Prototype and Metric Based Prediction for Data-Efficient Training

Gaowei Zhou
{"title":"Prototype and Metric Based Prediction for Data-Efficient Training","authors":"Gaowei Zhou","doi":"10.1109/acmlc58173.2022.00019","DOIUrl":null,"url":null,"abstract":"We propose a prototype- and metric-based prediction method together with several training pipelines suitable for training a network without using any additional data in the few-shot learning tasks with different intra-class variances. Being tested on two datasets commonly used for few-shot learning, our method has shown satisfactory ability to improve data efficiency and prevent overfitting. It even competes with the meta-learning-based method trained with a lot of extra labeled samples on the dataset with low intra-class variance and shows no significant performance gap when it comes to the dataset with a high intra-class variance. We reported 99.0% acc on the Omniglot dataset and 48.0% acc on the mini-ImageNet for 5-way 5-shot tasks.","PeriodicalId":375920,"journal":{"name":"2022 5th Asia Conference on Machine Learning and Computing (ACMLC)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 5th Asia Conference on Machine Learning and Computing (ACMLC)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/acmlc58173.2022.00019","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

We propose a prototype- and metric-based prediction method together with several training pipelines suitable for training a network without using any additional data in the few-shot learning tasks with different intra-class variances. Being tested on two datasets commonly used for few-shot learning, our method has shown satisfactory ability to improve data efficiency and prevent overfitting. It even competes with the meta-learning-based method trained with a lot of extra labeled samples on the dataset with low intra-class variance and shows no significant performance gap when it comes to the dataset with a high intra-class variance. We reported 99.0% acc on the Omniglot dataset and 48.0% acc on the mini-ImageNet for 5-way 5-shot tasks.
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
基于原型和度量的数据高效训练预测
我们提出了一种基于原型和度量的预测方法,以及几种适合训练网络的训练管道,而无需在具有不同类内方差的少量学习任务中使用任何额外数据。通过对两组常用的few-shot学习数据集的测试,我们的方法显示出了令人满意的提高数据效率和防止过拟合的能力。它甚至可以与基于元学习的方法竞争,该方法在类内方差低的数据集上训练了大量额外的标记样本,并且在类内方差高的数据集上没有明显的性能差距。我们在Omniglot数据集上报告了99.0%的acc,在mini-ImageNet上报告了48.0%的acc。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
A Data-Driven Pricing Strategy for Automobile Insurance Policies An Evolutionary Strategy Based Training Optimization of Supervised Machine Learning Algorithms (EStoTimeSMLAs) Copyright Page Integrated Age Estimation Mechanism based on Decision-Level Fusion of Error and Deviation Orientation Model Application of PRA and Machine Learning Algorithm in Budget Data Acquisition and Processing System
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1