EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Multi-FusNet: fusion mapping of features for fine-grained image retrieval networks

Xiaohui Cui, Huan Li, Lei Liu, Sheng Wang, Fu Xu

PeerJ Computer Science · 24.06.2024 · 10 · e2025

DOI: 10.7717/peerj-cs.2025 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PeerJ Computer Science, online erschienen am 24.06.2024. Verfasst von Xiaohui Cui und 4 weiteren Autor:innen. Beteiligte Einrichtung: Engineering Research Center for Forestry-oriented Intelligent Information Processing of National Forestry and Grassland Administration, Beijing, Chin…. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 82 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: The National Key R&D Program of China, The Emergency Open Competition Project of National Forestry and Grassland Administration, Outstanding Youth Team Project of Central Universities.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

As the diversity and volume of images continue to grow, the demand for efficient fine-grained image retrieval has surged across numerous fields. However, the current deep learning-based approaches to fine-grained image retrieval often concentrate solely on the top-layer features, neglecting the relevant information carried in the middle layer, even though these information contains more fine-grained identification content. Moreover, these methods typically employ a uniform weighting strategy during hash code mapping, risking the loss of critical region mapping—an irreversible detriment to fine-grained retrieval tasks. To address the above problems, we propose a novel method for fine-grained image retrieval that leverage feature fusion and hash mapping techniques. Our approach harnesses a multi-level feature cascade, emphasizing not just top-layer but also intermediate-layer image features, and integrates a feature fusion module at each level to enhance the extraction of discriminative information. In addition, we introduce an agent self-attention architecture, marking its first application in this context, which steers the model to prioritize on long-range features, further avoiding the loss of critical regions of the mapping. Finally, our proposed model significantly outperforms existing state-of-the-art, improving the retrieval accuracy by an average of 40% for the 12-bit dataset, 22% for the 24-bit dataset, 16% for the 32-bit dataset, and 11% for the 48-bit dataset across five publicly available fine-grained datasets. We also validate the generalization ability and performance stability of our proposed method by another five datasets and statistical significance tests. Our code can be downloaded from https://github.com/BJFU-CS2012/MuiltNet.git .

Schlagwörter

Stichwörter der Autor:innen

Attention mechanismDeep hashingFeature fusionFine-grained hashing

Autor:innen und Institutionen

  • Engineering Research Center for Forestry-oriented Intelligent Information Processing of National Forestry and Grassland Administration, Beijing, China.
  • School of Information Science and Technology, Beijing Forestry University, Beijing, China.
  • State Key Laboratory of Efficient Production of Forest Resources, Beijing, China.

Förderung

  • The National Key R&D Program of China
  • The Emergency Open Competition Project of National Forestry and Grassland Administration
  • Outstanding Youth Team Project of Central Universities

Zitieren

APA

Cui, X., Li, H., Liu, L., Wang, S., & Xu, F. (2024). Multi-FusNet: fusion mapping of features for fine-grained image retrieval networks. PeerJ Computer Science, 10, e2025. https://doi.org/10.7717/peerj-cs.2025

Vancouver

Cui X, Li H, Liu L, Wang S, Xu F. Multi-FusNet: fusion mapping of features for fine-grained image retrieval networks. PeerJ Computer Science. 2024;10:e2025. doi:10.7717/peerj-cs.2025

BibTeX
@article{Cui2024,
  author = {Cui, Xiaohui and Li, Huan and Liu, Lei and Wang, Sheng and Xu, Fu},
  title = {Multi-FusNet: fusion mapping of features for fine-grained image retrieval networks},
  journal = {PeerJ Computer Science},
  year = {2024},
  volume = {10},
  pages = {e2025},
  doi = {10.7717/peerj-cs.2025}
}
Kostenlos starten →