Lessons learned from the NeurIPS 2021 MetaDL challenge: Backbone fine-tuning without episodic meta-learning dominates for few-shot learning image classification

Adrian El Baz, Ihsan Ullah, Edesio Alcobaça, André C. P. L. F. Carvalho, Hong Chen, Fabio Ferreira, Henry Gouk, Chaoyu Guan, Isabelle Guyon, Timothy Hospedales, Shell Hu, Mike Huisman, Frank Hutter, Zhengying Liu, Felix Mohr, Ekrem Oztürk, Jan N. van Rijn, Haozhe Sun, Xin Wang, Wenwu Zhu

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract / Description of output

Although deep neural networks are capable of achieving performance superior to humans on various tasks, they are notorious for requiring large amounts of data and computing resources, restricting their success to domains where such resources are available. Metalearning methods can address this problem by transferring knowledge from related tasks, thus reducing the amount of data and computing resources needed to learn new tasks. We organize the MetaDL competition series, which provide opportunities for research groups all over the world to create and experimentally assess new meta-(deep)learning solutions for real problems. In this paper, authored collaboratively between the competition organizers and the top-ranked participants, we describe the design of the competition, the datasets, the best experimental results, as well as the top-ranked methods in the NeurIPS 2021 challenge, which attracted 15 active teams who made it to the final phase (by outperforming the baseline), making over 100 code submissions during the feedback phase. The solutions of the top participants have been open-sourced. The lessons learned include that learning good representations is essential for effective transfer learning
Original languageEnglish
Title of host publicationProceedings of the NeurIPS 2021 Competition and Demonstration Track
EditorsDouwe Kiela, Barbara Caputo, Marco Ciccone
PublisherPMLR
Pages80-96
Number of pages17
Volume176
DOIs
Publication statusPublished - 8 Dec 2021
Event2nd MetaDL Competition Workshop at NeurIPS
-
Duration: 8 Dec 20218 Dec 2021
Conference number: 2
https://metalearning.chalearn.org/metadlneurips2021

Publication series

NameProceedings of Machine Learning Research
PublisherPMLR
Volume176
ISSN (Electronic)2640-3498

Workshop

Workshop2nd MetaDL Competition Workshop at NeurIPS
Abbreviated titleMetaDL@NeurIPS'21
Period8/12/218/12/21
Internet address

Keywords / Materials (for Non-textual outputs)

  • automated machine learning
  • meta-learning
  • competition

Fingerprint

Dive into the research topics of 'Lessons learned from the NeurIPS 2021 MetaDL challenge: Backbone fine-tuning without episodic meta-learning dominates for few-shot learning image classification'. Together they form a unique fingerprint.

Cite this