Effective Visual Domain Adaptation via Generative Adversarial Distribution Matching
Document Type
Article
Publication Date
9-1-2021
Abstract
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.
Identifier
85091316102 (Scopus)
Publication Title
IEEE Transactions on Neural Networks and Learning Systems
External Full Text Location
https://doi.org/10.1109/TNNLS.2020.3016180
e-ISSN
21622388
ISSN
2162237X
PubMed ID
32915748
First Page
3919
Last Page
3929
Issue
9
Volume
32
Grant
51775385
Fund Ref
National Natural Science Foundation of China
Recommended Citation
Kang, Qi; Yao, Siya; Zhou, Mengchu; Zhang, Kai; and Abusorrah, Abdullah, "Effective Visual Domain Adaptation via Generative Adversarial Distribution Matching" (2021). Faculty Publications. 3852.
https://digitalcommons.njit.edu/fac_pubs/3852