Affordable Access

deepdyve-link
Publisher Website

Knowledge Exchange between Domain-Adversarial and Private Networks Improves Open Set Image Classification.

Authors
  • Zhou, Haohong
  • Azzam, Mohamed
  • Zhong, Jian
  • Liu, Cheng
  • Wu, Si
  • Wong, Hau-San
Type
Published Article
Journal
IEEE Transactions on Image Processing
Publisher
Institute of Electrical and Electronics Engineers
Publication Date
Jun 17, 2021
Volume
PP
Identifiers
DOI: 10.1109/TIP.2021.3088642
PMID: 34138710
Source
Medline
Language
English
License
Unknown

Abstract

Both target-specific and domain-invariant features can facilitate Open Set Domain Adaptation (OSDA). To exploit these features, we propose a Knowledge Exchange (KnowEx) model which jointly trains two complementary constituent networks: (1) a Domain-Adversarial Network (DAdvNet) learning the domain-invariant representation, through which the supervision in source domain can be exploited to infer the class information of unlabeled target data; (2) a Private Network (PrivNet) exclusive for target domain, which is beneficial for discriminating between instances from known and unknown classes. The two constituent networks exchange training experience in the learning process. Toward this end, we exploit an adversarial perturbation process against DAdvNet to regularize PrivNet. This enhances the complementarity between the two networks. At the same time, we incorporate an adaptation layer into DAdvNet to address the unreliability of the PrivNet's experience. Therefore, DAdvNet and PrivNet are able to mutually reinforce each other during training. We have conducted thorough experiments on multiple standard benchmarks to verify the effectiveness and superiority of KnowEx in OSDA.

Report this publication

Statistics

Seen <100 times