Journal article

LogDet Metric-Based Domain Adaptation

Youfa Liu, Bo Du, Weiping Tu, Mingming Gong, Yuhong Guo, Dacheng Tao

IEEE Transactions on Neural Networks and Learning Systems | Institute of Electrical and Electronics Engineers | Published : 2020

Abstract

Domain adaptation has proven to be successful in dealing with the case where training and test samples are drawn from two kinds of distributions, respectively. Recently, the second-order statistics alignment has gained significant attention in the field of domain adaptation due to its superior simplicity and effectiveness. However, researchers have encountered major difficulties with optimization, as it is difficult to find an explicit expression for the gradient. Moreover, the used transformation employed here does not perform dimensionality reduction. Accordingly, in this article, we prove that there exits some scaled LogDet metric that is more effective for the second-order statistics ali..

View full abstract

University of Melbourne Researchers

Grants

Awarded by National Natural Science Foundation of China


Awarded by National Key R&D Program of China


Awarded by Natural Science Foundation of Hubei Province


Awarded by Science and Technology Major Project of Hubei Province (Next Generation AI Technologies)


Awarded by Australian Research Council


Funding Acknowledgements

This work was supported in part by the National Natural Science Foundation of China under Grant 61822113 and Grant 41871243, in part by the National Key R&D Program of China under Grant 2018YFA060550, in part by the Natural Science Foundation of Hubei Province under Grant 2018CFA050, in part by the Science and Technology Major Project of Hubei Province (Next Generation AI Technologies) under Grant 2019AEA170, and in part by the Australian Research Council under Project FL-170100117, Project DP-180103424, and Project IH-180100002.