Self-adaptive label filtering learning for unsupervised domain adaptation

作     者：Qing TIAN Heyang SUN Shun PENG Tinghuai MA Qing TIAN;Heyang SUN;Shun PENG;Tinghuai MA

作者机构：School of Computer and SoftwareNanjing University of Information Science and TechnologyNanjing 210044China Engineering Research Center of Digital ForensicsMinistry of EducationNanjing University of Information Science and TechnologyNanjing 210044China 

出 版 物：《Frontiers of Computer Science》 (中国计算机科学前沿（英文版）)

年 卷 期：2023年第17卷第1期

页      面：225-227页

核心收录：

学科分类：08[工学] 081104[工学-模式识别与智能系统] 0835[工学-软件工程] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：supported by the National Natural Science Foundation of China(Grants Nos.62176128 and 61702273) the Natural Science Foundation of Jiangsu Province(BK20170956) the Open Projects Program of National Laboratory of Pattern Recognition(202000007) the Fundamental Research Funds for the Central Universities(NJ2019010) the Project Funded by the Priority Academic Program Development of Jiangsu Higher Education Institutions(PAPD)fund,the Postgraduate Research&Practice Innovation Program of Jiangsu Province KYCX21_1006,and was also sponsored by the Qing Lan Project. 

主　　题：filtering resort overcome 

摘      要：1 Introduction As an emerging machine learning paradigm,unsupervised domain adaptation(UDA)aims to train an effective model for unlabeled target domain by leveraging knowledge from related but distribution-inconsistent source domain.Most of the existing UDA methods[2]align class-wise distributions resorting to target domain pseudo-labels,for which hard labels may be misguided by misclassifications while soft labels are confusing with trivial noises so that both of them tend to cause frustrating performance.To overcome such drawbacks,as shown in Fig.1,we propose to achieve UDA by performing self-adaptive label filtering learning(SALFL)from both the statistical and the geometrical perspectives,which filters out the misclassified pseudo-labels to reduce negative transfer.Specifically,the proposed SALFL firstly predicts labels for the target domain instances by graph-based random walking and then filters out those noise labels by self-adaptive learning strategy.