Multi-Source Domain Adaptation by Deep CockTail Networks

Ziliang Chen () and Liang Lin ()
Additional contact information
Ziliang Chen: Sun Yat-sen University
Liang Lin: Sun Yat-sen University

Chapter Chapter 12 in Domain Adaptation in Computer Vision with Deep Learning, 2020, pp 213-233 from Springer

Abstract: Abstract Regular domain adaptation (DA) problems are interested in source examples drawn from a single source distribution, yet they probably come from multiple source domains in reality. Compared with DAs, Multi-Source DA (MSDA) is more challenging to settle: The extra domain shifts exist between source domains and moreover, the multi-source domains may also disagree on their semantic information. In this section, we surveyed Deep CockTail Network (DCTN), a prevalent MSDA algorithm that battles the multi-source-derived domain and semantic shifts. The ideology behind is inspired by making cocktails with multiple kinds of stuff (i.e. sources in our background). In particular, DCTN replays two alternating learning phases: (1) DCTN goes through a multi-way adversarial DA process to minimize the domain discrepancy between the target and each source, in order to obtain domain-invariant features. In this process, each target example would lead to the source-specific perplexity scores, denoting how similar each target feature appears to a feature from one of the source domains. (2) Integrated with the perplexity scores, the multi-source category classifiers categorizes target samples, and the pseudo-labeled target samples and source samples jointly update the category classifiers and the feature extractor. In the empirical studies, DCTNs are evaluated in three domain adaptation benchmarks in vanilla and source-category-shift MSDA scenarios. The results thoroughly evidence the superiority of DCTN framework that resists negative transfers across domains and tasks.

Keywords: Multi-source domain adaptation; Cocktail network; Adversarial learning; Pseudo labels (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_12

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

DOI: 10.1007/978-3-030-45529-3_12

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 ().