Please use this identifier to cite or link to this item: http://hdl.handle.net/2440/116193
Citations
Scopus Web of Science® Altmetric
?
?
Type: Journal article
Title: Unsupervised domain adaptation using robust class-wise matching
Author: Zhang, L.
Wang, P.
Wei, W.
Lu, H.
Shen, C.
van den Hengel, A.
Zhang, Y.
Citation: IEEE Transactions on Circuits and Systems for Video Technology, 2019; 29(5):1339-1349
Publisher: IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
Issue Date: 2019
ISSN: 1051-8215
1558-2205
Statement of
Responsibility: 
Lei Zhang, Peng Wang, Wei Wei, Hao Lu, Chunhua Shen, Anton van den Hengel, Yanning Zhang
Abstract: Unsupervised domain adaptation (DA) enables a classifier trained on data from one domain to be applied to data from another without labels. Given that the key to transferring a classifier across domains is to mitigate the data distribution mismatch for each class, most previous works completely or partially focus on global distribution matching across domains. The global data space, however, can be complicated, which makes modelling the global distribution difficult. To mitigate this problem, we present a novel unsupervised DA framework where the DA problem is addressed by proposing a robust class-wise matching strategy. Specifically, through minimizing a maximum mean discrepancy (MMD) based class-wise Fisher discriminant across domains, this framework jointly optimizes two modules: a transferable feature learning module that reduces the distribution discrepancy between the same classes as well as increasing the distribution discrepancy between different classes across domains by a linear projection, and a robust classifier that exploits both the supervised information in source domain and the unsupervised low-rank property of target domain. In experiments on three DA benchmark datasets, the proposed framework shows the state-of-the-art performance.
Rights: © 2018 IEEE
RMID: 0030090425
DOI: 10.1109/TCSVT.2018.2842206
Grant ID: http://purl.org/au-research/grants/arc/FT120100969
Appears in Collections:Australian Institute for Machine Learning publications
Computer Science publications

Files in This Item:
There are no files associated with this item.


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.