An embarrassingly simple approach to visual domain adaptation
Date
2018
Authors
Lu, H.
Shen, C.
Cao, Z.
Xiao, Y.
Van Den Hengel, A.
Editors
Advisors
Journal Title
Journal ISSN
Volume Title
Type:
Journal article
Citation
IEEE Transactions on Image Processing, 2018; 27(7):3403-3417
Statement of Responsibility
Hao Lu, Chunhua Shen, Zhiguo Cao , Yang Xiao , and Anton van den Hengel
Conference Name
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.
School/Discipline
Dissertation Note
Provenance
Description
Access Status
Rights
© 2018 IEEE