Feature constrained by pixel: Hierarchical adversarial deep domain adaptation

Rui Shao, Xiangyuan LAN, Pong Chi YUEN

Research output: Chapter in book/report/conference proceedingConference contributionpeer-review

8 Citations (Scopus)

Abstract

In multimedia analysis, one objective of unsupervised visual domain adaptation is to train a classifier that works well on a target domain given labeled source samples and unlabeled target samples. Feature alignment of two domains is the key issue which should be addressed to achieve this objective. Inspired by the recent study of Generative Adversarial Networks (GAN) in domain adaptation, this paper proposes a new model based on Generative Adversarial Network, named Hierarchical Adversarial Deep Network (HADN), which jointly optimizes the feature-level and pixel-level adversarial adaptation within a hierarchical network structure. Specifically, the hierarchical network structure ensures that the knowledge from pixel-level adversarial adaptation can be back propagated to facilitate the feature-level adaptation, which achieves a better feature alignment under the constraint of pixel-level adversarial adaptation. Extensive experiments on various visual recognition tasks show that the proposed method performs favorably against or better than competitive state-of-the-art methods.

Original languageEnglish
Title of host publicationMM 2018 - Proceedings of the 2018 ACM Multimedia Conference
PublisherAssociation for Computing Machinery, Inc
Pages220-228
Number of pages9
ISBN (Electronic)9781450356657
DOIs
Publication statusPublished - 15 Oct 2018
Event26th ACM Multimedia conference, MM 2018 - Seoul, Korea, Republic of
Duration: 22 Oct 201826 Oct 2018

Publication series

NameMM 2018 - Proceedings of the 2018 ACM Multimedia Conference

Conference

Conference26th ACM Multimedia conference, MM 2018
Country/TerritoryKorea, Republic of
CitySeoul
Period22/10/1826/10/18

Scopus Subject Areas

  • Computer Graphics and Computer-Aided Design
  • Human-Computer Interaction

User-Defined Keywords

  • Deep learning
  • Generative Adversarial Network
  • Unsupervised domain adaptation

Fingerprint

Dive into the research topics of 'Feature constrained by pixel: Hierarchical adversarial deep domain adaptation'. Together they form a unique fingerprint.

Cite this