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

Leaderboards for few-shot image classification on miniImageNet, tieredImageNet, FC100, and CIFAR-FS.

A curated list of awesome prompt/adapter learning methods for vision-language models like CLIP.

This repository contains an easy and intuitive approach to few-shot NER using most similar expansion over spaCy embeddings. Now with entity scoring.

This repository contains an easy and intuitive approach to few-shot classification using sentence-transformers or spaCy models, or zero-shot classification with Huggingface.

[ICCV 2023] Prompt-aligned Gradient for Prompt Tuning

(NeurIPS 2020) Transductive Information Maximization for Few-Shot Learning https://arxiv.org/abs/2008.11297

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)

[ICCV'21] Official PyTorch implementation of Relational Embedding for Few-Shot Classification

A non-official 100% PyTorch implementation of META-DATASET benchmark for few-shot classification

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)

[ICML 2022] Channel Importance Matters in Few-shot Image Classification

Code and data for paper https://arxiv.org/pdf/2106.05517.pdf (CVPR 2022)

Code release for Proto-CLIP: Vision-Language Prototypical Network for Few-Shot Learning

Few-Shot Graph Classification via distance metric learning.

Official Implementation of CVPR 2023 paper: "Meta-Learning with a Geometry-Adaptive Preconditioner"

Code Repository for "SSL-ProtoNet: Self-supervised Learning Prototypical Networks for few-shot learning"

Official implementation of POODLE: Improving Few-shot Learning via Penalizing Out-of-Distribution Samples (NeurIPS 2021)