Meta-ensemble learning with a multi-headed model for few-shot problems

doi:10.1016/j.icte.2022.09.001

Meta-ensemble learning with a multi-headed model for few-shot problems

2023-10-01

2

OA

AI

DOI：10.1016/j.icte.2022.09.001

原文链接

查看原文

摘要

En 中文

Recent meta-learning algorithms for few-shot learning are based on episodic training where each episode consists of only a few support and query samples to imitate a target few-shot task. However, due to the limited number of categories and few samples in each category, this framework suffers from over-fitting to both a meta-training dataset and the support set of each episode. It also causes a large variance in the accuracy of each episode, which reduces reliability and confidence in model performance. To address this problem, we propose a novel meta -ensemble learning approach based on a recent ensemble method: a multi-input multi-output (MIMO) configuration. Our approach is simply applied to existing meta-learning algorithms. Multiple subnetworks in a single model simultaneously learn multiple episodes and ensemble the predictions, leveraging the model capacity. We show that meta-ensemble learning achieves significant improvement in generalization. It also improves the performance of meta-learning algorithms on few-shot classification benchmarks.(c) 2022 The Author(s). Published by Elsevier B.V. on behalf of The Korean Institute of Communications and Information Sciences.This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).

Keyword:

Computer vision

Few-shot learning

Meta learning

Meta-ensemble learning with a multi-headed model for few-shot problems

摘要

AI总结

期刊

机构

引用论文