Adversarial Transform Networks for Unsupervised Transfer Learning

Guanyu Cai, Yuqin Wang, Lianghua He, Mengchu Zhou

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Transfer learning, especially unsupervised domain adaptation, is a crucial technology for sample-efficient learning. Recently, deep adversarial domain adaptation methods perform remarkably well in various tasks, which introduce a domain classifier to promote domain-invariant representation. However, previous methods either constrain the representative ability with an identical feature extractor for both domains or ignore the relationship between domains with separate extractors. In this paper, we propose a novel adversarial domain adaptation method named Adversarial Transform Network (ATN) to both enhance the representative ability and transfer general information between domains. Residual connections are used to share features in the bottom layers, which deliver transferrable features to boost generalization performance. Moreover, a regularizer is proposed to alleviate a vanishing gradient problem, thus stabilizing the optimization procedure. Extensive experiments are conducted to show that the proposed ATN is comparable with the methods of the state-of-the-art and effectively deals with the vanishing gradient problem.

Original languageEnglish (US)
Title of host publication2020 IEEE International Conference on Networking, Sensing and Control, ICNSC 2020
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781728168531
DOIs
StatePublished - Oct 30 2020
Event2020 IEEE International Conference on Networking, Sensing and Control, ICNSC 2020 - Nanjing, China
Duration: Oct 30 2020Nov 2 2020

Publication series

Name2020 IEEE International Conference on Networking, Sensing and Control, ICNSC 2020

Conference

Conference2020 IEEE International Conference on Networking, Sensing and Control, ICNSC 2020
Country/TerritoryChina
CityNanjing
Period10/30/2011/2/20

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Computer Networks and Communications
  • Statistics, Probability and Uncertainty
  • Control and Optimization
  • Sensory Systems

Keywords

  • Adversarial transform networks
  • gradient vanishing problem
  • transfer learning

Fingerprint

Dive into the research topics of 'Adversarial Transform Networks for Unsupervised Transfer Learning'. Together they form a unique fingerprint.

Cite this