TLR: transfer latent representation for unsupervised domain adaptation

Pan Xiao, Bo Du*, Jia Wu, Lefei Zhang, Ruimin Hu, Xuelong Li

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference proceeding contributionpeer-review

7 Citations (Scopus)

Abstract

Domain adaptation refers to the process of learning prediction models in a target domain by making use of data from a source domain. Many classic methods solve the domain adaptation problem by establishing a common latent space, which may cause the loss of many important properties across both domains. In this manuscript, we develop a novel method, transfer latent representation (TLR), to learn a better latent space. Specifically, we design an objective function based on a simple linear autoencoder to derive the latent representations of both domains. The encoder in the autoencoder aims to project the data of both domains into a robust latent space. Besides, the decoder imposes an additional constraint to reconstruct the original data, which can preserve the common properties of both domains and reduce the noise that causes domain shift. Experiments on cross-domain tasks demonstrate the advantages of TLR over competing methods.

Original languageEnglish
Title of host publication2018 IEEE International Conference on Multimedia and Expo, ICME 2018
Place of PublicationPiscataway, NJ
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Pages1-6
Number of pages6
Volume2018-July
ISBN (Electronic)9781538617373
ISBN (Print)9781538617380
DOIs
Publication statusPublished - 8 Oct 2018
Event2018 IEEE International Conference on Multimedia and Expo, ICME 2018 - San Diego, United States
Duration: 23 Jul 201827 Jul 2018

Conference

Conference2018 IEEE International Conference on Multimedia and Expo, ICME 2018
CountryUnited States
CitySan Diego
Period23/07/1827/07/18

Keywords

  • Domain adaptation
  • linear autoencoder
  • object and action recognition

Fingerprint

Dive into the research topics of 'TLR: transfer latent representation for unsupervised domain adaptation'. Together they form a unique fingerprint.

Cite this