EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Category-Level Contrastive Learning for Unsupervised Hashing in Cross-Modal Retrieval

Mengying Xu, Linyin Luo, Hanjiang Lai, Jian Yin

Data Science and Engineering · 2024-09 · 9 (3) · 251-263

DOI: 10.1007/s41019-024-00248-9 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Data Science and Engineering, online erschienen am 02.04.2024. Verfasst von Mengying Xu und 3 weiteren Autor:innen. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the Key-Area Research and Development Program of Guangdong Province.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Unsupervised hashing for cross-modal retrieval has received much attention in the data mining area. Recent methods rely on image-text paired data to conduct unsupervised cross-modal hashing in batch samples. There are two main limitations for existing models: (1) learning of cross-modal representations is restricted to batches; (2) semantically similar samples may be wrongly treated as negative. In this paper, we propose a novel category-level contrastive learning for unsupervised cross-modal hashing, which alleviates the above problems and improves cross-modal query accuracy. To break the limitation of learning in small batches, a selected memory module is first proposed to take global relations into account. Then, we obtain pseudo labels through clustering and combine the labels with the Hadamard Matrix for category-centered learning. To reduce wrong negatives, we further propose a memory bank to store clusters of samples and construct negatives by selecting samples from different categories for contrastive learning. Extensive experiments show the significant superiority of our approach over the state-of-the-art models on MIRFLICKR-25K and NUS-WIDE datasets.

Förderung

  • the Key-Area Research and Development Program of Guangdong Province

Zitieren

APA

Xu, M., Luo, L., Lai, H., & Yin, J. (2024). Category-Level Contrastive Learning for Unsupervised Hashing in Cross-Modal Retrieval. Data Science and Engineering, 9(3), 251-263. https://doi.org/10.1007/s41019-024-00248-9

Vancouver

Xu M, Luo L, Lai H, Yin J. Category-Level Contrastive Learning for Unsupervised Hashing in Cross-Modal Retrieval. Data Science and Engineering. 2024;9(3):251-263. doi:10.1007/s41019-024-00248-9

BibTeX
@article{Xu2024,
  author = {Xu, Mengying and Luo, Linyin and Lai, Hanjiang and Yin, Jian},
  title = {Category-Level Contrastive Learning for Unsupervised Hashing in Cross-Modal Retrieval},
  journal = {Data Science and Engineering},
  year = {2024},
  volume = {9},
  number = {3},
  pages = {251--263},
  doi = {10.1007/s41019-024-00248-9}
}
Kostenlos starten →