Pub Date : 2022-08-31DOI: 10.48550/arXiv.2208.14686
Dustin Carri'on-Ojeda, Hong Chen, Adrian El Baz, Sergio Escalera, Chaoyu Guan, Isabelle M Guyon, I. Ullah, Xin Wang, Wenwu Zhu
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.
{"title":"NeurIPS'22 Cross-Domain MetaDL competition: Design and baseline results","authors":"Dustin Carri'on-Ojeda, Hong Chen, Adrian El Baz, Sergio Escalera, Chaoyu Guan, Isabelle M Guyon, I. Ullah, Xin Wang, Wenwu Zhu","doi":"10.48550/arXiv.2208.14686","DOIUrl":"https://doi.org/10.48550/arXiv.2208.14686","url":null,"abstract":"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.","PeriodicalId":435618,"journal":{"name":"Meta-Knowledge Transfer @ ECML/PKDD","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121903297","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：