A Proposed Algorithm to Perform Few Shot Learning with different sampling sizes

Kashvi Dedhia, Mallika Konkar, Dhruvil Shah, Prachi Tawde
{"title":"A Proposed Algorithm to Perform Few Shot Learning with different sampling sizes","authors":"Kashvi Dedhia, Mallika Konkar, Dhruvil Shah, Prachi Tawde","doi":"10.1109/ICAECC54045.2022.9716609","DOIUrl":null,"url":null,"abstract":"Often times there is scarcity when it comes to model training of a quality dataset. Sometimes the data that is available is unlabelled, sometimes very few samples are available for some classes. In these cases, few shot learning comes in handy. There are two approaches to few shot learning Data Level approach and Parameter Level approach. The paper consists of analysis of the number of training samples using parameter level approach. Two classes have been used to perform few shot learning. Meta transfer learning is being used, by initialising the parameters of convolutional neutral networks (CNN) learner model from a model trained on ImageNet. It has been performed incrementally on datasets of various sizes. The results and performance of all the models are compared to the results when the entire dataset is used. As well as the advantages of using few shot learning. It has found its applications in a wide range of fields mainly computer vision, natural language processing etc.","PeriodicalId":199351,"journal":{"name":"2022 IEEE Fourth International Conference on Advances in Electronics, Computers and Communications (ICAECC)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-01-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 IEEE Fourth International Conference on Advances in Electronics, Computers and Communications (ICAECC)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICAECC54045.2022.9716609","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

Often times there is scarcity when it comes to model training of a quality dataset. Sometimes the data that is available is unlabelled, sometimes very few samples are available for some classes. In these cases, few shot learning comes in handy. There are two approaches to few shot learning Data Level approach and Parameter Level approach. The paper consists of analysis of the number of training samples using parameter level approach. Two classes have been used to perform few shot learning. Meta transfer learning is being used, by initialising the parameters of convolutional neutral networks (CNN) learner model from a model trained on ImageNet. It has been performed incrementally on datasets of various sizes. The results and performance of all the models are compared to the results when the entire dataset is used. As well as the advantages of using few shot learning. It has found its applications in a wide range of fields mainly computer vision, natural language processing etc.
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
一种不同采样大小的少镜头学习算法
当涉及到高质量数据集的模型训练时,通常存在稀缺性。有时可用的数据是未标记的,有时对于某些类可用的样本很少。在这些情况下,很少有射击学习能派上用场。少球学习有两种方法:数据级方法和参数级方法。本文采用参数水平法对训练样本数量进行了分析。两个类已经被用来执行一些射击学习。使用元迁移学习,从ImageNet上训练的模型初始化卷积神经网络(CNN)学习器模型的参数。它已经在不同大小的数据集上逐步执行。将所有模型的结果和性能与使用整个数据集时的结果进行比较。以及使用少枪学习的优点。它在计算机视觉、自然语言处理等领域有着广泛的应用。
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
Highly Accurate Static Hand Gesture Recognition Model Using Deep Convolutional Neural Network for Human Machine Interaction DV-Hop Propagation Based Localization in Wireless Sensor Networks A Proposed Algorithm to Perform Few Shot Learning with different sampling sizes OpenGL Based Simulation Test Bed for Aircraft Ground Telemetry System using Antenna Beam Forming Energy Efficiency and BER analysis of Concatenated FEC Coded MIMO-OFDM-FSO 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