About

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

TREND DATASET BEST METHOD PAPER TITLE PAPER CODE COMPARE

Subtasks

Datasets

Greatest papers with code

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

17 Sep 2020InsaneLife/ChineseNLPCorpus

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

FEW-SHOT LEARNING

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

ICML 2017 cbfinn/maml

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.

CLASSIFICATION FEW-SHOT IMAGE CLASSIFICATION FEW-SHOT REGRESSION ONE-SHOT LEARNING

Learning What to Learn for Video Object Segmentation

ECCV 2020 visionml/pytracking

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 SEMANTIC SEGMENTATION VIDEO OBJECT SEGMENTATION VIDEO SEMANTIC SEGMENTATION YOUTUBE-VOS

learn2learn: A Library for Meta-Learning Research

27 Aug 2020learnables/learn2learn

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

ICLR 2020 learnables/learn2learn

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

8 Mar 2018learnables/learn2learn

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

31 Jul 2017learnables/learn2learn

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

Prototypical Networks for Few-shot Learning

NeurIPS 2017 learnables/learn2learn

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.

CLASSIFICATION FEW-SHOT IMAGE CLASSIFICATION ONE-SHOT LEARNING ZERO-SHOT LEARNING

Big Transfer (BiT): General Visual Representation Learning

ECCV 2020 google-research/big_transfer

We conduct detailed analysis of the main components that lead to high transfer performance.

 Ranked #1 on Image Classification on ObjectNet (using extra training data)

FEW-SHOT LEARNING FINE-GRAINED IMAGE CLASSIFICATION REPRESENTATION LEARNING