plai-group/simple-cnaps

Source codes for "Improved Few-Shot Visual Classification" (CVPR 2020), "Enhancing Few-Shot Image Classification with Unlabelled Examples" (WACV 2022), and "Beyond Simple Meta-Learning: Multi-Purpose Models for Multi-Domain, Active and Continual Few-Shot Learning" (Neural Networks 2022 - in submission)

42
/ 100
Emerging

This project offers tools to help machine learning engineers and researchers classify new images with very few examples. It takes a small set of labeled images for new categories and outputs a model capable of accurately classifying future images in those categories. This is especially useful for quickly adapting image recognition systems to novel objects or scenes without extensive data collection.

No commits in the last 6 months.

Use this if you need to build robust image classification models for new categories when you only have a handful of labeled examples.

Not ideal if you have abundant labeled data for all your image classification needs, as more traditional deep learning methods might be more straightforward.

few-shot learning image classification computer vision machine learning research dataset efficiency
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 18 / 25

How are scores calculated?

Stars

59

Forks

15

Language

Python

License

MIT

Last pushed

Nov 03, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/plai-group/simple-cnaps"

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