Cross-Domain Transfer Hashing for Efficient Cross-Modal Retrieval
IEEE Transactions on Circuits and Systems for Video Technology · 2024-10 · 34 (10) · 9664-9677
DOI: 10.1109/tcsvt.2024.3374791 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Circuits and Systems for Video Technology, 2024-10. Verfasst von Fengling Li und 5 weiteren Autor:innen. Die Arbeit wurde bisher 38-mal zitiert (Crossref) und nennt 63 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Shandong, China, CCF-Baidu Open Fund.
Abstract (Originalsprache)
Unsupervised cross-modal hashing presents significant advantages in heterogeneous modality retrieval, offering label scalability, high retrieval efficiency, and low storage costs. However, the lack of explicit semantic supervision in this process results in a noticeable semantic deficit, impacting retrieval performance. In this paper, we address this challenge with a dual-pronged approach: Cross-Domain Transfer Hashing (CDTH), a lightweight weakly-supervised cross-modal hashing model. Our method leverages a semantically rich auxiliary domain to augment the target unsupervised cross-modal hash learning process. Simultaneously, we design a lightweight target cross-modal hashing network to reduce semantic requirements, lessening the burden of parameter optimization. Within the auxiliary domain, we perform direct semantic transfer with hashing network parameter transfer and indirect correlation semantic transfer by constructing an auxiliary semantic correlation graph with the identified cross-domain semantic consistent samples. In the target domain, we generate pseudo-labels using CLIP and establish a target weak semantic correlation graph. These two graphs collaborate to bolster the target cross-modal hashing training process. Extensive experiments on three publicly available datasets affirm the superiority of our approach in both retrieval accuracy and training efficiency. The source code for our method is accessible at: https://github.com/WangBowen7/CDTH.
Förderung
- National Natural Science Foundation of China
- Natural Science Foundation of Shandong, China
- CCF-Baidu Open Fund
Zitieren
APA
Li, F., Wang, B., Zhu, L., Li, J., Zhang, Z., & Chang, X. (2024). Cross-Domain Transfer Hashing for Efficient Cross-Modal Retrieval. IEEE Transactions on Circuits and Systems for Video Technology, 34(10), 9664-9677. https://doi.org/10.1109/tcsvt.2024.3374791
Vancouver
Li F, Wang B, Zhu L, Li J, Zhang Z, Chang X. Cross-Domain Transfer Hashing for Efficient Cross-Modal Retrieval. IEEE Transactions on Circuits and Systems for Video Technology. 2024;34(10):9664-9677. doi:10.1109/tcsvt.2024.3374791
BibTeX
@article{Li2024,
author = {Li, Fengling and Wang, Bowen and Zhu, Lei and Li, Jingjing and Zhang, Zheng and Chang, Xiaojun},
title = {Cross-Domain Transfer Hashing for Efficient Cross-Modal Retrieval},
journal = {IEEE Transactions on Circuits and Systems for Video Technology},
year = {2024},
volume = {34},
number = {10},
pages = {9664--9677},
doi = {10.1109/tcsvt.2024.3374791}
}
EUVIMED