Learning Domain-Invariant and Discriminative Features for Homogeneous Unsupervised Domain Adaptation  

作　　者：ZHANG Yun WANG Nianbin CAI Shaobin 

机构地区：[1]College of Computer Science and Technology,Harbin Engineering University,Harbin 150001,China [2]School of Electronic Information Engineering,Foshan University,Foshan 528225,China

出　　处：《Chinese Journal of Electronics》2020年第6期1119-1125,共7页电子学报（英文版）

基　　金：supported by the National Natural Science Foundation of China(No.61772152);the National Key Research and Development Program of China(No.2018YFC0806800);the Technical Basic Research Project(No.JSQB2017206C002);the Project funded by China Postdoctoral Science Foundation(No.2019M651262);the Youth Fund Project of Humanities and Social Sciences Research of the Ministry of Education of China(No.20YJCZH172);the Postdoctoral Foundation of Heilongjiang Province(No.LBH-Z19015).

摘　　要：A classifier trained on the label-rich source dataset tends to perform poorly on the unlabeled target dataset because of the distribution discrepancy across different datasets.Unsupervised domain adaptation aims to transfer knowledge from the labeled source dataset to the unlabeled target dataset to solve this problem.Most of the existing unsupervised domain adaptation methods only concentrate on learning domain-invariant features across different domains,but they neglect the discriminability of the learned features to satisfy the cluster assumption.In this paper,we propose Semantic pairwise centroid alignment(SPCA),which is a point-wise method to learn both domain-invariant and discriminative features for homogeneous unsupervised domain adaptation.SPCA utilizes a novel semantic centroid loss to reduce the intraclass distance in feature space by using source data and target High-confidence centroid points(HCCPs).Then a classifier trained on source features is expected to generalize well on target features.Extensive experiments on visual recognition tasks verify the effectiveness of the proposed SPCA and also demonstrate that both domaininvariant and discriminative features learned by SPCA can significantly boost the performance of homogeneous unsupervised domain adaptation.

关 键 词：Transfer learning Domain adaptation Semantic alignment Feature extraction 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程] TP391.41[自动化与计算机技术—控制科学与工程]