EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Deep Relational Knowledge Distillation Hashing via Relaxed Masking Triplet Optimization for Large-scale Image Retrieval

Xinyu Zhang, Qibing Qin, Wenfeng Zhang, Lei Huang

ACM Transactions on Multimedia Computing, Communications, and Applications · 31.08.2026 · 22 (8) · 1-22

DOI: 10.1145/3820061 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Multimedia Computing, Communications, and Applications, online erschienen am 22.07.2026. Verfasst von Xinyu Zhang und 3 weiteren Autor:innen. Die Arbeit nennt 52 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Shandong Provincial Natural Science Foundation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Large-scale image retrieval increasingly depends on triplet-based deep hashing methods, which typically construct training triplets using class labels. However, existing triplet-based hashing methods relying on sparse and noisy categorical labels suffer from two main issues: no triplet, where sparse annotations limit valid triplet formation, and bad triplet, where noisy or ambiguous labels cause misleading samples, which together hinder the network from learning a well-structured similarity space, causing semantically similar images to scatter and dissimilar ones to collapse, ultimately undermining retrieval accuracy. In this article, we solve this dilemma with a novel unified deep hashing framework, termed Deep Relational Knowledge Distillation Hashing (DRKDH), which decouples semantic relation modeling from visual feature learning by leveraging a teacher-student paradigm to learn semantically consistent hash codes. Specifically, the teacher model captures comprehensive semantic structural relationships across all instances, providing information-rich and noise-resilient supervision to guide the student model in learning expressive and discriminative visual embeddings, effectively mitigating the impact of low-quality triplet labels. Furthermore, by leveraging similarity weights predicted by the teacher model, a relaxed masking triplet loss is introduced into the student model, which dynamically adjusts the contribution of each triplet based on its informativeness, suppressing invalid or misleading triplets while emphasizing valuable ones to enhance training efficiency. Comprehensive experiments on THINGS, ImageNet, MIRFLICKR-25K, and NUS-WIDE show that DRKDH consistently outperforms state-of-the-art deep hashing methods under sparse and noisy supervision, while additional evaluations suggest competitive performance in selected zero-shot and few-shot settings. Source codes: https://github.com/QinLab-WFU/DRKDH .

Förderung

  • National Natural Science Foundation of China
  • Shandong Provincial Natural Science Foundation

Zitieren

APA

Zhang, X., Qin, Q., Zhang, W., & Huang, L. (2026). Deep Relational Knowledge Distillation Hashing via Relaxed Masking Triplet Optimization for Large-scale Image Retrieval. ACM Transactions on Multimedia Computing, Communications, and Applications, 22(8), 1-22. https://doi.org/10.1145/3820061

Vancouver

Zhang X, Qin Q, Zhang W, Huang L. Deep Relational Knowledge Distillation Hashing via Relaxed Masking Triplet Optimization for Large-scale Image Retrieval. ACM Transactions on Multimedia Computing, Communications, and Applications. 2026;22(8):1-22. doi:10.1145/3820061

BibTeX
@article{Zhang2026,
  author = {Zhang, Xinyu and Qin, Qibing and Zhang, Wenfeng and Huang, Lei},
  title = {Deep Relational Knowledge Distillation Hashing via Relaxed Masking Triplet Optimization for Large-scale Image Retrieval},
  journal = {ACM Transactions on Multimedia Computing, Communications, and Applications},
  year = {2026},
  volume = {22},
  number = {8},
  pages = {1--22},
  doi = {10.1145/3820061}
}
Kostenlos starten →