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.
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.
Stars
11
Forks
—
Language
Jupyter Notebook
License
MIT
Category
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.
Higher-rated alternatives
oscarknagg/few-shot
Repository for few-shot learning machine learning projects
jakesnell/prototypical-networks
Code for the NeurIPS 2017 Paper "Prototypical Networks for Few-shot Learning"
harveyslash/Facial-Similarity-with-Siamese-Networks-in-Pytorch
Implementing Siamese networks with a contrastive loss for similarity learning
google-research/meta-dataset
A dataset of datasets for learning to learn from few examples
akshaysharma096/Siamese-Networks
Few Shot Learning by Siamese Networks, using Keras.