NeurIPS'22 Cross-Domain MetaDL competition: Design and baseline results - Laboratoire Interdisciplinaire des Sciences du Numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

NeurIPS'22 Cross-Domain MetaDL competition: Design and baseline results

NeurIPS'22 Cross-Domain MetaDL Challenge: Conception et résultats de référence

Résumé

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.
Fichier principal
Vignette du fichier
paper.pdf (439.58 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03765151 , version 1 (30-08-2022)

Identifiants

  • HAL Id : hal-03765151 , version 1

Citer

Dustin Carrión-Ojeda, Hong Chen, Adrian El Baz, Sergio Escalera, Chaoyu Guan, et al.. NeurIPS'22 Cross-Domain MetaDL competition: Design and baseline results. Meta-Knowledge Transfer/Communication in Different Systems, Sep 2022, Grenoble, France. ⟨hal-03765151⟩
121 Consultations
89 Téléchargements

Partager

Gmail Facebook X LinkedIn More