Deep Class-Guided Hashing for Multi-Label Cross-Modal Retrieval

Deep hashing has gained widespread attention in cross-modal retrieval due to its low cost and efficient retrieval advantages. However, existing cross-modal hashing methods either focus solely on exploring relationships between data points—which inevitably leads to intra-class dispersion—or emphasize...

Full description

Saved in:
Bibliographic Details
Main Authors: Hao Chen, Zhuoyang Zou, Yiqiang Liu, Xinghui Zhu
Format: Article
Language:English
Published: MDPI AG 2025-03-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/15/6/3068
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850089772029050880
author Hao Chen
Zhuoyang Zou
Yiqiang Liu
Xinghui Zhu
author_facet Hao Chen
Zhuoyang Zou
Yiqiang Liu
Xinghui Zhu
author_sort Hao Chen
collection DOAJ
description Deep hashing has gained widespread attention in cross-modal retrieval due to its low cost and efficient retrieval advantages. However, existing cross-modal hashing methods either focus solely on exploring relationships between data points—which inevitably leads to intra-class dispersion—or emphasize the relationships between data points and categories while neglecting the preservation of inter-class structural relationships, resulting in suboptimal hash codes. To address this issue, this paper proposes a Deep Class-Guided Hashing (DCGH) method, which approaches model learning from the category level. It ensures that data of the same category are clustered around the same class center while maintaining the structural relationships between class centers. Extensive comparative experiments conducted on three benchmark datasets demonstrate that the DCGH method achieves comparable or even superior performance compared to existing cross-modal retrieval methods.
format Article
id doaj-art-6a4e496b3e5f4d319bfda4e9b17f1e99
institution DOAJ
issn 2076-3417
language English
publishDate 2025-03-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-6a4e496b3e5f4d319bfda4e9b17f1e992025-08-20T02:42:41ZengMDPI AGApplied Sciences2076-34172025-03-01156306810.3390/app15063068Deep Class-Guided Hashing for Multi-Label Cross-Modal RetrievalHao Chen0Zhuoyang Zou1Yiqiang Liu2Xinghui Zhu3College of Information and Intelligence, Hunan Agricultural University, Changsha 410128, ChinaCollege of Information and Intelligence, Hunan Agricultural University, Changsha 410128, ChinaCollege of Information and Intelligence, Hunan Agricultural University, Changsha 410128, ChinaCollege of Information and Intelligence, Hunan Agricultural University, Changsha 410128, ChinaDeep hashing has gained widespread attention in cross-modal retrieval due to its low cost and efficient retrieval advantages. However, existing cross-modal hashing methods either focus solely on exploring relationships between data points—which inevitably leads to intra-class dispersion—or emphasize the relationships between data points and categories while neglecting the preservation of inter-class structural relationships, resulting in suboptimal hash codes. To address this issue, this paper proposes a Deep Class-Guided Hashing (DCGH) method, which approaches model learning from the category level. It ensures that data of the same category are clustered around the same class center while maintaining the structural relationships between class centers. Extensive comparative experiments conducted on three benchmark datasets demonstrate that the DCGH method achieves comparable or even superior performance compared to existing cross-modal retrieval methods.https://www.mdpi.com/2076-3417/15/6/3068deep hashingintra-class aggregationinter-class structural relationshipssemantic bias
spellingShingle Hao Chen
Zhuoyang Zou
Yiqiang Liu
Xinghui Zhu
Deep Class-Guided Hashing for Multi-Label Cross-Modal Retrieval
Applied Sciences
deep hashing
intra-class aggregation
inter-class structural relationships
semantic bias
title Deep Class-Guided Hashing for Multi-Label Cross-Modal Retrieval
title_full Deep Class-Guided Hashing for Multi-Label Cross-Modal Retrieval
title_fullStr Deep Class-Guided Hashing for Multi-Label Cross-Modal Retrieval
title_full_unstemmed Deep Class-Guided Hashing for Multi-Label Cross-Modal Retrieval
title_short Deep Class-Guided Hashing for Multi-Label Cross-Modal Retrieval
title_sort deep class guided hashing for multi label cross modal retrieval
topic deep hashing
intra-class aggregation
inter-class structural relationships
semantic bias
url https://www.mdpi.com/2076-3417/15/6/3068
work_keys_str_mv AT haochen deepclassguidedhashingformultilabelcrossmodalretrieval
AT zhuoyangzou deepclassguidedhashingformultilabelcrossmodalretrieval
AT yiqiangliu deepclassguidedhashingformultilabelcrossmodalretrieval
AT xinghuizhu deepclassguidedhashingformultilabelcrossmodalretrieval