Weighted multi-deep ranking supervised hashing for efficient image retrieval

Jiayong LI, Wing W. Y. NG, Xing TIAN, Sam KWONG, Hui WANG

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

14 Citations (Scopus)

Abstract

Deep hashing has proven to be efficient and effective for large-scale image retrieval due to the strong representation capability of deep networks. Existing deep hashing methods only utilize a single deep hash table. In order to achieve both higher retrieval recall and precision, longer hash codes can be used but at the expense of higher space usage. To address this issue, a novel deep hashing method is proposed in this paper, weighted multi-deep ranking supervised hashing (WMDRH), which employs multiple weighted deep hash tables to improve precision/recall without increasing space usage. The hash table is constructed as an additional layer in a deep network. Hash codes are generated by minimizing the loss function that contains two terms: (1) the ranking pairwise loss and (2) the classification loss. The ranking pairwise loss ensures to generate discriminative hash codes by penalizing more for the (dis)similar image pairs with (small)large Hamming distances. The classification loss guarantees the hash codes to be effective for category prediction. Different hash bits in each individual hash table are treated differently by assigning corresponding weights based on information preservation and bit diversity. Moreover, multiple hash tables are integrated by assigning the appropriate weight to each table according to its mean average precision (MAP) score for image retrieval. Experiments on three widely-used image databases show the proposed method outperforms state-of-the-art hashing methods.
Original languageEnglish
Pages (from-to)883–897
JournalInternational Journal of Machine Learning and Cybernetics
Volume11
Issue number4
Early online date1 Nov 2019
DOIs
Publication statusPublished - Apr 2020
Externally publishedYes

Bibliographical note

This work was supported by National Natural Science Foundation of China under Grants 61876066, 61572201 and 61672443, Guangzhou Science and Technology Plan Project 201804010245, Hong Kong RGC General Research Funds under Grant 9042038 (CityU 11205314) and Grant 9042322 (CityU 11200116), and EU Horizon 2020 Programme (700381, ASGARD).

Keywords

  • Deep hashing
  • Image retrieval
  • Multi-table
  • Ranking loss
  • Weighting

Fingerprint

Dive into the research topics of 'Weighted multi-deep ranking supervised hashing for efficient image retrieval'. Together they form a unique fingerprint.

Cite this