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).
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.
Stars
5
Forks
—
Language
Jupyter Notebook
License
AGPL-3.0
Category
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.
Higher-rated alternatives
jncraton/languagemodels
Explore large language models in 512MB of RAM
microsoft/unilm
Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities
haizelabs/verdict
Inference-time scaling for LLMs-as-a-judge.
bytedance/Sa2VA
Official Repo For Pixel-LLM Codebase
albertan017/LLM4Decompile
Reverse Engineering: Decompiling Binary Code with Large Language Models