naamiinepal/tunevlseg

[ACCV 2024]: TuneVLSeg: Prompt Tuning Benchmark for Vision-Language Segmentation Models

25
/ 100
Experimental

This framework helps machine learning practitioners efficiently adapt powerful vision-language models for image segmentation to new, specialized fields like medicine. It takes existing image segmentation models and a specific dataset from your domain (e.g., medical scans) and outputs a fine-tuned model ready to identify and outline objects in your new images. It is designed for researchers and engineers working with computer vision who need to customize advanced models without extensive computational resources.

No commits in the last 6 months.

Use this if you need to quickly and efficiently customize pre-trained vision-language segmentation models for a new, domain-specific image dataset, especially when dealing with significant differences from the original training data.

Not ideal if you are looking for a plug-and-play solution without any machine learning background or if you primarily work with natural images that don't require specialized domain adaptation.

medical-imaging image-segmentation radiology pathology-detection computer-vision-research
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 4 / 25
Maturity 8 / 25
Community 13 / 25

How are scores calculated?

Stars

8

Forks

2

Language

Jupyter Notebook

License

Last pushed

Oct 07, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/naamiinepal/tunevlseg"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.