检索结果-南通市图书馆

A Novel Siamese Network for Few/Zero-Shot Handwritten Character Recognition Tasks

Computers, Materials & Continua 2023年第1期74卷 1837-1854页

作者： Nagwa Elaraby Sherif Barakat Amira Rezk Department of Information System Faculty of Computers and InformationMansoura UniversityMansouraP.O.35516Egypt

Deep metric learning is one of the recommended methods for the challenge of supporting few/zero-shot learning by deep *** depends on building a Siamese architecture of two homogeneous Convolutional Neural Networks(CNNs)for learning a distance function that can map input data from the input space to the feature *** of determining the class of each sample,the Siamese architecture deals with the existence of a few training samples by deciding if the samples share the same class identity or *** traditional structure for the Siamese architecture was built by forming two CNNs from scratch with randomly initialized weights and trained by binary cross-entropy *** two CNNs from scratch is a trial and error and time-consuming *** addition,training with binary crossentropy loss sometimes leads to poor *** this paper,a novel Siamese network is proposed and applied to few/zero-shot Handwritten Character Recognition(HCR)*** novelties of the proposed network are in.1)Utilizing transfer learning and using the pre-trained AlexNet as a feature extractor in the Siamese ***-tuning a pre-trained network is typically faster and easier than building from scratch.2)Training the Siamese architecture with contrastive loss instead of the binary *** loss helps the network to learn a nonlinear mapping function that enables it to map the extracted features in the vector space with an optimal *** proposed network is evaluated on the challenging chars74k datasets by conducting two *** is for testing the proposed network in few-shot learning while the other is for testing it in zero-shot *** recognition accuracy of the proposed network reaches to 85.6%and 82%in few-and zero-shot learning *** addition,a comparison between the performance of the proposed Siamese network and the traditional Siamese CNNs is *** comparison results show that the proposed network achieves hi

关键词： Handwritten character recognition(HCR) few-shot learning zero-shot learning deep metric learning transfer learning contrastive loss chars74k datasets

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

欢迎您,

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：