Skip to main navigation Skip to search Skip to main content

Hierarchical hashing for image retrieval

  • Cheng Yan*
  • , Xiao Bai
  • , Jun Zhou
  • , Yun Liu
  • *Corresponding author for this work
  • Beihang University
  • Griffith University Queensland

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

Abstract

Hashing has been widely used in large-scale vision problems thanks to its efficiency in both storage and speed. The quality of hashing can be boosted when supervised information is used to learn hash functions. On large-scale hierarchical datasets, hierarchical semantic information reflects the relationship between classes and their children, which however has been ignored by most supervised hashing methods. In this paper, we propose a hierarchical hashing method for image retrieval. This method models and fuses both hierarchical semantic level relationship through taxonomy structure of dataset and feature level relationship of images into an integrated learning objective, then an optimization scheme is developed to solve the learning problem. Experiments are performed on two large-scale datasets: ImageNet ILSVRC 2010 and Animals with Attributes (AWA) dataset. Besides standard evaluation criteria, we also developed hierarchical evaluation criteria for image retrieval and classification tasks. The results show that the proposed method improves the accuracy of supervised hashing in both types of criteria.

Original languageEnglish
Title of host publicationComputer Vision - 2nd CCF Chinese Conference, CCCV 2017, Proceedings
EditorsLiang Wang, Xiang Bai, Jinfeng Yang, Qingshan Liu, Deyu Meng, Qinghua Hu, Ming-Ming Cheng
PublisherSpringer Verlag
Pages111-125
Number of pages15
ISBN (Print)9789811073014
DOIs
StatePublished - 2017
Event2nd Chinese Conference on Computer Vision, CCCV 2017 - Tianjin, China
Duration: 11 Oct 201714 Oct 2017

Publication series

NameCommunications in Computer and Information Science
Volume772
ISSN (Print)1865-0929

Conference

Conference2nd Chinese Conference on Computer Vision, CCCV 2017
Country/TerritoryChina
CityTianjin
Period11/10/1714/10/17

Fingerprint

Dive into the research topics of 'Hierarchical hashing for image retrieval'. Together they form a unique fingerprint.

Cite this