Enhanced Cross-Modal Hashing via Hybrid Distillation and Structural Refinement
IEEE Transactions on Image Processing · 2025 · 34 · 7138-7151
DOI: 10.1109/tip.2025.3613942 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Image Processing, 2025. Verfasst von Xiaoqing Liu und 5 weiteren Autor:innen. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 54 Literaturangaben. Gefördert von: National Key Research and Development Program of China, National Natural Science Foundation of China, Major Key Project of Peng Cheng Laboratory.
Abstract (Originalsprache)
Since cross-modal hashing requires minimal storage and computation, it is becoming increasingly popular with the exponential growth of multimedia content on the internet. However, the lack of accurate supervisory data has curtailed the effectiveness of unsupervised hashing techniques. Conversely, supervised hashing strategies necessitate considerable human and financial resources for data annotation. To address this limitation, we propose a novel semi-supervised cross-modal hashing method called Enhanced Cross-Modal Hashing via Hybrid Distillation and Structural Refinement (HDSR). Specifically, we first learn the features of inter-modal and inter-instance similarity relationships through pointwise semantic alignment and listwise similarity partial order learning, respectively, to extract refined structural representations from partially labeled data. Secondly, by fusing inter-modal similarity to construct higher-order affinity matrices, we precisely delineate the semantic correlation information across cross-modal data, facilitating stable self-supervised training of unlabeled data through the application of momentum fusion strategies. Finally, the refined structural representation of labeled data is transferred into unlabeled branches through hybrid distillation, enhancing the performance of cross-modal hash learning by generating compact and accurate hash codes. The proposed HDSR is compared with several state-of-the-art deep cross-modal hashing methods on three widely used benchmark databases, and the experimental results verify its efficiency and superiority.
Förderung
- National Key Research and Development Program of China
- National Natural Science Foundation of China
- Major Key Project of Peng Cheng Laboratory
- Guangzhou Science and Technology Plan Project
- Basic and Applied Basic Research Foundation of Guangdong Province
Zitieren
APA
Liu, X., Yu, Z., Yang, K., Yu, J., Zeng, H., & Philip Chen, C. L. (2025). Enhanced Cross-Modal Hashing via Hybrid Distillation and Structural Refinement. IEEE Transactions on Image Processing, 34, 7138-7151. https://doi.org/10.1109/tip.2025.3613942
Vancouver
Liu X, Yu Z, Yang K, Yu J, Zeng H, Philip Chen CL. Enhanced Cross-Modal Hashing via Hybrid Distillation and Structural Refinement. IEEE Transactions on Image Processing. 2025;34:7138-7151. doi:10.1109/tip.2025.3613942
BibTeX
@article{Liu2025,
author = {Liu, Xiaoqing and Yu, Zhiwen and Yang, Kaixiang and Yu, Jun and Zeng, Huanqiang and Philip Chen, C L},
title = {Enhanced Cross-Modal Hashing via Hybrid Distillation and Structural Refinement},
journal = {IEEE Transactions on Image Processing},
year = {2025},
volume = {34},
pages = {7138--7151},
doi = {10.1109/tip.2025.3613942}
}
EUVIMED