Semantic-Consistent Bidirectional Contrastive Hashing for Noisy Multi-Label Cross-Modal Retrieval
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (29) · 24811-24819
DOI: 10.1609/aaai.v40i29.39667 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Likang Peng und 6 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref).
Abstract (Originalsprache)
Cross-modal hashing (CMH) facilitates efficient retrieval across different modalities (e.g., image and text) by encoding data into compact binary representations. While recent methods have achieved remarkable performance, they often rely heavily on fully annotated datasets, which are costly and labor-intensive to obtain. In real-world scenarios, particularly in multi-label datasets, label noise is prevalent and severely degrades retrieval performance. Moreover, existing CMH approaches typically overlook the partial semantic overlaps inherent in multi-label data, limiting their robustness and generalization. To tackle these challenges, we propose a novel framework named Semantic-Consistent Bidirectional Contrastive Hashing (SCBCH). The framework comprises two complementary modules: (1) Cross-modal Semantic-Consistent Classification (CSCC), which leverages cross-modal semantic consistency to estimate sample reliability and reduce the impact of noisy labels; (2) Bidirectional Soft Contrastive Hashing (BSCH), which dynamically generates soft contrastive sample pairs based on multi-label semantic overlap, enabling adaptive contrastive learning between semantically similar and dissimilar samples across modalities. Extensive experiments on four widely-used cross-modal retrieval benchmarks validate the effectiveness and robustness of our method, consistently outperforming state-of-the-art approaches under noisy multi-label conditions.
Zitieren
APA
Peng, L., Su, C., Wu, W., Sun, Y., Peng, D., Peng, X., & Wang, X. (2026). Semantic-Consistent Bidirectional Contrastive Hashing for Noisy Multi-Label Cross-Modal Retrieval. Proceedings of the AAAI Conference on Artificial Intelligence, 40(29), 24811-24819. https://doi.org/10.1609/aaai.v40i29.39667
Vancouver
Peng L, Su C, Wu W, Sun Y, Peng D, Peng X, et al. Semantic-Consistent Bidirectional Contrastive Hashing for Noisy Multi-Label Cross-Modal Retrieval. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(29):24811-24819. doi:10.1609/aaai.v40i29.39667
BibTeX
@article{Peng2026,
author = {Peng, Likang and Su, Chao and Wu, Wenyuan and Sun, Yuan and Peng, Dezhong and Peng, Xi and Wang, Xu},
title = {Semantic-Consistent Bidirectional Contrastive Hashing for Noisy Multi-Label Cross-Modal Retrieval},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {29},
pages = {24811--24819},
doi = {10.1609/aaai.v40i29.39667}
}
EUVIMED