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

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 tasks. However, current MAML-based algorithms have limitations in forming generalizable decision boundaries. In this paper, we propose an approach called MetaMix. It 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 the 25th International Conference on Pattern Recognition (ICPR)
Place of PublicationMilano (Virtual)
Pages407-414
Number of pages8
Publication statusPublished - 10 Jan 2021

Cite this