Re-weighted Adversarial Adaptation Network for Unsupervised Domain Adaptation

Qingchao Chen (), Yang Liu (), Zhaowen Wang (), Ian Wassell () and Kevin Chetty ()
Additional contact information
Qingchao Chen: University of Oxford
Yang Liu: University of Oxford
Zhaowen Wang: Adobe Research
Ian Wassell: University of Cambridge
Kevin Chetty: University College London

Chapter Chapter 5 in Domain Adaptation in Computer Vision with Deep Learning, 2020, pp 75-94 from Springer

Abstract: Abstract The development of deep networks has enabled state-of-the-art performance to be achieved in many application domains at the cost of a large amount of domain-specific annotations. Unsupervised Domain Adaptation (UDA), however, aims to transfer domain knowledge from existing well-defined tasks to new ones where labels are unavailable. Real-world domain discrepancies from different data modalities are caused by complex and uncontrollable factors, which motivates the desire to match the feature distributions when the discrepancies are disparate. In this chapter, we propose the Re-weighted Adversarial Adaptation Network (RAAN) that is composed of two procedures: one to reduce the feature distribution divergence and the other to adapt the classifier when domain discrepancies are disparate. Specifically, to alleviate the need for common supports in matching the feature distribution, we choose to minimize optimal transport (OT) based Earth-Mover (EM) distance and reformulate it as an adversarial training scheme. Utilizing this, RAAN can be trained in an end-to-end and adversarial manner. To adapt the classifier, we propose to match the label distribution by learning the cross-domain label distribution ratios and embed it into the adversarial training. Finally, RAAN was shown to outperform other various methods by a large margin when the domain shifts and discrepancies are disparate.

Keywords: Domain adaptation; Adversarial domain adaptation; Optimal transport; Earth mover distance (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_5

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

DOI: 10.1007/978-3-030-45529-3_5

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 ().