Adversarial auto-encoder for unsupervised deep domain adaptation

Rui Shao, Xiangyuan Lan*

*Corresponding author for this work

Research output: Contribution to journalJournal articlepeer-review

3 Citations (Scopus)

Abstract

Unsupervised visual domain adaptation aims to train a classifier that works well on a target domain given labelled source samples and unlabelled target samples. The key issue in unsupervised visual domain adaptation is how to do the feature alignment between source and target domains. Inspired by the adversarial learning in generative adversarial networks, this study proposes a novel adversarial auto-encoder for unsupervised deep domain adaptation. This method incorporates the auto-encoder with the adversarial learning so that the domain similarity and reconstruction information from the decoder can be exploited to facilitate the adversarial domain adaptation in the encoder. Extensive experiments on various visual recognition tasks show that the proposed method performs favourably against or better than competitive state-of-the-art methods.

Original languageEnglish
Pages (from-to)2772-2777
Number of pages6
JournalIET Image Processing
Volume13
Issue number14
DOIs
Publication statusPublished - 12 Dec 2019

Scopus Subject Areas

  • Software
  • Signal Processing
  • Computer Vision and Pattern Recognition
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Adversarial auto-encoder for unsupervised deep domain adaptation'. Together they form a unique fingerprint.

Cite this