Advertisement

Unsupervised Domain Adaptation Based on Subspace Alignment

  • Basura Fernando
  • Rahaf Aljundi
  • Rémi EmonetEmail author
  • Amaury Habrard
  • Marc Sebban
  • Tinne Tuytelaars
Chapter
  • 1.8k Downloads
Part of the Advances in Computer Vision and Pattern Recognition book series (ACVPR)

Abstract

Subspace-based domain adaptation methods have been very successful in the context of image recognition. In this chapter, we discuss methods using Subspace Alignment (SA). They are based on a mapping function which aligns the source subspace with the target one, so as to obtain a domain invariant feature space. The solution of the corresponding optimization problem can be obtained in closed form, leading to a simple to implement and fast algorithm. The only hyperparameter involved corresponds to the dimension of the subspaces. We give two methods, SA and SA-MLE, for setting this variable. SA is a purely linear method. As a nonlinear extension, Landmarks-based Kernelized Subspace Alignment (LSSA) first projects the data nonlinearly based on a set of landmarks, which have been selected so as to reduce the discrepancy between the domains.

Notes

Acknowledgements

The authors gratefully acknowledge support from the FP7 ERC Starting Grant 240530 COGNIMUND, and the ANR projects SOLSTICE (ANR-13-BS02-01) and LIVES (ANR-15-CE23-0026-03).

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  • Basura Fernando
    • 1
  • Rahaf Aljundi
    • 2
  • Rémi Emonet
    • 3
    Email author
  • Amaury Habrard
    • 3
  • Marc Sebban
    • 3
  • Tinne Tuytelaars
    • 2
  1. 1.The ANUCanberraAustralia
  2. 2.KU Leuven, SAT-PSI, IMECLeuvenBelgium
  3. 3.Univ. Lyon, JM-Saint-Etienne, CNRS, Institut D’Optique Graduate School Laboratoire Hubert Curien UMR 5516St-EtienneFrance

Personalised recommendations