Bidirectional-Feature-Learning-Based Adversarial Domain Adaptation with Generative Network

Author:

Han Chansu1ORCID,Choo Hyunseung2,Jeong Jongpil3ORCID

Affiliation:

1. Department of Electrical and Computer Engineering, Sungkyunkwan University, Suwon-si 16419, Republic of Korea

2. Department of AI System Engineering, Sungkyunkwan University, Suwon-si 16419, Republic of Korea

3. Department of Smart Factory Convergence, Sungkyunkwan University, Suwon-si 16419, Republic of Korea

Abstract

Studying domain adaptation is a recent research trend. Generally, many generative models that researchers have studied perform well on training data from a specific domain. However, their ability to be generalized to other domains might be limited. Therefore, a growing body of research has utilized domain adaptation techniques to address the problem of generative models being vulnerable to input from other domains. In this paper, we focused on generative models and representation learning. Generative models have received a lot of attention for their ability to generate various types of data such as images, music, and text. In particular, studies utilizing generative adversarial neural networks (GANs) and autoencoder structures have received a lot of attention. In this paper, we solved the domain adaptation problem by reconstructing real image data using an autoencoder structure. In particular, reconstructed image data, considered a type of noisy image data, are used as input data. How to reconstruct data by extracting features and selectively transforming them in order to reduce differences in characteristics between domains entails representative learning. Considering these research trends, this paper proposed a novel methodology combining bidirectional feature learning and generative networks to innovatively approach the domain adaptation problem. It could improve the adaptation ability by accurately simulating the real data distribution. The experimental results show that the proposed model outperforms the traditional DANN and ADDA. This demonstrates that combining bidirectional feature learning and generative networks is an effective solution in the field of domain adaptation. These results break new ground in the field of domain adaptation. They are expected to provide great inspiration for future research and applications. Finally, through various experiments and evaluations, we verify that the proposed approach outperforms the existing works. We conducted experiments for representative generative models and domain adaptation techniques and found that the proposed approach was effective in improving data and domain robustness. We hope to contribute to the development of domain-adaptive models that are robust to the domain.

Funder

SungKyunKwan University

BK21 FOUR

Ministry of Education

National Research Foundation of Korea

Publisher

MDPI AG

Subject

Fluid Flow and Transfer Processes,Computer Science Applications,Process Chemistry and Technology,General Engineering,Instrumentation,General Materials Science

Reference32 articles.

1. Domain-adversarial training of neural networks;Ganin;J. Mach. Learn. Res.,2016

2. Ganin, Y., and Lempitsky, V. (2015, January 6–11). Unsupervised domain adaptation by backpropagation. Proceedings of the 32nd International Conference on International Conference on Machine Learning-ICML’15, Lille, France.

3. Wang, J., Chen, Y., Hao, S., Feng, W., and Shen, Z. (2017, January 18–21). Balanced Distribution Adaptation for Transfer Learning. Proceedings of the 2017 IEEE International Conference on Data Mining (ICDM), New Orleans, LA, USA.

4. Tzeng, E., Hoffman, J., Zhang, N., Saenko, K., and Darrell, T. (2014). Deep Domain Confusion: Maximizing for Domain Invariance. arXiv.

5. Ma, S., Gao, S.-H., and Gao, Y. (2021, January 20–25). Baochang Zhang End-to-End Label-Constraint Adaptation for Adversarial Domain Alignment. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA.

Cited by 1 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3