horsepurve/DeepVoro
Few-shot Learning as Cluster-induced Voronoi Diagrams (ICLR 2022)
This project helps machine learning researchers improve the accuracy of 'few-shot learning' models, which are trained with very limited data. It takes existing pre-trained feature extraction models and datasets as input, and outputs enhanced classification models that perform better on tasks where only a few examples are available per category. The ideal user is a machine learning researcher or practitioner working on cutting-edge few-shot learning techniques.
No commits in the last 6 months.
Use this if you are a researcher developing few-shot learning models and want to improve their performance, especially when dealing with extremely sparse data, by applying a novel geometric approach.
Not ideal if you are looking for a plug-and-play solution for general machine learning tasks or do not have experience with advanced machine learning research concepts.
Stars
9
Forks
1
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Mar 23, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/horsepurve/DeepVoro"
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
Sha-Lab/FEAT
The code repository for "Few-Shot Learning via Embedding Adaptation with Set-to-Set Functions"