Few-Shot Learning

1284 papers with code • 27 benchmarks • 45 datasets

Few-Shot Learning is an example of meta-learning, where a learner is trained on several related tasks, during the meta-training phase, so that it can generalize well to unseen (but related) tasks with just few examples, during the meta-testing phase. An effective approach to the Few-Shot Learning problem is to learn a common representation for various tasks and train task specific classifiers on top of this representation.

Source: Penalty Method for Inversion-Free Deep Bilevel Optimization

Benchmarks

Add a Result

These leaderboards are used to track progress in Few-Shot Learning

Dataset	Best Model	Compare
MedConceptsQA	gpt-4-0125-preview	See all
FGVC Aircraft	SaSPA + CAL	See all
DTD	SaSPA + CAL	See all
Mini-Imagenet 5-way (1-shot)	EASY (transductive)	See all
Stanford Cars	SaSPA + CAL	See all
Mini-ImageNet - 5-Shot Learning	BGNN	See all
Mini-ImageNet - 1-Shot Learning	HCTransformers	See all
SST-2 Binary classification	DART	See all
MR	DART	See all
CR	DART	See all
MRPC	DART	See all
GLUE QQP	DART	See all
Caltech101	Variational Prompt Tuning	See all
OxfordPets	Variational Prompt Tuning	See all
StanforCars	Variational Prompt Tuning	See all
Flowers-102	Variational Prompt Tuning	See all
food101	Variational Prompt Tuning	See all
SUN397	Variational Prompt Tuning	See all
EuroSAT	Variational Prompt Tuning	See all
UCF101	Variational Prompt Tuning	See all
Large COVID-19 CT scan slice dataset	CovidExpert	See all
CaseHOLD	CoT-T5-11B (1024 Shot)	See all
MedNLI	CoT-T5-11B (1024 Shot)	See all
PubMedQA	CoT-T5-11B (1024 Shot)	See all
Mini-ImageNet - 10-Shot Learning	UNEM-Gaussian	See all
Mini-ImageNet - 20-Shot Learning	UNEM-Gaussian	See all
tieredImageNet - 5-shot	UNEM-Gaussian	See all

Show all 27 benchmarks

Collapse benchmarks

Libraries

Use these libraries to find Few-Shot Learning models and implementations

sicara/easy-few-shot-learning

13 papers

1,197

learnables/learn2learn

9 papers

2,780

peymanbateni/simple-cnaps

5 papers

119

plai-group/simple-cnaps

5 papers

Datasets

Subtasks

Unsupervised Few-Shot Learning

Few-Shot Relation Classification

Few-Shot Imitation Learning

Few-Shot Audio Classification

Few-Shot Camera-Adaptive Color Constancy

Few-shot HTC

Few-Shot Video Object Detection

few-shot-htc

Unsupervised Few-Shot Audio Classification

Most implemented papers

Most implemented Social Latest No code

Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks

cbfinn/maml • • ICML 2017

We propose an algorithm for meta-learning that is model-agnostic, in the sense that it is compatible with any model trained with gradient descent and applicable to a variety of different learning problems, including classification, regression, and reinforcement learning.

Paper
Code

Language Models are Few-Shot Learners

openai/gpt-3 • NeurIPS 2020

By contrast, humans can generally perform a new language task from only a few examples or from simple instructions - something which current NLP systems still largely struggle to do.

Paper
Code

LLaMA: Open and Efficient Foundation Language Models

facebookresearch/llama • • arXiv 2023

We introduce LLaMA, a collection of foundation language models ranging from 7B to 65B parameters.

Paper
Code

Prototypical Networks for Few-shot Learning

jakesnell/prototypical-networks • • NeurIPS 2017

We propose prototypical networks for the problem of few-shot classification, where a classifier must generalize to new classes not seen in the training set, given only a small number of examples of each new class.

Paper
Code

Matching Networks for One Shot Learning

oscarknagg/few-shot • • NeurIPS 2016

Our algorithm improves one-shot accuracy on ImageNet from 87. 6% to 93. 2% and from 88. 0% to 93. 8% on Omniglot compared to competing approaches.

Paper
Code

BioBERT: a pre-trained biomedical language representation model for biomedical text mining

dmis-lab/biobert • • 25 Jan 2019

Biomedical text mining is becoming increasingly important as the number of biomedical documents rapidly grows.

Paper
Code

Learning to Compare: Relation Network for Few-Shot Learning

sicara/easy-few-shot-learning • • CVPR 2018

Once trained, a RN is able to classify images of new classes by computing relation scores between query images and the few examples of each new class without further updating the network.

Paper
Code

On First-Order Meta-Learning Algorithms

openai/supervised-reptile • • 8 Mar 2018

This paper considers meta-learning problems, where there is a distribution of tasks, and we would like to obtain an agent that performs well (i. e., learns quickly) when presented with a previously unseen task sampled from this distribution.

Paper
Code