Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

6-2015

Abstract

In many real-world applications, we are often facing the problem of cross domain learning, i.e., to borrow the labeled data or transfer the already learnt knowledge from a source domain to a target domain. However, simply applying existing source data or knowledge may even hurt the performance, especially when the data distribution in the source and target domain is quite different, or there are very few labeled data available in the target domain. This paper proposes a novel domain adaptation framework, named Semi-supervised Domain Adaptation with Subspace Learning (SDASL), which jointly explores invariant lowdimensional structures across domains to correct data distribution mismatch and leverages available unlabeled target examples to exploit the underlying intrinsic information in the target domain. Specifically, SDASL conducts the learning by simultaneously minimizing the classification error, preserving the structure within and across domains, and restricting similarity defined on unlabeled target examples. Encouraging results are reported for two challenging domain transfer tasks (including image-to-image and imageto-video transfers) on several standard datasets in the context of both image object recognition and video concept detection.

Discipline

Databases and Information Systems | Graphics and Human Computer Interfaces

Research Areas

Intelligent Systems and Optimization

Publication

Proceedings of the 28th IEEE Conference on Computer Vision and Pattern Recognition: CVPR 2015, Boston, June 7-12

First Page

2142

Last Page

2150

ISBN

9781467369640

Identifier

10.1109/CVPR.2015.7298826

Publisher

IEEE

City or Country

Boston

Download

Share

COinS