leehyeonbeen/segment-anything-fine-tuning
Fine-tuning SAM using PASCAL VOC dataset
This project helps robotics engineers or computer vision researchers who need to precisely identify specific human body parts within images. It takes standard image datasets, applies fine-tuning to the Segment Anything Model (SAM), and outputs a more accurate model for human part segmentation. This allows for improved recognition capabilities in downstream applications like collaborative robots.
Use this if you need to fine-tune an existing foundation model like SAM for specific segmentation tasks, especially when focusing on human body part recognition in robotics or other vision-guided systems.
Not ideal if you're looking for an out-of-the-box solution for general object segmentation or if you don't have experience with deep learning model training and dataset preparation.
Stars
19
Forks
—
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Mar 20, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/leehyeonbeen/segment-anything-fine-tuning"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
PytorchConnectomics/pytorch_connectomics
PyTorch Connectomics: segmentation toolbox for EM connectomics
segments-ai/segments-ai
Segments.ai Python SDK
afermg/cp_measure
Morphological features from images and masks made easy.
oarriaga/paz
Hierarchical perception library in Python for pose estimation, object detection, instance...
JdeRobot/PerceptionMetrics
A toolkit designed to unify and streamline the evaluation of object detection and segmentation...