Few-Shot Learning

394 papers with code • 2 benchmarks • 14 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

Greatest papers with code

STraTA: Self-Training with Task Augmentation for Better Few-shot Learning

google-research/google-research 13 Sep 2021

Despite their recent successes in tackling many NLP tasks, large-scale pre-trained language models do not perform as well in few-shot settings where only a handful of training examples are available.

Few-Shot Learning Few-Shot NLI

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.

Common Sense Reasoning Coreference Resolution +9

FewJoint: A Few-shot Learning Benchmark for Joint Language Understanding

InsaneLife/ChineseNLPCorpus 17 Sep 2020

In this paper, we present FewJoint, a novel Few-Shot Learning benchmark for NLP.

Few-Shot Learning

Entailment as Few-Shot Learner

PaddlePaddle/PaddleNLP 29 Apr 2021

Large pre-trained language models (LMs) have demonstrated remarkable ability as few-shot learners.

Contrastive Learning Data Augmentation +8

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.

Few-Shot Image Classification Few-shot Regression +2

Learning What to Learn for Video Object Segmentation

visionml/pytracking ECCV 2020

This allows us to achieve a rich internal representation of the target in the current frame, significantly increasing the segmentation accuracy of our approach.

Few-Shot Learning One-shot visual object segmentation +3

learn2learn: A Library for Meta-Learning Research

learnables/learn2learn 27 Aug 2020

Meta-learning researchers face two fundamental issues in their empirical work: prototyping and reproducibility.

Few-Shot Learning Meta Reinforcement Learning

Rapid Learning or Feature Reuse? Towards Understanding the Effectiveness of MAML

learnables/learn2learn ICLR 2020

We conclude with a discussion of the rapid learning vs feature reuse question for meta-learning algorithms more broadly.

Few-Shot Image Classification

On First-Order Meta-Learning Algorithms

learnables/learn2learn 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.

Few-Shot Image Classification

Meta-SGD: Learning to Learn Quickly for Few-Shot Learning

learnables/learn2learn 31 Jul 2017

In contrast, meta-learning learns from many related tasks a meta-learner that can learn a new task more accurately and faster with fewer examples, where the choice of meta-learners is crucial.

Few-Shot Learning