Skip to main content
placeholder image

Joint geometrical and statistical alignment for visual domain adaptation

Conference Paper


Abstract


  • © 2017 IEEE. 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 lowdimensional 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.

Publication Date


  • 2017

Citation


  • Zhang, J., Li, W. & Ogunbona, P. (2017). Joint geometrical and statistical alignment for visual domain adaptation. 30th IEEE Conference on Computer Vision and Pattern Recognitio, (CVPR 2017) (pp. 5150-5158). United States: IEEE.

Scopus Eid


  • 2-s2.0-85044304033

Start Page


  • 5150

End Page


  • 5158

Place Of Publication


  • United States

Abstract


  • © 2017 IEEE. 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 lowdimensional 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.

Publication Date


  • 2017

Citation


  • Zhang, J., Li, W. & Ogunbona, P. (2017). Joint geometrical and statistical alignment for visual domain adaptation. 30th IEEE Conference on Computer Vision and Pattern Recognitio, (CVPR 2017) (pp. 5150-5158). United States: IEEE.

Scopus Eid


  • 2-s2.0-85044304033

Start Page


  • 5150

End Page


  • 5158

Place Of Publication


  • United States