Attention-Aware Joint Location Constraint Hashing for Multi-Label Image Retrieval

Yingqi ZHANG, Yong FENG*, Jiaxing SHANG, Mingliang ZHOU, Baohua QIANG

*Corresponding author for this work

Research output: Journal PublicationsJournal Article (refereed)peer-review

4 Citations (Scopus)


Learning based hashing has been widely used in approximate nearest neighbor search for image retrieval. However, most of the existing hashing methods are designed to learn only simplex feature similarity while ignored the location similarity among multiple objects, thus cannot work well on multi-label image retrieval tasks. In this paper, we propose a novel supervised hashing method which fusions the two kinds of similarities together. First, we leverage an adjacency matrix to record the relative location relationship among multiple objects. Second, by incorporating matrix discretization difference and image label difference, we re-define the pairwise image similarity in a more meticulous way. Third, to learn more distinguishable hash codes, we leverage an attention sub-network to identify the approximate regions of the objects in an image so that the extracted features can mainly focus on the foreground objects and ignore the background clutter. The loss function in our method consists of a multi-categories classification loss which is used to learn the attention sub-network and a hash loss with a scaled sigmoid function which is used to learn the efficient hash codes. Experiment results show that our proposed method is effective in preserving high-level similarities and outperforms the baseline methods in multi-label image retrieval.

Original languageEnglish
Article number8941049
Pages (from-to)3294-3307
Number of pages14
JournalIEEE Access
Early online date24 Dec 2020
Publication statusPublished - 2020
Externally publishedYes

Bibliographical note

Publisher Copyright:
© 2013 IEEE.


  • Attention sub-network
  • hashing method
  • image retrieval
  • location relationship


Dive into the research topics of 'Attention-Aware Joint Location Constraint Hashing for Multi-Label Image Retrieval'. Together they form a unique fingerprint.

Cite this