Noise-Robust Generative Hashing for Cross-Modal Retrieval
ACM Transactions on Multimedia Computing, Communications, and Applications · 30.04.2026 · 22 (4) · 1-22
DOI: 10.1145/3777477 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Multimedia Computing, Communications, and Applications, online erschienen am 09.03.2026. Verfasst von Zequn Wang und 4 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 54 Literaturangaben. Gefördert von: Fundamental Research Funds for the Central Universities.
Abstract (Originalsprache)
Deep hashing has proven remarkable effectiveness for large-scale cross-modal retrieval, yet its performance is highly vulnerable to supervisory noise, such as mismatched cross-modal correspondences and incorrect category labels. Such noise is prevalent in real-world scenarios, where correspondence mismatches and label inaccuracies often coexist, posing significant challenges for learning accurate multimodal representations. Existing methods typically address only a single type of noise in isolation and neglect the potential value of noisy data, resulting in limited performance gains. To address these challenges, we propose Noise-Robust Generative Hashing (NRGH), a unified framework designed to accommodate various forms of noise inherent in cross-modal retrieval. Specifically, NRGH introduces a hash-driven noise estimation module that computes the confidence score for each multimodal sample by combining frozen auxiliary hash functions with a Gaussian mixture model. Guided by these confidence scores, NRGH performs data correction through two stages: generative text refinement and multi-label probability calibration. The former leverages a pre-trained vision-language model to generate descriptive captions that refine noisy textual information, while the latter corrects noisy labels using confidence-aware soft labels. Furthermore, a dynamic margin contrastive loss adaptively modulates the data contribution of each sample based on its confidence, enabling sample-level adaptive learning. Extensive experiments on benchmark datasets demonstrate that NRGH significantly exceeds state-of-the-art baselines in various noisy scenarios, delivering superior robustness and accuracy. Our source codes and datasets are available at https://github.com/xiaolaohuuu/NRGH .
Förderung
- Fundamental Research Funds for the Central Universities
Zitieren
APA
Wang, Z., Wang, T., Li, F., Li, J., & Zhu, L. (2026). Noise-Robust Generative Hashing for Cross-Modal Retrieval. ACM Transactions on Multimedia Computing, Communications, and Applications, 22(4), 1-22. https://doi.org/10.1145/3777477
Vancouver
Wang Z, Wang T, Li F, Li J, Zhu L. Noise-Robust Generative Hashing for Cross-Modal Retrieval. ACM Transactions on Multimedia Computing, Communications, and Applications. 2026;22(4):1-22. doi:10.1145/3777477
BibTeX
@article{Wang2026,
author = {Wang, Zequn and Wang, Tianshi and Li, Fengling and Li, Jingjing and Zhu, Lei},
title = {Noise-Robust Generative Hashing for Cross-Modal Retrieval},
journal = {ACM Transactions on Multimedia Computing, Communications, and Applications},
year = {2026},
volume = {22},
number = {4},
pages = {1--22},
doi = {10.1145/3777477}
}
EUVIMED