baiksung/MeTAL

Official PyTorch implementation of "Meta-Learning with Task-Adaptive Loss Function for Few-Shot Learning" (ICCV2021 Oral)

34
/ 100
Emerging

This project helps machine learning researchers and practitioners tackle 'few-shot learning' problems where you have very little labeled data for new tasks. It provides code to train models that can quickly adapt to new image classification tasks, even with just a few examples. The input is a dataset like miniImageNet, and the output is a trained model capable of classifying new images with high accuracy from limited samples.

No commits in the last 6 months.

Use this if you are a machine learning researcher working on meta-learning or few-shot image classification and need a robust, high-performance implementation.

Not ideal if you are a beginner looking for a simple, out-of-the-box solution for general image classification without diving into meta-learning specifics.

few-shot learning meta-learning image classification deep learning research computer vision
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 8 / 25
Community 18 / 25

How are scores calculated?

Stars

66

Forks

13

Language

Python

License

Last pushed

Dec 18, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/baiksung/MeTAL"

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