Meta-Album: Multi-domain Meta-Dataset for Few-Shot Image ClassificationDownload PDF

Published: 17 Sept 2022, Last Modified: 12 Mar 2024NeurIPS 2022 Datasets and Benchmarks Readers: Everyone
Keywords: meta-dataset, few-shot learning, meta-learning, cross-domain meta-learning
TL;DR: A meta-dataset for few shot image classification
Abstract: We introduce Meta-Album, an image classification meta-dataset designed to facilitate few-shot learning, transfer learning, meta-learning, among other tasks. It includes 40 open datasets, each having at least 20 classes with 40 examples per class, with verified licences. They stem from diverse domains, such as ecology (fauna and flora), manufacturing (textures, vehicles), human actions, and optical character recognition, featuring various image scales (microscopic, human scales, remote sensing). All datasets are preprocessed, annotated, and formatted uniformly, and come in 3 versions (Micro $\subset$ Mini $\subset$ Extended) to match users’ computational resources. We showcase the utility of the first 30 datasets on few-shot learning problems. The other 10 will be released shortly after. Meta-Album is already more diverse and larger (in number of datasets) than similar efforts, and we are committed to keep enlarging it via a series of competitions. As competitions terminate, their test data are released, thus creating a rolling benchmark, available through Our website contains the source code of challenge winning methods, baseline methods, data loaders, and instructions for contributing either new datasets or algorithms to our expandable meta-dataset.
Author Statement: Yes
Open Credentialized Access: NA
Dataset Url:
Dataset Embargo: Meta-Album datasets will be released according to the following schedule on OpenML ( ): Set-0 : 10 datasets - released 06 June 2022 Set-1 and Set-2 : 20 datasets - to be released on or before 30 November 2022, before NeurIPS (datasets currently used in a NeurIPS’22 challenge) Set-3 : 10 datasets - to be released on or before 06 June 2023 (datasets to be used in an upcoming challenge on bias detection)
License: Meta-Album is realeased under the license : CC BY-NC 4.0 (
Supplementary Material: zip
Contribution Process Agreement: Yes
In Person Attendance: Yes
Community Implementations: [![CatalyzeX](/images/catalyzex_icon.svg) 18 code implementations](
13 Replies