1. Effective Visual Domain Adaptation via Generative Adversarial Distribution Matching
- Author
-
Kai Zhang, Qi Kang, Abdullah Abusorrah, MengChu Zhou, and Siya Yao
- Subjects
Matching (statistics) ,Artificial neural network ,Contextual image classification ,Computer Networks and Communications ,Computer science ,business.industry ,02 engineering and technology ,Machine learning ,computer.software_genre ,Field (computer science) ,Computer Science Applications ,Visualization ,Artificial Intelligence ,0202 electrical engineering, electronic engineering, information engineering ,020201 artificial intelligence & image processing ,Artificial intelligence ,Adaptation (computer science) ,business ,computer ,Software - 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.
- Published
- 2021