University of Leicester
Browse
20220513-Major revision v3.docx (7.08 MB)

Discriminative feature mining hashing for Fine-grained image retrieval

Download (7.08 MB)
journal contribution
posted on 2022-08-08, 10:37 authored by W Lang, H Sun, C Xu, N Liu, Huiyu Zhou

With the development of multimedia technology, fine-grained image retrieval has gradually become a new hot topic in computer vision, while its accuracy and speed are limited due to the low discriminative high-dimensional real-valued embedding. To solve this problem, we propose an end-to-end framework named DFMH (Discriminative Feature Mining Hashing), which consists of the DFEM (Discriminative Feature Extracting Module) and SHCM (Semantic Hash Coding Module). Specifically, DFEM explores more discriminative local regions by attention drop and obtains finer local feature expression by attention re-sample. SHCM generates high-quality hash codes by combining the quantization loss and bit balance loss. Validated by extensive experiments and ablation studies, our method consistently outperforms both the state-of-the-art generic retrieval methods as well as fine-grained retrieval methods on three datasets, including CUB Birds, Stanford Dogs and Stanford Cars.

History

Author affiliation

School of Informatics, University of Leicester

Version

  • AM (Accepted Manuscript)

Published in

Journal of Visual Communication and Image Representation

Volume

87

Publisher

Elsevier

issn

1047-3203

Acceptance date

2022-07-16

Copyright date

2022

Available date

2023-07-20

Language

en

Usage metrics

    University of Leicester Publications

    Categories

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC