Dot-Product Based Global and Local Feature Fusion for Image Search

Zechao Hu; Adrian Gheorghe Bors

doi:10.1109/ICIP46576.2022.9897661

Dot-Product Based Global and Local Feature Fusion for Image Search

Zechao Hu, Adrian Gheorghe Bors

Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

Content-based image retrieval (CBIR) consists in searching the most similar images to the query content from a given pool of images or database. Existing works' success relies on taking advantage of both local and global feature information leading to better retrieval performance than when using either of these. Lately, CBIR area has been dominated by the two-stage image retrieval framework which utilizes global features to get initial retrieval results, while using local features for re-ranking in a second stage. In this study, instead of utilizing local and global features separately during two stages, we propose to use a dot-product based local and global (DPLG) feature fusion module leading to a comprehensive global feature descriptor. The proposed fusion module is jointly end-to-end trained within the convolution backbone structure. According to the experimental results, the proposed module achieves new state-of-the-art results on some benchmark datasets. Index Terms-Content based image retrieval, Local and global features, Dot-product attention.

Original language	English
Title of host publication	IEEE International Conference on Image Processing (ICIP)
Place of Publication	Bordeaux, France
Publisher	IEEE
Pages	1911-1915
ISBN (Print)	9781665496209
DOIs	https://doi.org/10.1109/ICIP46576.2022.9897661
Publication status	Published - 18 Oct 2022

Bibliographical note

© 2022 IEEE. This is an author-produced version of the published paper. Uploaded in accordance with the publisher’s self-archiving policy. Further copying may not be permitted; contact the publisher for details

Access to Document

10.1109/ICIP46576.2022.9897661

Dot-Product Based Global and Local Feature Fusion for Image Search
© 2022 IEEE. This is an author-produced version of the published paper. Uploaded in accordance with the publisher’s self-archiving policy. Further copying may not be permitted; contact the publisher for details
Accepted author manuscript, 566 KB

Cite this

@inproceedings{d2319e63bc84408789222814ded6b4a7,

title = "Dot-Product Based Global and Local Feature Fusion for Image Search",

abstract = "Content-based image retrieval (CBIR) consists in searching the most similar images to the query content from a given pool of images or database. Existing works' success relies on taking advantage of both local and global feature information leading to better retrieval performance than when using either of these. Lately, CBIR area has been dominated by the two-stage image retrieval framework which utilizes global features to get initial retrieval results, while using local features for re-ranking in a second stage. In this study, instead of utilizing local and global features separately during two stages, we propose to use a dot-product based local and global (DPLG) feature fusion module leading to a comprehensive global feature descriptor. The proposed fusion module is jointly end-to-end trained within the convolution backbone structure. According to the experimental results, the proposed module achieves new state-of-the-art results on some benchmark datasets. Index Terms-Content based image retrieval, Local and global features, Dot-product attention.",

author = "Zechao Hu and Bors, {Adrian Gheorghe}",

note = "{\textcopyright} 2022 IEEE. This is an author-produced version of the published paper. Uploaded in accordance with the publisher{\textquoteright}s self-archiving policy. Further copying may not be permitted; contact the publisher for details",

year = "2022",

month = oct,

day = "18",

doi = "10.1109/ICIP46576.2022.9897661",

language = "English",

isbn = "9781665496209",

pages = "1911--1915",

booktitle = "IEEE International Conference on Image Processing (ICIP)",

publisher = "IEEE",

address = "United States",

}

TY - GEN

T1 - Dot-Product Based Global and Local Feature Fusion for Image Search

AU - Hu, Zechao

AU - Bors, Adrian Gheorghe

N1 - © 2022 IEEE. This is an author-produced version of the published paper. Uploaded in accordance with the publisher’s self-archiving policy. Further copying may not be permitted; contact the publisher for details

PY - 2022/10/18

Y1 - 2022/10/18

N2 - Content-based image retrieval (CBIR) consists in searching the most similar images to the query content from a given pool of images or database. Existing works' success relies on taking advantage of both local and global feature information leading to better retrieval performance than when using either of these. Lately, CBIR area has been dominated by the two-stage image retrieval framework which utilizes global features to get initial retrieval results, while using local features for re-ranking in a second stage. In this study, instead of utilizing local and global features separately during two stages, we propose to use a dot-product based local and global (DPLG) feature fusion module leading to a comprehensive global feature descriptor. The proposed fusion module is jointly end-to-end trained within the convolution backbone structure. According to the experimental results, the proposed module achieves new state-of-the-art results on some benchmark datasets. Index Terms-Content based image retrieval, Local and global features, Dot-product attention.

AB - Content-based image retrieval (CBIR) consists in searching the most similar images to the query content from a given pool of images or database. Existing works' success relies on taking advantage of both local and global feature information leading to better retrieval performance than when using either of these. Lately, CBIR area has been dominated by the two-stage image retrieval framework which utilizes global features to get initial retrieval results, while using local features for re-ranking in a second stage. In this study, instead of utilizing local and global features separately during two stages, we propose to use a dot-product based local and global (DPLG) feature fusion module leading to a comprehensive global feature descriptor. The proposed fusion module is jointly end-to-end trained within the convolution backbone structure. According to the experimental results, the proposed module achieves new state-of-the-art results on some benchmark datasets. Index Terms-Content based image retrieval, Local and global features, Dot-product attention.

U2 - 10.1109/ICIP46576.2022.9897661

DO - 10.1109/ICIP46576.2022.9897661

M3 - Conference contribution

SN - 9781665496209

SP - 1911

EP - 1915

BT - IEEE International Conference on Image Processing (ICIP)

PB - IEEE

CY - Bordeaux, France

ER -