Unsupervised Domain Adaptation with Duplex Generative Adversarial Network

Lanqing Hu (), Meina Kan, Shiguang Shan and Xilin Chen
Additional contact information
Lanqing Hu: Institute of Computing Technology, Chinese Academy of Sciences, Key Lab of Intelligent Information Processing of Chinese Academy of Sciences
Meina Kan: Institute of Computing Technology, Chinese Academy of Sciences, Key Lab of Intelligent Information Processing of Chinese Academy of Sciences
Shiguang Shan: Institute of Computing Technology, Chinese Academy of Sciences, Key Lab of Intelligent Information Processing of Chinese Academy of Sciences
Xilin Chen: Institute of Computing Technology, Chinese Academy of Sciences, Key Lab of Intelligent Information Processing of Chinese Academy of Sciences

Chapter Chapter 6 in Domain Adaptation in Computer Vision with Deep Learning, 2020, pp 97-116 from Springer

Abstract: Abstract Unsupervised domain adaptation aims to train a good model for a target domain via transferring knowledge from a related labeled source domain, thus reducing the dependency on huge labeling of target domain samples. Generative adversarial net (GAN) is a newly proposed technique which has shown its capability of alleviating distribution discrepancy. Inspired by GAN, in this work, we propose a novel duplex GAN (DupGAN) which extracts domain invariant and discriminative representation guided by bidirectional domain transformation, formulated as a GAN with duplex discriminators. In addition, each of the duplex discriminators not only judges reality/falsity, but also performs category classification for real images to preserve the category information during domain transformation. As evaluated on the standard benchmarks, i.e., digits datasets and Office-31, our proposed DupGAN outperforms the state-of-the-art methods, indicating its effectiveness on unsupervised domain adaptation.

Keywords: Domain adaptation; Adversarial domain adaptation; Bidirectional domain transformation; Duplex discriminator (search for similar items in EconPapers)
Date: 2020
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:sprchp:978-3-030-45529-3_6

Ordering information: This item can be ordered from
http://www.springer.com/9783030455293

DOI: 10.1007/978-3-030-45529-3_6

Access Statistics for this chapter

More chapters in Springer Books from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().