Domain adaptation algorithms that handle shifts in the distribution between training and testing data are receiving much attention in computer vision. Recently, a Grassmann manifold-based domain adaptation algorithm that models the domain shift using intermediate subspaces along the geodesic connecting the source and target domains was presented in . We build upon this work and propose replacing the step of concatenating feature projections on a very few sampled inter- mediate subspaces by directly integrating the distance between feature projections along the geodesic. The proposed approach considers all the intermediate sub- spaces along the geodesic. Thus, it is a more principled way of quantifying the cross-domain distance. We present the results of experiments on two standard datasets and show that the proposed algorithm yields favorable performance over previous approaches.
Proceedings Title: Proceedings of the International Conference on Pattern Recognition
Conference Dates: November 11-15, 2012
Conference Location: Tuskuba Science City, -1
Conference Title: International Conference on Pattern Recognition
Pub Type: Conferences