Distribution-aware hierarchical weighting method for deep metric learning

Yinong ZHU, Yong FENG*, Mingliang ZHOU*, Baohua QIANG, Leong Hou U, Jiajie ZHU

*Corresponding author for this work

Research output: Book Chapters | Papers in Conference ProceedingsConference paper (refereed)Researchpeer-review

Abstract

In this paper, we propose distribution-aware hierarchical weighting (DHW) method for deep metric learning. First, we formulate the distributions of different classes according to the form of gaussian curves, and update distributions as the training process. Second, depending on the learnable distribution, we propose a loss function named distribution-aware loss with dynamic mining margins and hierarchical degrees of weights to make full use of samples. The experimental results show that our algorithm outperforms other state-of-the-art methods in terms of retrieval and clustering tasks. Code is available at https://github.com/zhuyinong1/DHW-master.

Original languageEnglish
Title of host publication2021 IEEE International Conference on Acoustics, Speech, and Signal Processing: Proceedings
PublisherIEEE
Pages1770-1774
Number of pages5
Volume2021-June
ISBN (Electronic)9781728176055
DOIs
Publication statusPublished - 2021
Externally publishedYes
Event2021 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2021 - Virtual, Toronto, Canada
Duration: 6 Jun 202111 Jun 2021

Publication series

NameICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISSN (Print)1520-6149

Conference

Conference2021 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2021
Country/TerritoryCanada
CityVirtual, Toronto
Period6/06/2111/06/21

Bibliographical note

Publisher Copyright:
© 2021 IEEE

Keywords

  • Distribution quantification
  • Hierarchical weighting
  • Metric learning
  • Relationship maintenance

Fingerprint

Dive into the research topics of 'Distribution-aware hierarchical weighting method for deep metric learning'. Together they form a unique fingerprint.

Cite this