Please use this identifier to cite or link to this item: http://hdl.handle.net/2440/116113
Citations
Scopus Web of Science® Altmetric
?
?
Type: Journal article
Title: An embarrassingly simple approach to visual domain adaptation
Author: Lu, H.
Shen, C.
Cao, Z.
Xiao, Y.
Van Den Hengel, A.
Citation: IEEE Transactions on Image Processing, 2018; 27(7):3403-3417
Publisher: IEEE
Issue Date: 2018
ISSN: 1057-7149
1941-0042
Statement of
Responsibility: 
Hao Lu, Chunhua Shen, Zhiguo Cao , Yang Xiao , and Anton van den Hengel
Abstract: We show that it is possible to achieve high-quality domain adaptation without explicit adaptation. The nature of the classification problem means that when samples from the same class in different domains are sufficiently close, and samples from differing classes are separated by large enough margins, there is a high probability that each will be classified correctly. Inspired by this, we propose an embarrassingly simple yet effective approach to domain adaptation-only the class mean is used to learn class-specific linear projections. Learning these projections is naturally cast into a linear-discriminant-analysis-like framework, which gives an efficient, closed form solution. Furthermore, to enable to application of this approach to unsupervised learning, an iterative validation strategy is developed to infer target labels. Extensive experiments on cross-domain visual recognition demonstrate that, even with the simplest formulation, our approach outperforms existing non-deep adaptation methods and exhibits classification performance comparable with that of modern deep adaptation methods. An analysis of potential issues effecting the practical application of the method is also described, including robustness, convergence, and the impact of small sample sizes.
Rights: © 2018 IEEE
RMID: 0030085640
DOI: 10.1109/TIP.2018.2819503
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.