Domain neural adaptation

Sentao Chen, Zijie Hong, Mehrtash Harandi, Xiaowei Yang

Research output: Contribution to journalArticleResearchpeer-review

8 Citations (Scopus)

Abstract

Domain adaptation is concerned with the problem of generalizing a classification model to a target domain with little or no labeled data, by leveraging the abundant labeled data from a related source domain. The source and target domains possess different joint probability distributions, making it challenging for model generalization. In this article, we introduce domain neural adaptation (DNA): an approach that exploits nonlinear deep neural network to 1) match the source and target joint distributions in the network activation space and 2) learn the classifier in an end-to-end manner. Specifically, we employ the relative chi-square divergence to compare the two joint distributions, and show that the divergence can be estimated via seeking the maximal value of a quadratic functional over the reproducing kernel hilbert space. The analytic solution to this maximization problem enables us to explicitly express the divergence estimate as a function of the neural network mapping. We optimize the network parameters to minimize the estimated joint distribution divergence and the classification loss, yielding a classification model that generalizes well to the target domain. Empirical results on several visual datasets demonstrate that our solution is statistically better than its competitors.

Original languageEnglish
Pages (from-to)8630-8641
Number of pages12
JournalIEEE Transactions on Neural Networks and Learning Systems
Volume34
Issue number11
DOIs
Publication statusPublished - Nov 2023

Keywords

  • Adaptation models
  • Data models
  • DNA
  • Domain adaptation
  • Hilbert space
  • joint distribution matching
  • Kernel
  • neural network
  • Neural networks
  • Probability distribution
  • relative chi-square (RCS) divergence
  • reproducing kernel hilbert space (RKHS).

Cite this