检索结果-南通市图书馆

Computational Visual Media 2024年第4期10卷 725-740页

作者： Zhaofeng Xuan Dayan Wu Wanqian Zhang Qinghang Su Bo Li Weiping Wang Institute of Information Engineering Chinese Academy of SciencesBeijing 100085China School of Cyber Security University of Chinese Academy of SciencesBeijing 100049China Key Laboratory of Cyberspace Security Defense Institute of Information EngineeringChinese Academy of SciencesBeijing 100085China

Asymmetric image retrieval methods have drawn much attention due to their effectiveness in resource-constrained *** try to learn two models in an asymmetric paradigm,i.e.,a small model for the query side and a large model for the ***,we empirically find that the mutual training scheme(learning with each other)will inevitably degrade the performance of the large gallery model,due to the negative effects exerted by the small query *** this paper,we propose Central Similarity Consistency Hashing(CSCH),which simultaneously learns a small query model and a large gallery model in a mutually promoted manner,ensuring both high retrieval accuracy and efficiency on the query *** achieve this,we first introduce heuristically generated hash centers as the common learning target for both two *** of randomly assigning each hash center to its corresponding category,we introduce the Hungarian algorithm to optimally match each of them by aligning the Hamming similarity of hash centers to the semantic similarity of their ***,we introduce the instance-level consistency loss,which enables the explicit knowledge transfer from the gallery model to the query one,without the sacrifice of gallery *** by the unified learning of hash centers and the distilled knowledge from gallery model,the query model can be gradually aligned to the Hamming space of the gallery model in a decoupled *** experiments demonstrate the superiority of our CSCH method compared with current state-of-the-art deep hashing *** open-source code is available at https://***/dubanx/CSCH.

关键词： asymmetric image retrieval deep hashing Hungarian algorithm decoupled manner

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：