EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

PNANet: Probabilistic Two-Stage Detector Using Pyramid Non-Local Attention

Di Zhang iD, Weimin Zhang iD, Fangxing Li iD, Kaiwen Liang iD, Yuhang Yang

Sensors · 21.05.2023 · 23 (10) · 4938

DOI: 10.3390/s23104938 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 21.05.2023. Verfasst von Di Zhang und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Mechatronical Engineering, Beijing Institute of Technology, Beijing 100081, China. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 73 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, National Key R&D Program of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Object detection algorithms require compact structures, reasonable probability interpretability, and strong detection ability for small targets. However, mainstream second-order object detectors lack reasonable probability interpretability, have structural redundancy, and cannot fully utilize information from each branch of the first stage. Non-local attention can improve sensitivity to small targets, but most of them are limited to a single scale. To address these issues, we propose PNANet, a two-stage object detector with a probability interpretable framework. We propose a robust proposal generator as the first stage of the network and use cascade RCNN as the second stage. We also propose a pyramid non-local attention module that breaks the scale constraint and improves overall performance, especially in small target detection. Our algorithm can be used for instance segmentation after adding a simple segmentation head. Testing on COCO and Pascal VOC datasets as well as practical applications demonstrated good results in both object detection and instance segmentation tasks.

Schlagwörter

Stichwörter der Autor:innen

object detectionprobabilistic two-stage detectorpyramid non-local attentionrobust proposal generator

Autor:innen und Institutionen

  • School of Mechatronical Engineering, Beijing Institute of Technology, Beijing 100081, China.
  • Key Laboratory of Biomimetic Robots and Systems, Ministry of Education, Beijing Institute of Technology, Beijing 100081, China.
  • Beijing Advanced Innovation Center for Intelligent Robots and Systems, Beijing 100081, China.

ORCID-Profile: Di Zhang, Weimin Zhang, Fangxing Li, Kaiwen Liang

Förderung

  • National Natural Science Foundation of China
  • National Key R&D Program of China

Zitieren

APA

Zhang, D., Zhang, W., Li, F., Liang, K., & Yang, Y. (2023). PNANet: Probabilistic Two-Stage Detector Using Pyramid Non-Local Attention. Sensors, 23(10), 4938. https://doi.org/10.3390/s23104938

Vancouver

Zhang D, Zhang W, Li F, Liang K, Yang Y. PNANet: Probabilistic Two-Stage Detector Using Pyramid Non-Local Attention. Sensors. 2023;23(10):4938. doi:10.3390/s23104938

BibTeX
@article{Zhang2023,
  author = {Zhang, Di and Zhang, Weimin and Li, Fangxing and Liang, Kaiwen and Yang, Yuhang},
  title = {PNANet: Probabilistic Two-Stage Detector Using Pyramid Non-Local Attention},
  journal = {Sensors},
  year = {2023},
  volume = {23},
  number = {10},
  pages = {4938},
  doi = {10.3390/s23104938}
}
Kostenlos starten →