MetaMix: Improved meta-learning with interpolation-based consistency regularization

Yangbin Chen, Yun Ma, Tom Ko, Jianping Wang, Qing Li

Research output: Chapter in book / Conference proceedingConference article published in proceeding or bookAcademic researchpeer-review

4 Citations (Scopus)

Abstract

Model-Agnostic Meta-Learning (MAML) and its variants are popular few-shot classification methods. They train an initializer across a variety of sampled learning tasks (also known as episodes) such that the initialized model can adapt quickly to new ones. However, current MAML-based algorithms have limitations in forming generalizable decision boundaries. In this paper, we propose an approach called MetaMix, which generates virtual feature-target pairs within each episode to regularize the backbone models. MetaMix can be integrated with any of the MAML-based algorithms and learn the decision boundaries generalizing better to new tasks. Experiments on the mini-ImageNet, CUB, and FC100 datasets show that MetaMix improves the performance of MAML-based algorithms and achieves state-of-the-art result when integrated with Meta-Transfer Learning.

Original languageEnglish
Title of host publicationProceedings of ICPR 2020 - 25th International Conference on Pattern Recognition
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages407-414
Number of pages8
ISBN (Electronic)9781728188089
DOIs
Publication statusPublished - 2020
Event25th International Conference on Pattern Recognition, ICPR 2020 - Virtual, Milan, Italy
Duration: 10 Jan 202115 Jan 2021

Publication series

NameProceedings - International Conference on Pattern Recognition
ISSN (Print)1051-4651

Conference

Conference25th International Conference on Pattern Recognition, ICPR 2020
Country/TerritoryItaly
CityVirtual, Milan
Period10/01/2115/01/21

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition

Fingerprint

Dive into the research topics of 'MetaMix: Improved meta-learning with interpolation-based consistency regularization'. Together they form a unique fingerprint.

Cite this