典型文献
Metric learning for domain adversarial network
文献摘要:
1 Introduction
The existing domain adaptation methods[1,2]always aim to perform domain alignment between the source and target domain to alleviate the problem of domain shift[3].
The target domain samples are likely to scatter on the classification boundary due to a lack of label information.Therefore,how to identify these overlapping classes in the target domain,called easily-confused classes,becomes the key to the improvement of classification performance.
文献关键词:
中图分类号:
作者姓名:
Haifeng HU;Yan YANG;Yueming YIN;Jiansheng WU
作者机构:
College of Telecommunications and Information Engineering,Nanjing University of Posts and Telecommunications,Nanjing 210023,China;College of Geography and Biological Information,Nanjing University of Posts and Telecommunications,Nanjing 210023,China
文献出处:
引用格式:
[1]Haifeng HU;Yan YANG;Yueming YIN;Jiansheng WU-.Metric learning for domain adversarial network)[J].计算机科学前沿,2022(05):213-215
A类:
B类:
Metric,learning,domain,adversarial,network,Introduction,
The,existing,adaptation,methods,always,aim,alignment,between,source,target,alleviate,problem,shift,samples,are,likely,scatter,classification,boundary,due,lack,label,information,Therefore,how,identify,these,overlapping,classes,called,easily,confused,becomes,key,improvement,performance
AB值:
0.681516
相似文献
机标中图分类号,由域田数据科技根据网络公开资料自动分析生成,仅供学习研究参考。