Synthetic-to-Real Domain Adaptation and Refinement

Sergey I. Nikolenko ()
Additional contact information
Sergey I. Nikolenko: Synthesis AI

Chapter Chapter 10 in Synthetic Data for Deep Learning, 2021, pp 235-268 from Springer

Abstract: Abstract Domain adaptation is a set of techniques aimed to make a model trained on one domain of data to work well on a different target domain. In this chapter, we give a survey of domain adaptation approaches that have been used for synthetic-to-real adaptation, that is, methods for making models trained on synthetic data work well on real data, which is almost always the end goal. We distinguish two main approaches. In synthetic-to-real refinement input synthetic data is modified, usually to be made more realistic, and we can actually see the modified data. In model-based domain adaptation, it is the training process or the model structure that changes to ensure domain adaptation, while the data remains as synthetic as it has been. We will discuss neural architectures for both approaches, including many models based on generative adversarial networks.

Date: 2021
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:spochp:978-3-030-75178-4_10

Ordering information: This item can be ordered from
http://www.springer.com/9783030751784

DOI: 10.1007/978-3-030-75178-4_10

Access Statistics for this chapter

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