Open AccessLessons learned from the NeurIPS 2021 MetaDL challenge: Backbone fine-tuning without episodic meta-learning dominates for few-shot learning image classification
Author(s) -
Adrian El Baz,
Ihsan Ullah,
Edesio Alcobaça,
André C. P. L. F. de Carvalho,
Hong Chen,
Fábio Furlan Ferreira,
Henry Gouk,
Chaoyu Guan,
Isabelle Guyon,
Timothy M. Hospedales,
Shell Xu Hu,
Mike Huisman,
Frank Hutter,
Zhengying Liu,
Felix Mohr,
Ekrem Öztürk,
Jan N. van Rijn,
Haozhe Sun,
Xin Wang,
Wenwu Zhu
Publication year - 2021
Publication title -
hal (le centre pour la communication scientifique directe)
Language(s) - English
Resource type - Conference proceedings
Subject(s) - shot (pellet) , computer science , meta learning (computer science) , artificial intelligence , one shot , image (mathematics) , machine learning , task (project management) , engineering , materials science , mechanical engineering , systems engineering , metallurgy