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...
Saved in:
| Main Authors: | , , , |
|---|---|
| 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 |