Timezone: »

 
Poster
Meta-Album: Multi-domain Meta-Dataset for Few-Shot Image Classification
Ihsan Ullah · Dustin Carrión-Ojeda · Sergio Escalera · Isabelle Guyon · Mike Huisman · Felix Mohr · Jan N. van Rijn · Haozhe Sun · Joaquin Vanschoren · Phan Anh Vu

Thu Dec 01 02:00 PM -- 04:00 PM (PST) @ Hall J #1031
in Poster Session 6 »
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 OpenML.org. Our website https://meta-album.github.io/ 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.
Keywords: Meta-Learning · Few-Shot Learning · cross-domain meta-learning · meta-dataset
[ Paper]  [ Poster]  [ OpenReview] 

Author Information

Ihsan Ullah (Université Paris Saclay)
Dustin Carrión-Ojeda (TU Darmstadt)
Sergio Escalera (Computer Vision Center and University of Barcelona)
Isabelle Guyon (Google and ChaLearn)
Mike Huisman (Leiden University)
Felix Mohr (Universidad de La Sabana)
Jan N. van Rijn (Leiden University)
Haozhe Sun (Université Paris-Saclay)
Joaquin Vanschoren (Eindhoven University of Technology)
Phan Anh Vu (Université Paris Saclay)

More from the Same Authors