TY - JOUR
T1 - Effective Visual Domain Adaptation via Generative Adversarial Distribution Matching
AU - Kang, Qi
AU - Yao, Siya
AU - Zhou, Mengchu
AU - Zhang, Kai
AU - Abusorrah, Abdullah
N1 - Funding Information:
Manuscript received August 5, 2019; revised February 2, 2020 and June 12, 2020; accepted August 8, 2020. Date of publication September 10, 2020; date of current version September 1, 2021. This work was supported in part by the National Natural Science Foundation of China under Grant 51775385, Grant 61703279, and Grant 71371142; 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 under Grant D-503-135-1441. This article’s early version was presented at the IEEE 16th International Conference on Networking, Sensing and Control, Banff, AB, Canada. (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:
© 2012 IEEE.
PY - 2021/9
Y1 - 2021/9
N2 - In the field of computer vision, without sufficient labeled images, it is challenging to train an accurate model. However, through visual adaptation from source to target domains, a relevant labeled dataset can help solve such problem. Many methods apply adversarial learning to diminish cross-domain distribution difference. They are able to greatly enhance the performance on target classification tasks. Generative adversarial network (GAN) loss is widely used in adversarial adaptation learning methods to reduce an across-domain distribution difference. However, it becomes difficult to decline such distribution difference if generator or discriminator in GAN fails to work as expected and degrades its performance. To solve such cross-domain classification problems, we put forward a novel adaptation framework called generative adversarial distribution matching (GADM). In GADM, we improve the objective function by taking cross-domain discrepancy distance into consideration and further minimize the difference through the competition between a generator and discriminator, thereby greatly decreasing cross-domain distribution difference. Experimental results and comparison with several state-of-the-art methods verify GADM's superiority in image classification across domains.
AB - In the field of computer vision, without sufficient labeled images, it is challenging to train an accurate model. However, through visual adaptation from source to target domains, a relevant labeled dataset can help solve such problem. Many methods apply adversarial learning to diminish cross-domain distribution difference. They are able to greatly enhance the performance on target classification tasks. Generative adversarial network (GAN) loss is widely used in adversarial adaptation learning methods to reduce an across-domain distribution difference. However, it becomes difficult to decline such distribution difference if generator or discriminator in GAN fails to work as expected and degrades its performance. To solve such cross-domain classification problems, we put forward a novel adaptation framework called generative adversarial distribution matching (GADM). In GADM, we improve the objective function by taking cross-domain discrepancy distance into consideration and further minimize the difference through the competition between a generator and discriminator, thereby greatly decreasing cross-domain distribution difference. Experimental results and comparison with several state-of-the-art methods verify GADM's superiority in image classification across domains.
KW - Adversarial learning
KW - distribution matching
KW - generative adversarial networks (GANs)
KW - image classification
KW - visual domain adaptation
UR - http://www.scopus.com/inward/record.url?scp=85091316102&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85091316102&partnerID=8YFLogxK
U2 - 10.1109/TNNLS.2020.3016180
DO - 10.1109/TNNLS.2020.3016180
M3 - Article
C2 - 32915748
AN - SCOPUS:85091316102
SN - 2162-237X
VL - 32
SP - 3919
EP - 3929
JO - IEEE Transactions on Neural Networks and Learning Systems
JF - IEEE Transactions on Neural Networks and Learning Systems
IS - 9
M1 - 9194389
ER -