EUVIMEDEUVIMED entdecken
Crossref

Privacy-Enhanced Prototype-Based Federated Cross-Modal Hashing for Cross-Modal Retrieval

Ruifan Zuo, Chaoqun Zheng, Fengling Li, Lei Zhu, Zheng Zhang

ACM Transactions on Multimedia Computing, Communications, and Applications · 30.09.2024 · 20 (9) · 1-19

DOI: 10.1145/3674507 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Multimedia Computing, Communications, and Applications, online erschienen am 23.09.2024. Verfasst von Ruifan Zuo und 4 weiteren Autor:innen. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 46 Literaturangaben. Gefördert von: Qilu University of Technology (Shandong Academy of Sciences) Science, Program of New Twenty Policies for Universities of Jinan, Program of Innovation Improvement for Small and Medium-sized Enterprises of Shandong.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Cross-modal hashing is widely used for efficient similarity searches, improving data processing efficiency, and reducing storage costs. Existing cross-modal hashing methods primarily focus on centralized training scenarios, where fixed-scale and fixed-category multi-modal data is collected beforehand. However, these methods often face challenges associated with the potential risk of privacy breaches and high data communication costs during data transmission in real-world multimedia retrieval tasks. To tackle these challenges, in this article, we propose an efficient privacy-enhanced prototype-based federated cross-modal hashing (PEPFCH). In PEPFCH, we integrate local and global prototypes in order to effectively capture the distinctive traits of individual clients, while also harnessing the collective intelligence of the entire federated learning system. Moreover, to ensure the security of prototype information and prevent its disclosure during the aggregation process, we use a prototype encryption transmission mechanism to encrypt the prototype information before transmission, making it challenging for attackers to gain access to sensitive data. Additionally, to facilitate personalized federated learning and alleviate the issue of parametric catastrophic forgetting, we establish the image and text hyper-networks for each client and adopt a hyper-network extension strategy to selectively preserve and update previously acquired knowledge when acquiring new concepts or categories. Comprehensive experiments highlight the efficiency and superiority of our proposed method. To enhance research and accessibility, we have publicly released our source codes at: https://github.com/vindahi/PEPFCH .

Förderung

  • Qilu University of Technology (Shandong Academy of Sciences) Science
  • Program of New Twenty Policies for Universities of Jinan
  • Program of Innovation Improvement for Small and Medium-sized Enterprises of Shandong

Zitieren

APA

Zuo, R., Zheng, C., Li, F., Zhu, L., & Zhang, Z. (2024). Privacy-Enhanced Prototype-Based Federated Cross-Modal Hashing for Cross-Modal Retrieval. ACM Transactions on Multimedia Computing, Communications, and Applications, 20(9), 1-19. https://doi.org/10.1145/3674507

Vancouver

Zuo R, Zheng C, Li F, Zhu L, Zhang Z. Privacy-Enhanced Prototype-Based Federated Cross-Modal Hashing for Cross-Modal Retrieval. ACM Transactions on Multimedia Computing, Communications, and Applications. 2024;20(9):1-19. doi:10.1145/3674507

BibTeX
@article{Zuo2024,
  author = {Zuo, Ruifan and Zheng, Chaoqun and Li, Fengling and Zhu, Lei and Zhang, Zheng},
  title = {Privacy-Enhanced Prototype-Based Federated Cross-Modal Hashing for Cross-Modal Retrieval},
  journal = {ACM Transactions on Multimedia Computing, Communications, and Applications},
  year = {2024},
  volume = {20},
  number = {9},
  pages = {1--19},
  doi = {10.1145/3674507}
}
Kostenlos starten →