edi-meta-learning/meta-omnium
Implementation of "Meta Omnium: A Benchmark for General-Purpose Learning-to-Learn"
This project helps machine learning researchers evaluate how well their few-shot learning algorithms generalize across many different computer vision tasks. It provides a dataset-of-datasets spanning image recognition, keypoint localization, semantic segmentation, and regression tasks. Researchers can use this to input their meta-learning model and assess its ability to learn with limited data across diverse vision applications.
No commits in the last 6 months.
Use this if you are a meta-learning researcher developing few-shot vision algorithms and need a standardized way to test their generalization across a broad range of tasks.
Not ideal if you are looking for a pre-trained model for a specific computer vision task or a general-purpose machine learning library.
Stars
25
Forks
3
Language
Python
License
—
Category
Last pushed
Jun 19, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/edi-meta-learning/meta-omnium"
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"