Joint Geometrical and Statistical Alignment for Visual Domain Adaptation

Jing Zhang, Wanqing Li, Philip Ogunbona; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, pp. 1859-1867

Abstract


This paper presents a novel unsupervised domain adaptation method for cross-domain visual recognition. We propose a unified framework that reduces the shift between domains both statistically and geometrically, referred to as Joint Geometrical and Statistical Alignment (JGSA). Specifically, we learn two coupled projections that project the source domain and target domain data into low-dimensional subspaces where the geometrical shift and distribution shift are reduced simultaneously. The objective function can be solved efficiently in a closed form. Extensive experiments have verified that the proposed method significantly outperforms several state-of-the-art domain adaptation methods on a synthetic dataset and three different real world cross-domain visual recognition tasks.

Related Material


[pdf] [arXiv] [poster]
[bibtex]
@InProceedings{Zhang_2017_CVPR,
author = {Zhang, Jing and Li, Wanqing and Ogunbona, Philip},
title = {Joint Geometrical and Statistical Alignment for Visual Domain Adaptation},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {July},
year = {2017}
}