Cross-domain neural-kernel networks

Siamak Mehrkanoon*

*Corresponding author for this work

Research output: Contribution to journalArticleAcademicpeer-review

Abstract

This paper introduces a novel cross-domain neural-kernel networks architecture for semi-supervised domain adaption problem. The proposed model consists of two stream neural-kernel networks corresponding to the source and target domains which are enriched with a coupling term. Each stream neural-kernel networks follows a combination of neural network layer and an explicit feature map constructed by means of random Fourier features. The introduced coupling term aims at enforcing correlations among the output of the intermediate layers of the two stream networks as well as encouraging the two networks to learn shared representation of the data from both source and target domains. Experimental results are given to illustrate the effectiveness of the proposed approaches on synthetic and real-life datasets. (C) 2019 Elsevier B.V. All rights reserved.

Original languageEnglish
Pages (from-to)474-480
Number of pages7
JournalPattern Recognition Letters
Volume125
DOIs
Publication statusPublished - 1 Jul 2019

Keywords

  • Domain adaptation
  • Neural networks
  • Kernel methods
  • Coupling regularization
  • ADAPTATION

Fingerprint

Dive into the research topics of 'Cross-domain neural-kernel networks'. Together they form a unique fingerprint.

Cite this