Transfer-learning and meta-learning are two effective methods to apply knowledge learned from large data sources to new tasks. In few-class, few-shot target task settings (i.e. when there are only a few classes and training examples available in the target task), meta-learning approaches that optimize for future task learning have outperformed the typical transfer approach of initializing model weights from a pre-trained starting point. But as we experimentally show, meta-learning algorithms that work well in the few-class setting do not generalize well in many-shot and many-class cases. In this paper, we propose a joint training approach that combines both transfer-learning and meta-learning. Benefiting from the advantages of each, our method obtains improved generalization performance on unseen target tasks in both few- and many-class and few- and many-shot scenarios.
@article{arxiv.1809.08346,
title = {A Meta-Learning Approach for Custom Model Training},
author = {Amir Erfan Eshratifar and Mohammad Saeed Abrishami and David Eigen and Massoud Pedram},
journal= {arXiv preprint arXiv:1809.08346},
year = {2019}
}