检索结果-南通市图书馆

Robust and Discriminative Feature learning via Mutual Information Maximization for Object Detection in Aerial Images

引用

Computers, Materials & Continua 2024年第9期80卷 4149-4171页

作者： Xu Sun Yinhui Yu Qing Cheng School of Communication Engineering Jilin UniversityChangchun130012China

Object detection in unmanned aerial vehicle(UAV)aerial images has become increasingly important in military and civil *** object detection models are not robust enough against interclass similarity and intraclass variability of small objects,and UAV-specific nuisances such as uncontrolledweather *** previous approaches focusing on high-level semantic information,we report the importance of underlying features to improve detection accuracy and robustness fromthe information-theoretic ***,we propose a robust and discriminative feature learning approach through mutual information maximization(RD-MIM),which can be integrated into numerous object detection methods for aerial ***,we present the rank sample mining method to reduce underlying feature differences between the natural image domain and the aerial image ***,we design a momentum contrast learning strategy to make object features similar to the same category and dissimilar to different ***,we construct a transformer-based global attention mechanism to boost object location semantics by leveraging the high interrelation of different receptive *** conduct extensive experiments on the VisDrone and Unmanned Aerial Vehicle Benchmark Object Detection and Tracking(UAVDT)datasets to prove the effectiveness of the proposed *** experimental results show that our approach brings considerable robustness gains to basic detectors and advanced detection methods,achieving relative growth rates of 51.0%and 39.4%in corruption robustness,*** code is available at https://***/cq100/RD-MIM(accessed on 2 August 2024).

关键词： Aerial images object detection mutual information contrast learning attention mechanism

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：