Joint Geometrical and Statistical Alignment Using Triplet Loss for Deep Domain Adaptation

R. Satya Rajendra Singh, Rakesh Kumar Sanodiya, P. V. Arun

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Although the primitive and deep learning methods have made significant progress, problems can arise if there are large differences or distribution gaps between the training and test images. To overcome this problem, shallow and deep domain adaptation (DA) approaches have been developed. However, none of the existing deep DA approaches reduce the disparity in distribution among domains statistically and geometrically and never attempt to reduce the distance among congruent images and maximize the distance between incongruous images. Therefore, in this paper, we introduce a joint geometrical and statistical alignment using the triplet loss (JGSAT) method for deep domain adaptation. More specifically, the JGSAT reduces domain shift between the domains statistically and geometrically simultaneously by incorporating maximum mean discrepancy (MMD), CORrelation ALignment (CORAL), and triplet loss in a unified framework. Ubiquitous evaluations have affirmed that the suggested method JGSAT remarkably vanquishes cutting-edge shallow and deep domain adaptation techniques on the PIE face recognition dataset.

Original languageEnglish
Title of host publicationResponsible Data Science - Select Proceedings of ICDSE 2021
EditorsJimson Mathew, G. Santhosh Kumar, Deepak Padmanabhan, Joemon M. Jose
PublisherSpringer Science and Business Media Deutschland GmbH
Pages119-130
Number of pages12
ISBN (Print)9789811944529
DOIs
StatePublished - 1 Jan 2022
Externally publishedYes
Event7th International Conference on Data Science and Engineering, ICDSE 2021 - Patna, India
Duration: 17 Dec 202118 Dec 2021

Publication series

NameLecture Notes in Electrical Engineering
Volume940
ISSN (Print)1876-1100
ISSN (Electronic)1876-1119

Conference

Conference7th International Conference on Data Science and Engineering, ICDSE 2021
Country/TerritoryIndia
CityPatna
Period17/12/2118/12/21

Keywords

  • Deep domain adaptation
  • Domain adaptation
  • Transfer learning
  • Triplet Loss

ASJC Scopus subject areas

  • Industrial and Manufacturing Engineering

Fingerprint

Dive into the research topics of 'Joint Geometrical and Statistical Alignment Using Triplet Loss for Deep Domain Adaptation'. Together they form a unique fingerprint.

Cite this