ModelListedExternal

MedCLIPSeg

This repository hosts the official trained model checkpoints for MedCLIPSeg, presented in the paper MedCLIPSeg: Probabilistic Vision-Language Adaptation for Data-Efficient and Generalizable Medical Image Segmentation.

Sourcehuggingface.co/TahaKoleilat/MedCLIPSeg/tree/69bfb8fbdb0d572a7ce268a15ecc605f7a42e129

KindOtherVersionRevision 69bfb8f

Model source

Kind: Other
File size: 962 MB–4.63 GB
Version: vRevision 69bfb8f
Updated: Sep 15, 2026
Downloads: 0
Tasks: Captioning, Image segmentation
Source: Hugging Face

Source excerpt

Sources

1 source

Hugging FacePrimaryVersion 69bfb8fbdb0d572a7ce268a15ecc605f7a42e129

huggingface.co/TahaKoleilat/MedCLIPSeg/tree/69bfb8fbdb0d572a7ce268a15ecc605f7a42e129

Verified Sep 15

Model artifacts

27 artifacts

BTMRI_10/trained_models/seed666/MedCLIPSeg_unimedclip_ViT-B-16_latest.pth

pth · 962 MB · SHA-256 6cf5608e0ce6…29fe · Hugging Face

Download

BTMRI_25/trained_models/seed666/MedCLIPSeg_unimedclip_ViT-B-16_latest.pth

pth · 962 MB · SHA-256 c4676343e40e…6bdc · Hugging Face

Download

BTMRI_50/trained_models/seed666/MedCLIPSeg_unimedclip_ViT-B-16_latest.pth

pth · 962 MB · SHA-256 4b810d967950…b380 · Hugging Face

Download

BTMRI/trained_models/seed666/MedCLIPSeg_unimedclip_ViT-B-16_latest.pth

pth · 962 MB · SHA-256 97afd5b837ab…2475 · Hugging Face

Download

BUSI_10/trained_models/seed666/MedCLIPSeg_unimedclip_ViT-B-16_latest.pth

pth · 962 MB · SHA-256 c77ff3fc11f7…a873 · Hugging Face

Download

BUSI_25/trained_models/seed666/MedCLIPSeg_unimedclip_ViT-B-16_latest.pth

pth · 962 MB · SHA-256 b70c3bc157dc…3ce4 · Hugging Face

Download

BUSI_50/trained_models/seed666/MedCLIPSeg_unimedclip_ViT-B-16_latest.pth

pth · 962 MB · SHA-256 6a2615cfc25b…8a41 · Hugging Face

Download

BUSI/trained_models/seed666/MedCLIPSeg_unimedclip_ViT-B-16_latest.pth

pth · 962 MB · SHA-256 14fe67e2145e…5b31 · Hugging Face

Download

checkpoints/PubMedCLIP_ViT32.pth

pth · 1.46 GB · SHA-256 56d244ea2e54…d9c6 · Hugging Face

Download

checkpoints/unimed_clip_vit_b16.pt

pt · 2.19 GB · SHA-256 bfdce18ca247…2842 · Hugging Face

Download

checkpoints/unimed_clip_vit_l14_base_text_encoder.pt

pt · 4.63 GB · SHA-256 4d0d263203f2…7159 · Hugging Face

Download

Covid19_10/trained_models/seed666/MedCLIPSeg_unimedclip_ViT-B-16_latest.pth

pth · 962 MB · SHA-256 04dabc05641c…be3a · Hugging Face

Download

Covid19_25/trained_models/seed666/MedCLIPSeg_unimedclip_ViT-B-16_latest.pth

pth · 962 MB · SHA-256 7ac6b823156d…7cbb · Hugging Face

Download

Covid19_50/trained_models/seed666/MedCLIPSeg_unimedclip_ViT-B-16_latest.pth

pth · 962 MB · SHA-256 b90baf7df6d4…03e2 · Hugging Face

Download

Covid19/trained_models/seed666/MedCLIPSeg_unimedclip_ViT-B-16_latest.pth

pth · 962 MB · SHA-256 1963632a11b3…8ba1 · Hugging Face

Download

EUS_10/trained_models/seed666/MedCLIPSeg_unimedclip_ViT-B-16_latest.pth

pth · 962 MB · SHA-256 ff14efd6c329…7cef · Hugging Face

Download

EUS_25/trained_models/seed666/MedCLIPSeg_unimedclip_ViT-B-16_latest.pth

pth · 962 MB · SHA-256 1a04f89aebbd…24a2 · Hugging Face

Download

EUS_50/trained_models/seed666/MedCLIPSeg_unimedclip_ViT-B-16_latest.pth

pth · 962 MB · SHA-256 ca56ab593512…3b75 · Hugging Face

Download

EUS/trained_models/seed666/MedCLIPSeg_unimedclip_ViT-B-16_latest.pth

pth · 962 MB · SHA-256 127c8728576e…e102 · Hugging Face

Download

ISIC_10/trained_models/seed666/MedCLIPSeg_unimedclip_ViT-B-16_latest.pth

pth · 962 MB · SHA-256 5bad33011fb4…15de · Hugging Face

Download

ISIC_25/trained_models/seed666/MedCLIPSeg_unimedclip_ViT-B-16_latest.pth

pth · 962 MB · SHA-256 483b9a8b8140…504b · Hugging Face

Download

ISIC_50/trained_models/seed666/MedCLIPSeg_unimedclip_ViT-B-16_latest.pth

pth · 962 MB · SHA-256 693890e11bbb…d355 · Hugging Face

Download

ISIC/trained_models/seed666/MedCLIPSeg_unimedclip_ViT-B-16_latest.pth

pth · 962 MB · SHA-256 01ea091471b2…ffb3 · Hugging Face

Download

Kvasir_10/trained_models/seed666/MedCLIPSeg_unimedclip_ViT-B-16_latest.pth

pth · 962 MB · SHA-256 d8c850a24493…596f · Hugging Face

Download

Kvasir_25/trained_models/seed666/MedCLIPSeg_unimedclip_ViT-B-16_latest.pth

pth · 962 MB · SHA-256 16bea602ba10…3053 · Hugging Face

Download

Kvasir_50/trained_models/seed666/MedCLIPSeg_unimedclip_ViT-B-16_latest.pth

pth · 962 MB · SHA-256 cec822462408…d1c6 · Hugging Face

Download

Kvasir/trained_models/seed666/MedCLIPSeg_unimedclip_ViT-B-16_latest.pth

pth · 962 MB · SHA-256 dfc76ba75d0a…df1c · Hugging Face

Download

Source excerpts

2 excerpts

ReadmeSep 15huggingface.co/TahaKoleilat/MedCLIPSeg

--- language: - en license: cc-by-nc-4.0 pipeline_tag: image-segmentation tags: - medical-imaging - vision-language-models - clip - unimedclip - biomedical - healthcare --- # MedCLIPSeg: Probabilistic Vision–Language Adaptation for Data-Efficient and Generalizable Medical Image Segmentation <a href="https://arxiv.org/abs/2602.20423" target="_blank"><img alt="arXiv" src="https://img.shields.io/badge/arXiv-2602.20423-B31B1B?logo=arxiv&logoColor=white" height="25"/></a> <a href="https://tahakoleilat.github.io/MedCLIPSeg" target="_blank"><img alt="Project Website" src="https://img.shields.io/badge/%F0%9F%94%97%20Project-Website-blue" height="25"/></a> <a href="https://github.com/HealthX-Lab/MedCLIPSeg" target="_blank"><img alt="Code" src="https://img.shields.io/badge/Code-GitHub-1f6feb?logo=github&logoColor=white" height="25"/></a> <a href="https://huggingface.co/datasets/TahaKoleilat/MedCLIPSeg" target="_blank"><img alt="HuggingFace Dataset" src="https://img.shields.io/badge/%F0%9F%A4%97%20_Datasets-Access-ffc107?color=ffc107&logoColor=white" height="25"/></a> <a href="https://huggingface.co/TahaKoleilat/MedCLIPSeg" target="_blank"><img alt="HuggingFace Models" src="https://img.shields.io/badge/Models-Reproduce-2ea44f?logo=huggingface&logoColor=white" height="25"/></a> <a href="#citation"><img alt="Citation" src="https://img.shields.io/badge/Citation-BibTeX-6C63FF?logo=bookstack&logoColor=white" height="25"/></a> This repository hosts the **official trained model checkpoints** for **MedCLIPSeg**, presented in the paper [MedCLIPSeg: Probabilistic Vision-Language Adaptation for Data-Efficient and Generalizable Medical Image Segmentation](https://huggingface.co/papers/2602.20423). **Authors:** Taha Koleilat, Hojat Asgariandehkordi, Omid Nejati Manzari, Berardino Barile, Yiming Xiao, Hassan Rivaz. MedCLIPSeg is a vision–language framework for **medical image segmentation** built on top of **CLIP**. It adapts CLIP for robust, data-efficient, and uncertainty-aware segmentation through probabilistic cross-modal attention and bidirectional interaction between image and text tokens. The released checkpoints correspond exactly to the experiments reported in our paper and are provided **for evaluation and reproducibility purposes only**. ## 🧠 Model Overview - **Backbone**: UniMedCLIP ViT-B/16 - **Task**: Medical Image Segmentation - **Modalities**: Ultrasound,...

NoteSep 15huggingface.co/TahaKoleilat/MedCLIPSeg

Source context: 0 downloads · 3 likes · Pipeline image-segmentation · Repo TahaKoleilat/MedCLIPSeg