%0 Conference Proceedings
%T NeurIPS’22 Cross-Domain MetaDL competition: Design and baseline results
%A Dustin Carrion Ojeda
%A Hong Chen
%A Adrian El Baz
%A Sergio Escalera
%A Chaoyu Guan
%A Isabelle Guyon
%A Ihsan Ullah
%A Xin Wang
%A Wenwu Zhu
%B Understanding Social Behavior in Dyadic and Small Group Interactions
%D 2022
%V 191
%F Dustin Carrion Ojeda2022
%O HUPBA; no menciona
%O exported from refbase (http://refbase.cvc.uab.es/show.php?record=3802), last updated on Mon, 24 Apr 2023 15:32:28 +0200
%X We present the design and baseline results for a new challenge in the ChaLearn meta-learning series, accepted at NeurIPS'22, focusing on "cross-domain" meta-learning. Meta-learning aims to leverage experience gained from previous tasks to solve new tasks efficiently (i.e., with better performance, little training data, and/or modest computational resources). While previous challenges in the series focused on within-domain few-shot learning problems, with the aim of learning efficiently N-way k-shot tasks (i.e., N class classification problems with k training examples), this competition challenges the participants to solve "any-way" and "any-shot" problems drawn from various domains (healthcare, ecology, biology, manufacturing, and others), chosen for their humanitarian and societal impact. To that end, we created Meta-Album, a meta-dataset of 40 image classification datasets from 10 domains, from which we carve out tasks with any number of "ways" (within the range 2-20) and any number of "shots" (within the range 1-20). The competition is with code submission, fully blind-tested on the CodaLab challenge platform. The code of the winners will be open-sourced, enabling the deployment of automated machine learning solutions for few-shot image classification across several domains.
%U https://proceedings.mlr.press/v191/carrion-ojeda22a
%U http://refbase.cvc.uab.es/files/CCB2022.pdf
%P 24-37