Sha-Lab/FEAT
The code repository for "Few-Shot Learning via Embedding Adaptation with Set-to-Set Functions"
This project helps machine learning practitioners, particularly those in computer vision, classify images even when they have very few examples of a new category. You provide a small set of labeled images for new classes and the system outputs a model capable of accurately classifying new, unseen images from those classes. This is ideal for researchers or data scientists building image recognition systems.
434 stars. No commits in the last 6 months.
Use this if you need to quickly train an image classifier for new categories with only a handful of examples per category.
Not ideal if you have large datasets for all your classes or are working on tasks outside of image classification.
Stars
434
Forks
85
Language
Python
License
MIT
Category
Last pushed
Jul 31, 2020
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Sha-Lab/FEAT"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
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
oscarknagg/few-shot
Repository for few-shot learning machine learning projects
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.