Kaushalya/medclip
A multi-modal CLIP model trained on the medical dataset ROCO
This helps radiologists, researchers, and medical practitioners quickly find relevant medical images using text descriptions. You input a medical image or a descriptive caption, and it retrieves corresponding images or captions from a dataset of radiology images. This is useful for anyone working with large collections of medical imagery who needs to efficiently search and organize their visual data.
151 stars. No commits in the last 6 months.
Use this if you need to search a collection of radiology images using text, or find text descriptions for medical images.
Not ideal if you need to distinguish between very specific anatomical details or diagnoses (e.g., a brain scan vs. a lung scan), as the model's current capability is limited to higher-level features like image modality.
Stars
151
Forks
21
Language
Jupyter Notebook
License
Apache-2.0
Category
Last pushed
Jun 04, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/Kaushalya/medclip"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
OFA-Sys/Chinese-CLIP
Chinese version of CLIP which achieves Chinese cross-modal retrieval and representation generation.
kastalimohammed1965/CLIP-fine-tune-registers-gated
Vision Transformers Needs Registers. And Gated MLPs. And +20M params. Tiny modality gap ensues!
BUAADreamer/SPN4CIR
[ACM MM 2024] Improving Composed Image Retrieval via Contrastive Learning with Scaling Positives...
clip-italian/clip-italian
CLIP (Contrastive Language–Image Pre-training) for Italian
zer0int/CLIP-fine-tune-registers-gated
Vision Transformers Needs Registers. And Gated MLPs. And +20M params. Tiny modality gap ensues!