Domain neural adaptation

Sentao Chen, Zijie Hong, Mehrtash Harandi, Xiaowei Yang

Research output: Contribution to journalArticleResearchpeer-review

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
Number of pages12
JournalIEEE Transactions on Neural Networks and Learning Systems
DOIs
Publication statusAccepted/In press - 8 Mar 2022

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