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)
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.
Stars
59
Forks
15
Language
Python
License
MIT
Category
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.
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"