d-SNE: Domain Adaptation Using Stochastic Neighborhood Embedding

Xiong Zhou (), Xiang Xu (), Ragav Venkatesan (), Gurumurthy Swaminathan () and Orchid Majumder ()
Additional contact information
Xiong Zhou: AWS AI
Xiang Xu: AWS AI
Ragav Venkatesan: AWS AI
Gurumurthy Swaminathan: AWS AI
Orchid Majumder: AWS AI

Chapter Chapter 3 in Domain Adaptation in Computer Vision with Deep Learning, 2020, pp 43-56 from Springer

Abstract: Abstract Training a deep neural network often requires enormous amount of labeled data, while data annotation is usually an expensive and tedious task. Domain adaptation is a popular way to solve this problem by leveraging data source from a different but related domain. In this chapter, we introduce a domain adaptation algorithm (d-SNE) that uses stochastic neighborhood embedding for aligning the source and target data. Extensive experiments demonstrate the efficacy of proposed method compared to conventional domain adaptation approaches.

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_3

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

DOI: 10.1007/978-3-030-45529-3_3

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 ().