TY - JOUR
T1 - Enhanced Subspace Distribution Matching for Fast Visual Domain Adaptation
AU - Kang, Qi
AU - Yao, Siya
AU - Zhou, Mengchu
AU - Zhang, Kai
AU - Abusorrah, Abdullah
N1 - Funding Information:
Manuscript received April 8, 2020; accepted May 31, 2020. Date of publication June 25, 2020; date of current version August 6, 2020. This work was supported in part by the National Natural Science Foundation of China under Grant 51775385 and Grant 61703279, in part by the Strategy Research Project of Artificial Intelligence Algorithms of Ministry of Education of China under Grant 000011, in part by the Fundamental Research Funds for the Central Universities, and in part by the Deanship of Scientific Research (DSR) at King Abdulaziz University, Jeddah, under Grant RG-21-135-38. This article was presented at the IEEE 15th International Conference on Networking, Sensing and Control, Zhuhai, China. (Corresponding authors: Qi Kang; MengChu Zhou.) Qi Kang, Siya Yao, and Kai Zhang are with the Department of Control Science and Engineering, Tongji University, Shanghai 201804, China, and also with the Shanghai Institute of Intelligent Science and Technology, Tongji University, Shanghai 200092, China (e-mail: qkang@tongji.edu.cn; yaosiya@tongji. edu.cn; 875199448@qq.com).
Publisher Copyright:
© 2014 IEEE.
PY - 2020/8
Y1 - 2020/8
N2 - In computer vision, when labeled images of the target domain are highly insufficient, it is challenging to build an accurate classifier. Domain adaptation stands for an effective solution to address it by utilizing available and related source domain which has sufficient labeled images, even when there is a substantial difference in properties and distributions of these two domains. Yet, most prior approaches merely reduce subspace conditional or marginal distribution differences between domains but entirely ignoring label dependence (LD) information of source data in subspace. This article proposes a novel approach of domain adaptation, called enhanced subspace distribution matching (ESDM), which makes good use of label information to enhance the distribution matching between the source and target domains in a shared subspace. It reduces both conditional and marginal distributions in a shared subspace during a procedure of kernel principal dimensionality reduction and also preserves source data LD information to the maximum extent, thereby significantly improving cross domain subspace distribution matching. We also provide a learning algorithm with highly affordable computation, which solves the ESDM optimization problem without using time-consuming iterations. Results confirm that it can well outperform several recent domain adaptation methods on image classification tasks in terms of classification accuracy and running time. The results can be used in social cognition, person reidentification, and human-machine interactions.
AB - In computer vision, when labeled images of the target domain are highly insufficient, it is challenging to build an accurate classifier. Domain adaptation stands for an effective solution to address it by utilizing available and related source domain which has sufficient labeled images, even when there is a substantial difference in properties and distributions of these two domains. Yet, most prior approaches merely reduce subspace conditional or marginal distribution differences between domains but entirely ignoring label dependence (LD) information of source data in subspace. This article proposes a novel approach of domain adaptation, called enhanced subspace distribution matching (ESDM), which makes good use of label information to enhance the distribution matching between the source and target domains in a shared subspace. It reduces both conditional and marginal distributions in a shared subspace during a procedure of kernel principal dimensionality reduction and also preserves source data LD information to the maximum extent, thereby significantly improving cross domain subspace distribution matching. We also provide a learning algorithm with highly affordable computation, which solves the ESDM optimization problem without using time-consuming iterations. Results confirm that it can well outperform several recent domain adaptation methods on image classification tasks in terms of classification accuracy and running time. The results can be used in social cognition, person reidentification, and human-machine interactions.
KW - Distribution matching
KW - domain adaptation
KW - image classification
KW - social intelligence and cognition
KW - visual domain adaptation
UR - http://www.scopus.com/inward/record.url?scp=85087506166&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85087506166&partnerID=8YFLogxK
U2 - 10.1109/TCSS.2020.3001517
DO - 10.1109/TCSS.2020.3001517
M3 - Article
AN - SCOPUS:85087506166
SN - 2329-924X
VL - 7
SP - 1047
EP - 1057
JO - IEEE Transactions on Computational Social Systems
JF - IEEE Transactions on Computational Social Systems
IS - 4
M1 - 9126270
ER -