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 it, we
find the procedure and datasets that are used to assess their progress lacking.
To address this limitation, we propose Meta-Dataset: a new benchmark for
training and evaluating models that is large-scale, consists of diverse
datasets, and presents more realistic tasks. We experiment with popular
baselines and meta-learners on Meta-Dataset, along with a competitive method
that we propose. We analyze performance as a function of various
characteristics of test tasks and examine the models' ability to leverage
diverse training sources for improving their generalization. We also propose a
new set of baselines for quantifying the benefit of meta-learning in
Meta-Dataset. Our extensive experimentation has uncovered important research
challenges and we hope to inspire work in these directions.
Описание
[1903.03096] Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examples
%0 Journal Article
%1 triantafillou2019metadataset
%A Triantafillou, Eleni
%A Zhu, Tyler
%A Dumoulin, Vincent
%A Lamblin, Pascal
%A Evci, Utku
%A Xu, Kelvin
%A Goroshin, Ross
%A Gelada, Carles
%A Swersky, Kevin
%A Manzagol, Pierre-Antoine
%A Larochelle, Hugo
%D 2019
%K datasets few-shot
%T Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few
Examples
%U http://arxiv.org/abs/1903.03096
%X 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 it, we
find the procedure and datasets that are used to assess their progress lacking.
To address this limitation, we propose Meta-Dataset: a new benchmark for
training and evaluating models that is large-scale, consists of diverse
datasets, and presents more realistic tasks. We experiment with popular
baselines and meta-learners on Meta-Dataset, along with a competitive method
that we propose. We analyze performance as a function of various
characteristics of test tasks and examine the models' ability to leverage
diverse training sources for improving their generalization. We also propose a
new set of baselines for quantifying the benefit of meta-learning in
Meta-Dataset. Our extensive experimentation has uncovered important research
challenges and we hope to inspire work in these directions.
@article{triantafillou2019metadataset,
abstract = {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 it, we
find the procedure and datasets that are used to assess their progress lacking.
To address this limitation, we propose Meta-Dataset: a new benchmark for
training and evaluating models that is large-scale, consists of diverse
datasets, and presents more realistic tasks. We experiment with popular
baselines and meta-learners on Meta-Dataset, along with a competitive method
that we propose. We analyze performance as a function of various
characteristics of test tasks and examine the models' ability to leverage
diverse training sources for improving their generalization. We also propose a
new set of baselines for quantifying the benefit of meta-learning in
Meta-Dataset. Our extensive experimentation has uncovered important research
challenges and we hope to inspire work in these directions.},
added-at = {2020-03-11T20:33:26.000+0100},
author = {Triantafillou, Eleni and Zhu, Tyler and Dumoulin, Vincent and Lamblin, Pascal and Evci, Utku and Xu, Kelvin and Goroshin, Ross and Gelada, Carles and Swersky, Kevin and Manzagol, Pierre-Antoine and Larochelle, Hugo},
biburl = {https://www.bibsonomy.org/bibtex/29ab0f9370b0a68ebada4fb6080c1d350/kirk86},
description = {[1903.03096] Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examples},
interhash = {a4eb23e5268ef6fbfd4c5a1329acceb0},
intrahash = {9ab0f9370b0a68ebada4fb6080c1d350},
keywords = {datasets few-shot},
note = {cite arxiv:1903.03096Comment: Code available at https://github.com/google-research/meta-dataset},
timestamp = {2020-03-11T20:33:26.000+0100},
title = {Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few
Examples},
url = {http://arxiv.org/abs/1903.03096},
year = 2019
}