Ready-to-use code and tutorial notebooks to boost your way into few-shot learning for image classification.
-
Updated
May 7, 2024 - Python
Ready-to-use code and tutorial notebooks to boost your way into few-shot learning for image classification.
[ICLR2021 Oral] Free Lunch for Few-Shot Learning: Distribution Calibration
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" (SSRN Electronic Journal)
(NeurIPS 2020) Transductive Information Maximization for Few-Shot Learning https://arxiv.org/abs/2008.11297
[ICCV'21] Official PyTorch implementation of Relational Embedding for Few-Shot Classification
This repository contains an easy and intuitive approach to few-shot NER using most similar expansion over spaCy embeddings. Now with entity scoring.
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 repository contains an easy and intuitive approach to few-shot classification using sentence-transformers or spaCy models, or zero-shot classification with Huggingface.
[ICML 2022] Channel Importance Matters in Few-shot Image Classification
A non-official 100% PyTorch implementation of META-DATASET benchmark for few-shot classification
[ICCV 2023] Prompt-aligned Gradient for Prompt Tuning
Code release for Proto-CLIP: Vision-Language Prototypical Network for Few-Shot Learning
Code and data for paper https://arxiv.org/pdf/2106.05517.pdf (CVPR 2022)
Code Repository for "SSL-ProtoNet: Self-supervised Learning Prototypical Networks for few-shot learning"
Interactive Skeleton Based Few Shot Action Recognition
[AAAI 2023] This is the code for our paper `Neighborhood-Regularized Self-Training for Learning with Few Labels'.
A streamlit web app that allows you to train Few Shot image classification models
This repository contains the main ResNet backbone experiments conducted in the ICLR 2022 spotlight paper "On the Importance of Firth Bias Reduction in Few-Shot Classification".
The code for "SCL: Self-supervised contrastive learning for few-shot image classification"
Add a description, image, and links to the few-shot-classifcation topic page so that developers can more easily learn about it.
To associate your repository with the few-shot-classifcation topic, visit your repo's landing page and select "manage topics."