Unsupervised Domain Adaptation Classification Model Based on Generative Adversarial Network

被引：0

作者：

Wang G.-G. ^{[1
]}

Guo T. ^{[1
]}

Yu Y. ^{[1
]}

Su H. ^{[1
]}

机构：

[1] Department of Computer Science, Sichuan Normal University, Chengdu, 610101, Sichuan

来源：

Guo, Tao (tguo@sicnu.edu.cn) | 1600年 / Chinese Institute of Electronics卷 / 48期

关键词：

Domain adaptation learning; Generate-to-adapt model; Generative adversarial network; MK-MMD; Transfer learning; Unsupervised learning;

D O I：

10.3969/j.issn.0372-2112.2020.06.021

中图分类号：

学科分类号：

摘要：

Generate-to-adapt model has used generative adversarial network to implement model structure and has made a breakthrough in domain adaptation learning. However, some of its network structures lack information interaction, and the ability to use only adversarial learning is not sufficient to completely reduce the inter-domain distance. In this paper, an unsupervised domain adaptation classification model based on generative adversarial network (UDAG) is proposed. This model optimizes inter-domain differences and makes full use of the information between unsupervised confrontation training and supervised classification training to learn the shared features between the source and target domain distribution. The experimental results under four domain adaptation conditions show that the UDAG model learns better shared feature embedding and implements domain adaptive classification, and the classification accuracy is significantly improved. © 2020, Chinese Institute of Electronics. All right reserved.

引用

页码：1190 / 1197

页数：7

共 23 条

[1] WANG X, GUPTA A., Unsupervised learning of visual representations using videos, Proceedings of the IEEE International Conference on Computer Vision, pp. 2794-2802, (2015)
[2] MAHJOURIAN R, WICKE M, ANGELOVA A., Unsupervised learning of depth and ego-motion from monocular video using 3D geometric constraints, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5667-5675, (2018)
[3] LIU Jian-Wei, SUN Zheng-Kang, Et al., Review and research development on domain adaptation learning, Acta Automatica Sinica, 40, 8, pp. 1576-1600, (2014)
[4] PAN S J, YANG Q., A survey on transfer learning, IEEE Transactions on Knowledge and Data Engineering, 22, 10, pp. 1345-1359, (2010)
[5] ROZANTSEV A, SALZMANN M, FUA P., Beyond sharing weights for deep domain adaptation, IEEE Transactions on Pattern Analysis and Machine Intelligence, 41, 4, pp. 801-814, (2018)
[6] GANIN Y, LEMPITSKY V., Unsupervised domain adaptation by backpropagation
[7] GHIFARY M, KLEIJN W B, ZHANG M, Et al., Deep reconstruction-classification networks for unsupervised domain adaptation, European Conference on Computer Vision, pp. 597-613, (2016)
[8] TZENG E, HOFFMAN J, ZHANG N, Et al., Deep domain confusion: Maximizing for domain invariance
[9] TZENG E, HOFFMAN J, SAENKO K, Et al., Adversarial discriminative domain adaptation, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7167-7176, (2017)
[10] GOODFELLOW I, POUGET-ABADIE J, MIRZA M, Et al., Generative adversarial nets, Advances in Neural Information Processing Systems, pp. 2672-2680, (2014)

← 1 2 3 →