yinboc/few-shot-meta-baseline
Meta-Baseline: Exploring Simple Meta-Learning for Few-Shot Learning, in ICCV 2021
This project helps researchers and machine learning practitioners train image classification models with very limited data. It takes a small collection of example images for new categories and outputs a model capable of recognizing those categories. This is particularly useful for specialists working with rare data or in fields where extensive datasets are unavailable, such as medical imaging or specialized object detection.
653 stars. No commits in the last 6 months.
Use this if you need to classify new image categories effectively with only a handful of examples per category.
Not ideal if you have large, well-labeled datasets for all your image classification tasks, as traditional deep learning methods might be more straightforward.
Stars
653
Forks
107
Language
Python
License
MIT
Category
Last pushed
Oct 10, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/yinboc/few-shot-meta-baseline"
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"