MetaMix: Improved Meta-Learning with Interpolation-based Consistency Regularization
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.
Cite
@article{arxiv.2009.13735,
title = {MetaMix: Improved Meta-Learning with Interpolation-based Consistency Regularization},
author = {Yangbin Chen and Yun Ma and Tom Ko and Jianping Wang and Qing Li},
journal= {arXiv preprint arXiv:2009.13735},
year = {2020}
}
Comments
8 pages, 3 figures, 3 tables. Accepted by 25th International Conference on Pattern Recognition (ICPR) 2020