SOFT RANKING THRESHOLD LOSSES FOR IMAGE RETRIEVAL

Chiao An Yang, Zhixiang Wang, Yen Yu Lin, Yung Yu Chuang

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

Abstract

This paper proposes a novel loss, soft ranking threshold loss, for driving deep networks to learn better representations for image retrieval. Instead of working in the metric space, our loss works in the rank space which has a more uniform distribution and explicit scale and bounds. Our loss reduces the ranks of the distances between anchor-positive pairs below the threshold while increasing the ones between anchor-negative pairs above the threshold. In addition to the basic form, two extensions are proposed for improving the effectiveness: hard thresholds and ranking margin. Experiments show that the proposed loss outperforms the state-of-the-art losses on image retrieval applications.

Original languageEnglish
Title of host publication2021 IEEE International Conference on Image Processing, ICIP 2021 - Proceedings
PublisherIEEE Computer Society
Pages1339-1343
Number of pages5
ISBN (Electronic)9781665441155
DOIs
StatePublished - 2021
Event2021 IEEE International Conference on Image Processing, ICIP 2021 - Anchorage, United States
Duration: 19 Sep 202122 Sep 2021

Publication series

NameProceedings - International Conference on Image Processing, ICIP
Volume2021-September
ISSN (Print)1522-4880

Conference

Conference2021 IEEE International Conference on Image Processing, ICIP 2021
Country/TerritoryUnited States
CityAnchorage
Period19/09/2122/09/21

Keywords

  • Deep learning
  • Image and video retrieval

Fingerprint

Dive into the research topics of 'SOFT RANKING THRESHOLD LOSSES FOR IMAGE RETRIEVAL'. Together they form a unique fingerprint.

Cite this