Advertisement

Geodesic Flow Kernel and Landmarks: Kernel Methods for Unsupervised Domain Adaptation

  • Boqing Gong
  • Kristen Grauman
  • Fei Sha
Chapter
Part of the Advances in Computer Vision and Pattern Recognition book series (ACVPR)

Abstract

Domain Adaptation (DA) aims to correct the mismatch in statistical properties between the source domain on which a classifier is trained and the target domain to which the classifier is to be applied. In this chapter, we address the challenging scenario of unsupervised domain adaptation, where the target domain does not provide any annotated data to assist in adapting the classifier. Our strategy is to learn robust features which are resilient to the mismatch across domains allowing to construct classifiers that will perform well on the target domain. To this end, we propose novel kernel learning approaches to inferring such features for adaptation. Concretely, we explore two closely related directions. On one hand, we propose unsupervised learning of a Geodesic Flow Kernel (GFK) which summarizes the inner products in an infinite sequence of feature subspaces that smoothly interpolate between the source and target domains. On the other hand, we propose supervised learning of a kernel that discriminatively combines multiple base GFKs to model the source and the target domains at fine-grained granularities. In particular, each base kernel pivots on a different set of landmarks—the most useful data instances that reveal the similarity between the source and target domains, thus bridging them to achieve adaptation. The proposed approaches are computationally convenient and capable of learning features/kernels and classifiers discriminatively without the need of labeled target data. We show through extensive empirical studies, using standard benchmark object recognition datasets, that our approaches outperform a variety of competing methods.

Notes

Acknowledgements

This work is partially supported by DARPA D11-AP00278 and NSF IIS-1065243 (B. G. and F. S.), and ONR ATL #N00014-11-1-0105 (K. G.). The Flickr images in Fig. 3.1 are under a CC Attribution 2.0 Generic license, courtesy of berzowska, IvanWalsh.com, warrantedarrest, HerryLawford, yuichi.sakuraba, zimaowuyu, GrahamAndDairne, Bernt Rostad, Keith Roper, flavorrelish, and deflam.

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  1. 1.University of Central FloridaOrlandoUSA
  2. 2.University of Texas at AustinAustinUSA
  3. 3.University of Southern CaliforniaLos AngelesUSA

Personalised recommendations