A visual domain adaptation method based on enhanced subspace distribution matching

Kai Zhang, Qi Kang, Xuesong Wang, Mengchu Zhou, Sisi Li

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Scopus citations

Abstract

One of the challenges in computer vision is how to learn an accurate classifier for a new domain by using labeled images from an old domain under the condition that there is no available labeled images in the new domain. Domain adaptation is an outstanding solution that tackles this challenge by employing available source-labeled datasets, even with significant difference in distribution and properties. However, most prior methods only reduce the difference in subspace marginal or conditional distributions across domains while completely ignoring the source data label dependence information in a subspace. In this paper, we put forward a novel domain adaptation approach, referred to as Enhanced Subspace Distribution Matching. Specifically, it aims to jointly match the marginal and conditional distributions in a kernel principal dimensionality reduction procedure while maximizing the source label dependence in a subspace, thus raising the subspace distribution matching degree. Extensive experiments verify that it can significantly outperform several state-of-the-art methods for cross-domain image classification problems.

Original languageEnglish (US)
Title of host publicationICNSC 2018 - 15th IEEE International Conference on Networking, Sensing and Control
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1-6
Number of pages6
ISBN (Electronic)9781538650530
DOIs
StatePublished - May 18 2018
Event15th IEEE International Conference on Networking, Sensing and Control, ICNSC 2018 - Zhuhai, China
Duration: Mar 27 2018Mar 29 2018

Publication series

NameICNSC 2018 - 15th IEEE International Conference on Networking, Sensing and Control

Other

Other15th IEEE International Conference on Networking, Sensing and Control, ICNSC 2018
Country/TerritoryChina
CityZhuhai
Period3/27/183/29/18

All Science Journal Classification (ASJC) codes

  • Instrumentation
  • Artificial Intelligence
  • Computer Networks and Communications
  • Control and Optimization
  • Modeling and Simulation

Keywords

  • distribution matching
  • domain adaptation
  • image classification
  • label dependence

Fingerprint

Dive into the research topics of 'A visual domain adaptation method based on enhanced subspace distribution matching'. Together they form a unique fingerprint.

Cite this