Low-resolution image categorization via heterogeneous domain adaptation

Yuan Yao, Xutao Li*, Yunming Ye, Feng Liu, Kwok Po NG, Zhichao Huang, Yu ZHANG

*Corresponding author for this work

Research output: Contribution to journalJournal articlepeer-review

12 Citations (Scopus)


Most of existing image categorizations assume that the given datasets have a good resolution and quality. However, the assumption is often violated in real applications. In this paper, we study the low-resolution (LR) image categorization. By utilizing labeled high-resolution (HR) images as auxiliary information, we formulate the problem as a heterogeneous domain adaptation problem and propose a Discriminative Joint Distribution Adaptation (DJDA) model to solve it. The DJDA model projects both LR and HR images into an intermediate subspace with a well-designed objective function, where the distance between classes is expected to be enlarged and the distribution divergence to be reduced. As a result, the discriminative knowledge for HR images can be transferred effectively to LR images. Experimental results demonstrate the proposed DJDA method produces significantly superior categorization accuracies against state-of-the-art competitors.

Original languageEnglish
Pages (from-to)656-665
Number of pages10
JournalKnowledge-Based Systems
Publication statusPublished - 1 Jan 2019

Scopus Subject Areas

  • Management Information Systems
  • Software
  • Information Systems and Management
  • Artificial Intelligence

User-Defined Keywords

  • Heterogeneous domain adaptation
  • Low-resolution image categorization
  • Subspace learning


Dive into the research topics of 'Low-resolution image categorization via heterogeneous domain adaptation'. Together they form a unique fingerprint.

Cite this