barzansaeedpour/few-shot-learning-using-just-5-images

In this repository, we leverage the power of few-shot learning combined with a transfer learning approach to tackle the task of object detection.

21
/ 100
Experimental

This project helps computer vision practitioners train object detection models quickly, even when they only have a handful of example images for a new object. You provide just 5 images of the object you want to detect, and it outputs a model capable of recognizing that object in new images. This is ideal for researchers, AI product developers, or automation engineers working with niche object detection tasks.

No commits in the last 6 months.

Use this if you need to build an object detection system but have very limited labeled data for the specific objects you want to identify.

Not ideal if you have thousands of labeled images for your target objects or require extremely high precision for safety-critical applications without further extensive validation.

object-detection computer-vision machine-learning-training image-analysis AI-prototyping
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 16 / 25
Community 0 / 25

How are scores calculated?

Stars

11

Forks

Language

Jupyter Notebook

License

MIT

Last pushed

Jun 17, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/barzansaeedpour/few-shot-learning-using-just-5-images"

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