典型文献
Self-corrected unsupervised domain adaptation
文献摘要：
Unsupervised domain adaptation(UDA),which aims to use knowledge from a label-rich source domain to help learn unlabeled target domain,has recently attracted much attention.UDA methods mainly concentrate on source classifi-cation and distribution alignment between domains to expect the correct target prediction.While in this paper,we attempt to learn the target prediction end to end directly,and develop a Self-corrected unsupervised domain adaptation(SCUDA)method with probabilistic label correction.SCUDA adopts a probabilistic label corrector to learn and correct the target labels directly.Specifically,besides model parameters,those target pseudo-labels are also updated in learning and corrected by the anchor-variable,which preserves the class candidates for samples.Experiments on real datasets show the competitive-ness of SCUDA.
文献关键词：
中图分类号：
作者姓名：
Yunyun WANG;Chao WANG;Hui XUE;Songcan CHEN
作者机构：
School of Computer Science and Engineering,Nanjing University of Posts&Telecommunications,Nanjing 210046,China;School of Computer Science and Engineering,Southeast University,Nanjing 210096,China;School of Computer Science and Technology,Nanjing University of Aeronautics and Astronautics,Nanjing 210023,China
文献出处：
引用格式：
[1]Yunyun WANG;Chao WANG;Hui XUE;Songcan CHEN-.Self-corrected unsupervised domain adaptation)[J].计算机科学前沿,2022(05):33-41
A类：
SCUDA
B类：
Self,corrected,unsupervised,adaptation,Unsupervised,which,aims,use,knowledge,from,rich,source,help,unlabeled,target,has,recently,attracted,much,attention,methods,mainly,concentrate,classifi,cation,distribution,alignment,between,domains,expect,prediction,While,this,paper,attempt,end,directly,develop,probabilistic,correction,adopts,corrector,labels,Specifically,besides,model,parameters,those,pseudo,are,also,updated,learning,by,anchor,variable,preserves,candidates,samples,Experiments,real,datasets,show,competitive,ness
AB值：
0.553292
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。
