sky24h/Training-Free_Zero-Shot_Semantic_Segmentation_with_LLM_Refinement

This repository contains official implementation of the paper "Training-Free Zero-Shot Semantic Segmentation with LLM Refinement" (BMVC 2024).

20
/ 100
Experimental

This project helps developers working with computer vision models to accurately identify and outline distinct objects within images without needing to train a new model for each new object type. You input an image and, using a large language model to refine the object definitions, it outputs images with specific objects precisely segmented and labeled. This is for researchers or engineers building applications that require detailed object recognition in images.

No commits in the last 6 months.

Use this if you need to segment specific objects in images but want to avoid the time and resources required for extensive model training on new datasets.

Not ideal if you have ample labeled data for your specific segmentation task and prefer to fine-tune a dedicated model for maximum precision and efficiency.

computer-vision image-analysis object-segmentation machine-learning-engineering
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 4 / 25
Maturity 16 / 25
Community 0 / 25

How are scores calculated?

Stars

5

Forks

Language

Jupyter Notebook

License

AGPL-3.0

Last pushed

Dec 23, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/sky24h/Training-Free_Zero-Shot_Semantic_Segmentation_with_LLM_Refinement"

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