检索结果-南通市图书馆

An Improved deep fusion CNN for Image Recognition

Computers, Materials & Continua 2020年第11期65卷 1691-1706页

作者： Rongyu Chen Lili Pan Cong Li Yan Zhou Aibin Chen Eric Beckman College of Computer Science and Information Technology Central South University of Forestry&TechnologyChangsha410114China China Chaplin School of Hospitality of Hospitality and Tourism Management Florida International UniversityNorth Miami33181USA

With the development of deep Convolutional Neural Networks(DCNNs),the extracted features for image recognition tasks have shifted from low-level features to the high-level semantic features of *** studies have shown that the deeper the network is,the more abstract the features ***,the recognition ability of deep features would be limited by insufficient training *** address this problem,this paper derives an improved deep fusion Convolutional Neural Network(DF-Net)which can make full use of the differences and complementarities during network learning and enhance feature expression under the condition of limited ***,DF-Net organizes two identical subnets to extract features from the input image in parallel,and then a well-designed fusion module is introduced to the deep layer of DF-Net to fuse the subnet’s features in ***,the more complex mappings are created and the more abundant and accurate fusion features can be extracted to improve recognition ***,a corresponding training strategy is also proposed to speed up the convergence and reduce the computation overhead of network ***,DF-Nets based on the well-known ResNet,DenseNet and MobileNetV2 are evaluated on CIFAR100,Stanford Dogs,and *** analysis and experimental results strongly demonstrate that DF-Net enhances the performance of DCNNs and increases the accuracy of image recognition.

关键词： deep convolutional neural networks deep features image recognition deep fusion feature fusion.

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

Benggang segmentation via deep exchanging of digital orthophoto map and digital surface model features

引用

International Soil and Water Conservation Research 2024年第3期12卷 589-599页

作者： Shengyu Shen Jiasheng Chen Dongbing Cheng Honghu Liu Tong Zhang Department of Soil and Water Conservation Changjiang River Scientific Research Institute of Changjiang Water Resources CommissionWuhan430010China Research Center on Mountain Torrent&Geologic Disaster Prevention Ministry of Water ResourcesWuhan430010China State Key Laboratory of Information Engineering in Surveying Mapping and Remote Sensing(LIESMARS)Wuhan UniversityWuhan430079China

Benggang is a typical fragmented erosional landscape in southern and southeastern China,posing sig-nificant risk to the local residents and economic ***,an efficient and accurate fine-grained segmentation method is crucial for monitoring the Benggang *** this paper,we propose a deep learning-based automatic segmentation method for Benggang by integrating high-resolution Digital Orthophoto Map(DOM)and Digital Surface Model(DSM)*** DSM data is used to extract slope maps,aiming to capture primary morphological *** proposed method consists of a dual-stream convolutional encoder-decoder network in which multiple cascaded convolutional layers and a skip connection scheme are used to extract morphological and visual features of the Benggang *** rich discriminative information in the DOM and slope data is fused by a channel exchanging mechanism that dynamically exchanges the most discriminative features from either the DOM or DSM stream ac-cording to their importance at the channel *** experiments were conducted on a chal-lenging dataset collected from Guangdong Province,China,and the results show that the proposed channel exchanging network based deep fusion method achieves 84.62%IoU in Benggang segmentation,outperforming several existing unimodal or multimodal *** proposed multimodal segmen-tation method greatly improves the efficiency of large-scale discovery of Benggang,and thus is important for the management and restoration of Benggang in southern and southeastern China,as well as the monitoring of other similar erosional landscapes.

关键词： Benggang segmentation deep fusion Channel exchanging DOM DSM

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

信息技术与教学深度融合的限度及其超越

引用

教育学 2019年第6期

作者：罗祖兵

在当前的教育研究中，存在将信息技术与教学“深度融合”唯一化、万能化的倾向。其实，二者的深度融合是有限度的，它比较适合于预成性教学、知识类目标的教学及陈述性知识的教学。为了充分发挥信息技术的教学价值，不能只强调“深度融... 详细信息

在当前的教育研究中，存在将信息技术与教学“深度融合”唯一化、万能化的倾向。其实，二者的深度融合是有限度的，它比较适合于预成性教学、知识类目标的教学及陈述性知识的教学。为了充分发挥信息技术的教学价值，不能只强调“深度融合”，更应实行“全面融合”。从“融合程度”上讲，有简单结合、中度整合、深度融合；从“融合途径”上讲，信息技术可以作为环境、作为手段、作为内容、作为思想融入教学。

关键词：信息技术教学深度融合全面融合 information technology teaching deep fusion comprehensive fusion

来源：人大复印报刊资料评论

在线全文

人大复印报刊资料

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

在线全文

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

在线全文

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：