NeurIPS'22 Cross-Domain MetaDL competition: Design and baseline results
This competition addresses the need for automated machine learning solutions in humanitarian and societal impact domains like healthcare and ecology, though it is incremental as it extends previous within-domain challenges to cross-domain settings.
The paper introduces the NeurIPS'22 Cross-Domain MetaDL competition, which tackles the problem of meta-learning for few-shot image classification across diverse domains by creating Meta-Album, a meta-dataset of 40 datasets from 10 domains, and reports baseline results for this new challenge.
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.