Heterogeneous Domain Adaptation by Information Capturing and Distribution Matching

Hanrui Wu*, Hong Zhu, Yuguang Yan, Jiaju Wu, Yifan Zhang, Michael K. Ng

*Corresponding author for this work

Research output: Contribution to journalJournal articlepeer-review

21 Citations (Scopus)

Abstract

Heterogeneous domain adaptation (HDA) is a challenging problem because of the different feature representations in the source and target domains. Most HDA methods search for mapping matrices from the source and target domains to discover latent features for learning. However, these methods barely consider the reconstruction error to measure the information loss during the mapping procedure. In this paper, we propose to jointly capture the information and match the source and target domain distributions in the latent feature space. In the learning model, we propose to minimize the reconstruction loss between the original and reconstructed representations to preserve information during transformation and reduce the Maximum Mean Discrepancy between the source and target domains to align their distributions. The resulting minimization problem involves two projection variables with orthogonal constraints that can be solved by the generalized gradient flow method, which can preserve orthogonal constraints in the computational procedure. We conduct extensive experiments on several image classification datasets to demonstrate that the effectiveness and efficiency of the proposed method are better than those of state-of-the-art HDA methods.

Original languageEnglish
Pages (from-to)6364-6376
Number of pages13
JournalIEEE Transactions on Image Processing
Volume30
DOIs
Publication statusPublished - 8 Jul 2021

Scopus Subject Areas

  • Software
  • Computer Graphics and Computer-Aided Design

User-Defined Keywords

  • domain adaptation
  • generalized gradient flow
  • Heterogeneous domain adaptation
  • transfer learning

Fingerprint

Dive into the research topics of 'Heterogeneous Domain Adaptation by Information Capturing and Distribution Matching'. Together they form a unique fingerprint.

Cite this