PCPE-YOLO with a lightweight dynamically reconfigurable backbone for small object detection

Abstract In the domain of object detection, small object detection remains a pressing challenge, as existing approaches often suffer from limited accuracy, high model complexity, and difficulty meeting lightweight deployment requirements. In this paper, we propose PCPE-YOLO, a novel object detection...

Full description

Saved in:
Bibliographic Details
Main Authors: Weijia Chen, Jiaming Liu, Tong Liu, Yaoming Zhuang
Format: Article
Language:English
Published: Nature Portfolio 2025-08-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-15975-w
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849735865651167232
author Weijia Chen
Jiaming Liu
Tong Liu
Yaoming Zhuang
author_facet Weijia Chen
Jiaming Liu
Tong Liu
Yaoming Zhuang
author_sort Weijia Chen
collection DOAJ
description Abstract In the domain of object detection, small object detection remains a pressing challenge, as existing approaches often suffer from limited accuracy, high model complexity, and difficulty meeting lightweight deployment requirements. In this paper, we propose PCPE-YOLO, a novel object detection algorithm, specifically designed to address these difficulties. First, we put forward a dynamically reconfigurable C2f_PIG module. This module uses a parameter-aware mechanism to adapt its bottleneck structures to different network depths and widths, reducing parameters while maintaining performance. Next, we introduce a Context Anchor Attention mechanism that boosts the model’s focus on the contexts of small objects, thereby improving detection accuracy. In addition, we add a small object detection layer to enhance the model’s localization capability for small objects. Finally, we integrate an Efficient Up-Convolution Block to sharpen decoder feature maps, enhancing small object recall with minimal computational overhead. Experiments on VisDrone2019, KITTI, and NWPU VHR-10 datasets show that PCPE-YOLO significantly outperforms both the baseline and other state-of-the-art methods in precision, recall, mean average precision, and parameters, achieving the best precision among all compared approaches. On VisDrone2019 in particular, it achieves improvements of 3.8% in precision, 5.6% in recall, 6.2% in mAP50, and 5% in F1 score, effectively combining lightweight design with high small object detection performance and providing a more efficient and reliable solution for small object detection in real-world applications.
format Article
id doaj-art-0610a787df0b42e6911260268d03d09f
institution DOAJ
issn 2045-2322
language English
publishDate 2025-08-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-0610a787df0b42e6911260268d03d09f2025-08-20T03:07:26ZengNature PortfolioScientific Reports2045-23222025-08-0115111510.1038/s41598-025-15975-wPCPE-YOLO with a lightweight dynamically reconfigurable backbone for small object detectionWeijia Chen0Jiaming Liu1Tong Liu2Yaoming Zhuang3Faculty of Business Administration, Northeastern UniversityFaculty of Robot Science and Engineering, Northeastern UniversityFaculty of Business Administration, Northeastern UniversityFaculty of Robot Science and Engineering, Northeastern UniversityAbstract In the domain of object detection, small object detection remains a pressing challenge, as existing approaches often suffer from limited accuracy, high model complexity, and difficulty meeting lightweight deployment requirements. In this paper, we propose PCPE-YOLO, a novel object detection algorithm, specifically designed to address these difficulties. First, we put forward a dynamically reconfigurable C2f_PIG module. This module uses a parameter-aware mechanism to adapt its bottleneck structures to different network depths and widths, reducing parameters while maintaining performance. Next, we introduce a Context Anchor Attention mechanism that boosts the model’s focus on the contexts of small objects, thereby improving detection accuracy. In addition, we add a small object detection layer to enhance the model’s localization capability for small objects. Finally, we integrate an Efficient Up-Convolution Block to sharpen decoder feature maps, enhancing small object recall with minimal computational overhead. Experiments on VisDrone2019, KITTI, and NWPU VHR-10 datasets show that PCPE-YOLO significantly outperforms both the baseline and other state-of-the-art methods in precision, recall, mean average precision, and parameters, achieving the best precision among all compared approaches. On VisDrone2019 in particular, it achieves improvements of 3.8% in precision, 5.6% in recall, 6.2% in mAP50, and 5% in F1 score, effectively combining lightweight design with high small object detection performance and providing a more efficient and reliable solution for small object detection in real-world applications.https://doi.org/10.1038/s41598-025-15975-wYOLOv8Object detectionSmall objectLightweight
spellingShingle Weijia Chen
Jiaming Liu
Tong Liu
Yaoming Zhuang
PCPE-YOLO with a lightweight dynamically reconfigurable backbone for small object detection
Scientific Reports
YOLOv8
Object detection
Small object
Lightweight
title PCPE-YOLO with a lightweight dynamically reconfigurable backbone for small object detection
title_full PCPE-YOLO with a lightweight dynamically reconfigurable backbone for small object detection
title_fullStr PCPE-YOLO with a lightweight dynamically reconfigurable backbone for small object detection
title_full_unstemmed PCPE-YOLO with a lightweight dynamically reconfigurable backbone for small object detection
title_short PCPE-YOLO with a lightweight dynamically reconfigurable backbone for small object detection
title_sort pcpe yolo with a lightweight dynamically reconfigurable backbone for small object detection
topic YOLOv8
Object detection
Small object
Lightweight
url https://doi.org/10.1038/s41598-025-15975-w
work_keys_str_mv AT weijiachen pcpeyolowithalightweightdynamicallyreconfigurablebackboneforsmallobjectdetection
AT jiamingliu pcpeyolowithalightweightdynamicallyreconfigurablebackboneforsmallobjectdetection
AT tongliu pcpeyolowithalightweightdynamicallyreconfigurablebackboneforsmallobjectdetection
AT yaomingzhuang pcpeyolowithalightweightdynamicallyreconfigurablebackboneforsmallobjectdetection