ilia10000/LO-Shot

Papers and code related to 'Less Than One'-Shot (LO-Shot) Learning

32
/ 100
Emerging

This collection of research and code explores "less than one-shot" (LO-Shot) learning, a method where a classification model can recognize more categories than the number of examples it was shown. It takes in a small number of data examples and outputs models capable of classifying many more categories. This is designed for machine learning researchers and practitioners who need to train accurate models with extremely limited training data.

No commits in the last 6 months.

Use this if you need to build machine learning models that can distinguish between many different classes, even when you have very few training examples for each class.

Not ideal if you already have large, well-labeled datasets or if your primary focus is on standard deep learning architectures with abundant data.

few-shot-learning low-data-classification prototype-learning machine-learning-research model-compression
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 8 / 25
Community 15 / 25

How are scores calculated?

Stars

87

Forks

13

Language

Jupyter Notebook

License

Last pushed

Jul 21, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/ilia10000/LO-Shot"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.