A Meta-Learning Approach for Custom Model Training


  • Amir Erfan Eshratifar University of Southern California
  • Mohammad Saeed Abrishami University of Southern California
  • David Eigen Clarifai
  • Massoud Pedram University of Southern California




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 pretrained starting point. But as we experimentally show, metalearning 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.




How to Cite

Eshratifar, A. E., Abrishami, M. S., Eigen, D., & Pedram, M. (2019). A Meta-Learning Approach for Custom Model Training. Proceedings of the AAAI Conference on Artificial Intelligence, 33(01), 9937-9938. https://doi.org/10.1609/aaai.v33i01.33019937



Student Abstract Track