EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

HA-FPN: Hierarchical Attention Feature Pyramid Network for Object Detection

Jin Dang, Xiaofen Tang iD, Shuai Li

Sensors · 05.05.2023 · 23 (9) · 4508

DOI: 10.3390/s23094508 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 05.05.2023. Verfasst von Jin Dang und 2 weiteren Autor:innen. Beteiligte Einrichtung: School of Information Engineering, Ningxia University, Yinchuan 750021, China. Die Arbeit wurde bisher 26-mal zitiert (Crossref) und nennt 29 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Nature Science Foundation of China, Natural Science Foundation of Ningxia.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The goals of object detection are to accurately detect and locate objects of various sizes in digital images. Multi-scale processing technology can improve the detection accuracy of the detector. Feature pyramid networks (FPNs) have been proven to be effective in extracting multi-scaled features. However, most existing object detection methods recognize objects in isolation, without considering contextual information between objects. Moreover, for the sake of computational efficiency, a significant reduction in the channel dimension may lead to the loss of semantic information. This study explores the utilization of attention mechanisms to augment the representational power and efficiency of features, ultimately improving the accuracy and efficiency of object detection. The study proposed a novel hierarchical attention feature pyramid network (HA-FPN), which comprises two key components: transformer feature pyramid networks (TFPNs) and channel attention modules (CAMs). In TFPNs, multi-scaled convolutional features are embedded as tokens and self-attention is applied to across both the intra- and inter-scales to capture contextual information between the tokens. CAMs are employed to select the channels with rich channel information to alleviate massive channel information losses. By introducing contextual information and attention mechanisms, the HA-FPN significantly improves the accuracy of bounding box detection, leading to more precise identification and localization of target objects. Extensive experiments conducted on the challenging MS COCO dataset demonstrate that the proposed HA-FPN outperforms existing multi-object detection models, while incurring minimal computational overhead.

Schlagwörter

Stichwörter der Autor:innen

attention modulesfeature pyramid networksobject detectiontransformer

Autor:innen und Institutionen

  • School of Information Engineering, Ningxia University, Yinchuan 750021, China.

ORCID-Profile: Xiaofen Tang

Förderung

  • National Nature Science Foundation of China
  • Natural Science Foundation of Ningxia

Zitieren

APA

Dang, J., Tang, X., & Li, S. (2023). HA-FPN: Hierarchical Attention Feature Pyramid Network for Object Detection. Sensors, 23(9), 4508. https://doi.org/10.3390/s23094508

Vancouver

Dang J, Tang X, Li S. HA-FPN: Hierarchical Attention Feature Pyramid Network for Object Detection. Sensors. 2023;23(9):4508. doi:10.3390/s23094508

BibTeX
@article{Dang2023,
  author = {Dang, Jin and Tang, Xiaofen and Li, Shuai},
  title = {HA-FPN: Hierarchical Attention Feature Pyramid Network for Object Detection},
  journal = {Sensors},
  year = {2023},
  volume = {23},
  number = {9},
  pages = {4508},
  doi = {10.3390/s23094508}
}
Kostenlos starten →