Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examples

03/07/2019
by   Eleni Triantafillou, et al.
43

Few-shot classification refers to learning a classifier for new classes given only a few examples. While a plethora of models have emerged to tackle this recently, we find the current procedure and datasets that are used to systematically assess progress in this setting lacking. To address this, we propose Meta-Dataset: a new benchmark for training and evaluating few-shot classifiers that is large-scale, consists of multiple datasets, and presents more natural and realistic tasks. The aim is to measure the ability of state-of-the-art models to leverage diverse sources of data to achieve higher generalization, and to evaluate that generalization ability in a more challenging setting. We additionally measure robustness of current methods to variations in the number of available examples and the number of classes. Finally our extensive empirical evaluation leads us to identify weaknesses in Prototypical Networks and MAML, two popular few-shot classification methods, and to propose a new method, Proto-MAML, which achieves improved performance on our benchmark.

READ FULL TEXT

page 12

page 13

07/26/2021

Meta-Learning Adversarial Domain Adaptation Network for Few-Shot Text Classification

Meta-learning has emerged as a trending technique to tackle few-shot tex...
04/08/2019

A Closer Look at Few-shot Classification

Few-shot classification aims to learn a classifier to recognize unseen c...
05/14/2021

Learning a Universal Template for Few-shot Dataset Generalization

Few-shot dataset generalization is a challenging variant of the well-stu...
01/27/2020

Exploiting Unsupervised Inputs for Accurate Few-Shot Classification

In few-shot classification, the aim is to learn models able to discrimin...
03/02/2018

Meta-Learning for Semi-Supervised Few-Shot Classification

In few-shot classification, we are interested in learning algorithms tha...
07/09/2020

Generalized Many-Way Few-Shot Video Classification

Few-shot learning methods operate in low data regimes. The aim is to lea...

Code Repositories

metadl

NeurIPS 2021 - Few-shot learning competition


view repo

nas-dmrl

Learning to reinforcement learn for Neural Architecture Search


view repo

AM3-MAML

meta learning from the initializaion induced by word embedding


view repo

REPTILE-Metalearning

Full implementation and re-production of the meta-learning algorithm REPTILE


view repo

Please sign up or login with your details

Forgot password? Click here to reset