ybendou/easy
This repository is the official implementation Ensemble Augmented-Shot Y-shaped Learning: State-Of-The-Art Few-Shot Classification with Simple Ingredients.
This project offers a powerful method for image classification, even when you have very few examples for a specific category. It takes your existing image datasets and a trained deep learning model, then efficiently expands the model's ability to recognize new, unfamiliar classes with high accuracy. This is ideal for machine learning practitioners, researchers, and data scientists working on computer vision tasks who need to quickly adapt models to new image categories without extensive new training data.
118 stars. No commits in the last 6 months.
Use this if you need to classify images into many categories, but only have a handful of example images for each new category you want to identify.
Not ideal if you already have large, labeled datasets for all your target image classes, as its primary benefit is in 'few-shot' scenarios.
Stars
118
Forks
20
Language
Python
License
MIT
Category
Last pushed
Jun 11, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/ybendou/easy"
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.