXT_PROMPT = "Please segment the blood vessels"
(Note: The model expects a dataset resolution of 512×512, which is resized to a SAM3 input resolution of 1008×1008 with normalization range [-1, 1].)
⚠️ Clinical Disclaimer
These models are released for research purposes only. They are not intended for direct clinical decision-making, patient diagnosis, or treatment planning.
While we would love to host the XCA angiography sequences on HF Datasets, they contain sensitive medical imaging data.
Sources
1 source
Sources
1 sourceVerified Sep 27
Model artifacts
4 artifacts
Model artifacts
4 artifactssemi_sam3_5labeled_checkpoint_final.pt
pt · 9.89 GB · SHA-256 d740140955c8…ad46 · Hugging Face
DownloadSource excerpts
2 excerpts
Source excerpts
2 excerpts--- license: apache-2.0 tags: - medical-imaging - image-segmentation - semi-supervised-learning - sam3 - angiography - mean-teacher - pytorch --- # SMART: Semi-supervised Medical Adaptive vessel Representation Toolkit [](https://huggingface.co/papers/2603.00881) [](https://arxiv.org/abs/2603.00881) [](https://github.com/qimingfan10/SMART) This repository hosts the official pre-trained and fine-tuned model checkpoints for the paper **SMART** (arXiv:2603.00881). SMART is a semi-supervised video vessel segmentation framework built on **SAM3 (Segment Anything Model 3)**. It features a Mean Teacher architecture and text prompt support, specifically designed for efficient coronary angiography vessel segmentation. ## 🗂️ Model Weights Overview We provide all necessary weights to reproduce our experiments, from the original baselines to our final semi-supervised checkpoints: | Filename | Size | Description | | :--- | :--- | :--- | | `sam2.1_hiera_large.pt` | 898 MB | Original SAM 2.1 Hiera Large baseline weights. | | `sam3_original.pt` | 3.45 GB | Original SAM 3 baseline weights. | | `sam3_1p_finetune_checkpoint_100.pt` | 10.1 GB | Supervised fine-tuning checkpoint trained using only 1% labeled data (100 epochs). | | `semi_sam3_5labeled_checkpoint_final.pt` | 10.6 GB | **Final SMART checkpoint** trained via semi-supervised learning (Mean Teacher) with 5% labeled data. | | `bpe_simple_vocab_16e6.txt.gz` | 1.36 MB | BPE vocabulary file required for the text prompt tokenizer. | ## 🚀 How to Use You can easily download these weights using the `huggingface_hub` library and integrate them directly into the SMART training/inference pipeline. ### 1. Install Dependencies ```bash pip install huggingface_hub torch torchvision ``` ### 2. Download and Load Checkpoints Here is an example of how to download the final SMART checkpoint and load it into your PyTorch environment: ```python from huggingface_hub import hf_hub_download import torch # 1. Download the final semi-supervised checkpoint ckpt_path = hf_hub_download( repo_id="ly17/TC-SemiSAM-checkpoints", filename="semi_sam3_5labeled_checkpoint_final.pt" ) print(f"Weights downloaded to: {ckp...
Source context: 0 downloads · 2 likes · Pipeline image-segmentation · Repo ly17/TC-SemiSAM-checkpoints
