Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

6-2019

Abstract

Meta-learning has been proposed as a framework to address the challenging few-shot learning setting. The key idea is to leverage a large number of similar few-shot tasks in order to learn how to adapt a base-learner to a new task for which only a few labeled samples are available. As deep neural networks (DNNs) tend to overfit using a few samples only, meta-learning typically uses shallow neural networks (SNNs), thus limiting its effectiveness. In this paper we propose a novel few-shot learning method called meta-transfer learning (MTL) which learns to adapt a deep NN for few shot learning tasks. Specifically, "meta" refers to training multiple tasks, and "transfer" is achieved by learning scaling and shifting functions of DNN weights for each task. In addition, we introduce the hard task (HT) meta-batch scheme as an effective learning curriculum for MTL. We conduct experiments using (5-class, 1-shot) and (5-class, 5-shot) recognition tasks on two challenging few-shot learning benchmarks: miniImageNet and Fewshot-CIFAR100. Extensive comparisons to related works validate that our meta-transfer learning approach trained with the proposed HT meta-batch scheme achieves top performance. An ablation study also shows that both components contribute to fast convergence and high accuracy.

Keywords

Few-shot learning, meta-learning, hard task mining, object classification

Discipline

Artificial Intelligence and Robotics | Numerical Analysis and Scientific Computing

Research Areas

Data Science and Engineering

Publication

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition: Long Beach, CA, June 16-20: Proceedings

First Page

403

Last Page

412

ISBN

9781728132938

Identifier

10.1109/CVPR.2019.00049

Publisher

IEEE Computer Society

City or Country

Los Alamitos, CA

Copyright Owner and License

Authors

Additional URL

https://doi.org/10.1109/CVPR.2019.00049

Download

Share

COinS