TY - GEN
T1 - MetaMix: Improved meta-learning with interpolation-based consistency regularization
AU - Chen, Yangbin
AU - Ma, Yun
AU - Ko, Tom
AU - Wang, Jianping
AU - Li, Qing
N1 - Publisher Copyright:
© 2020 IEEE
PY - 2020
Y1 - 2020
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85110535799&partnerID=8YFLogxK
U2 - 10.1109/ICPR48806.2021.9413158
DO - 10.1109/ICPR48806.2021.9413158
M3 - Conference article published in proceeding or book
AN - SCOPUS:85110535799
T3 - Proceedings - International Conference on Pattern Recognition
SP - 407
EP - 414
BT - Proceedings of ICPR 2020 - 25th International Conference on Pattern Recognition
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 25th International Conference on Pattern Recognition, ICPR 2020
Y2 - 10 January 2021 through 15 January 2021
ER -