Robust Visual Knowledge Transfer via Extreme Learning Machine-Based Domain Adaptation

Lei Zhang, Dapeng Zhang

Research output: Journal article publicationJournal articleAcademic researchpeer-review

101 Citations (Scopus)

Abstract

We address the problem of visual knowledge adaptation by leveraging labeled patterns from source domain and a very limited number of labeled instances in target domain to learn a robust classifier for visual categorization. This paper proposes a new extreme learning machine (ELM)-based cross-domain network learning framework, that is called ELM-based Domain Adaptation (EDA). It allows us to learn a category transformation and an ELM classifier with random projection by minimizing the l21-Norm of the network output weights and the learning error simultaneously. The unlabeled target data, as useful knowledge, is also integrated as a fidelity term to guarantee the stability during cross-domain learning. It minimizes the matching error between the learned classifier and a base classifier, such that many existing classifiers can be readily incorporated as the base classifiers. The network output weights cannot only be analytically determined, but also transferrable. In addition, a manifold regularization with Laplacian graph is incorporated, such that it is beneficial to semisupervised learning. Extensively, we also propose a model of multiple views, referred as MvEDA. Experiments on benchmark visual datasets for video event recognition and object recognition demonstrate that our EDA methods outperform the existing cross-domain learning methods.
Original languageEnglish
Article number7539280
Pages (from-to)4959-4973
Number of pages15
JournalIEEE Transactions on Image Processing
Volume25
Issue number10
DOIs
Publication statusPublished - 1 Oct 2016

Keywords

  • cross-domain learning
  • Domain adaptation
  • Extreme learning machine
  • knowledge adaptation

ASJC Scopus subject areas

  • Software
  • Computer Graphics and Computer-Aided Design

Cite this