DLE-YOLO: An efficient object detection algorithm with dual-branch lightweight excitation network

As a computer vision task, object detection algorithms can be applied to various real-world scenarios. However, efficient algorithms often come with a large number of parameters and high computational complexity. To meet the demand for high-performance object detection algorithms on mobile devices a...

Full description

Saved in:
Bibliographic Details
Main Authors: Peitao Cheng, Xuanjiao Lei, Haoran Chen, Xiumei Wang
Format: Article
Language:English
Published: KeAi Communications Co., Ltd. 2025-03-01
Series:Journal of Information and Intelligence
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2949715924000751
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849426123497144320
author Peitao Cheng
Xuanjiao Lei
Haoran Chen
Xiumei Wang
author_facet Peitao Cheng
Xuanjiao Lei
Haoran Chen
Xiumei Wang
author_sort Peitao Cheng
collection DOAJ
description As a computer vision task, object detection algorithms can be applied to various real-world scenarios. However, efficient algorithms often come with a large number of parameters and high computational complexity. To meet the demand for high-performance object detection algorithms on mobile devices and embedded devices with limited computational resources, we propose a new lightweight object detection algorithm called DLE-YOLO. Firstly, we design a novel backbone called dual-branch lightweight excitation network (DLEN) for feature extraction, which is mainly constructed by dual-branch lightweight excitation units (DLEU). DLEU is stacked with different numbers of dual-branch lightweight excitation blocks (DLEB), which can extract comprehensive features and integrate information between different channels of features. Secondly, in order to enhance the network to capture key feature information in the regions of interest, the attention model HS-coordinate attention (HS-CA) is introduced into the network. Thirdly, the localization loss utilizes SIoU loss to further optimize the accuracy of the bounding box. Our method achieves a mAP value of 46.0% on the MS-COCO dataset, which is a 2% mAP improvement compared to the baseline YOLOv5-m, while bringing a 19.3% reduction in parameter count and a 12.9% decrease in GFLOPs. Furthermore, our method outperforms some advanced lightweight object detection algorithms, validating the effectiveness of our approach.
format Article
id doaj-art-312a7dc00d5547d59eb0b2d86e9e530d
institution Kabale University
issn 2949-7159
language English
publishDate 2025-03-01
publisher KeAi Communications Co., Ltd.
record_format Article
series Journal of Information and Intelligence
spelling doaj-art-312a7dc00d5547d59eb0b2d86e9e530d2025-08-20T03:29:34ZengKeAi Communications Co., Ltd.Journal of Information and Intelligence2949-71592025-03-01329110210.1016/j.jiixd.2024.08.002DLE-YOLO: An efficient object detection algorithm with dual-branch lightweight excitation networkPeitao Cheng0Xuanjiao Lei1Haoran Chen2Xiumei Wang3School of Mechano-Electronic Engineering, Xidian University, Xi'an 710071, ChinaSchool of Mechano-Electronic Engineering, Xidian University, Xi'an 710071, ChinaSchool of Mechano-Electronic Engineering, Xidian University, Xi'an 710071, ChinaSchool of Electronic Engineering, Xidian University, Xi'an 710071, China; Corresponding author.As a computer vision task, object detection algorithms can be applied to various real-world scenarios. However, efficient algorithms often come with a large number of parameters and high computational complexity. To meet the demand for high-performance object detection algorithms on mobile devices and embedded devices with limited computational resources, we propose a new lightweight object detection algorithm called DLE-YOLO. Firstly, we design a novel backbone called dual-branch lightweight excitation network (DLEN) for feature extraction, which is mainly constructed by dual-branch lightweight excitation units (DLEU). DLEU is stacked with different numbers of dual-branch lightweight excitation blocks (DLEB), which can extract comprehensive features and integrate information between different channels of features. Secondly, in order to enhance the network to capture key feature information in the regions of interest, the attention model HS-coordinate attention (HS-CA) is introduced into the network. Thirdly, the localization loss utilizes SIoU loss to further optimize the accuracy of the bounding box. Our method achieves a mAP value of 46.0% on the MS-COCO dataset, which is a 2% mAP improvement compared to the baseline YOLOv5-m, while bringing a 19.3% reduction in parameter count and a 12.9% decrease in GFLOPs. Furthermore, our method outperforms some advanced lightweight object detection algorithms, validating the effectiveness of our approach.http://www.sciencedirect.com/science/article/pii/S2949715924000751Object detectionLightweight networkAttention mechanismLoss function
spellingShingle Peitao Cheng
Xuanjiao Lei
Haoran Chen
Xiumei Wang
DLE-YOLO: An efficient object detection algorithm with dual-branch lightweight excitation network
Journal of Information and Intelligence
Object detection
Lightweight network
Attention mechanism
Loss function
title DLE-YOLO: An efficient object detection algorithm with dual-branch lightweight excitation network
title_full DLE-YOLO: An efficient object detection algorithm with dual-branch lightweight excitation network
title_fullStr DLE-YOLO: An efficient object detection algorithm with dual-branch lightweight excitation network
title_full_unstemmed DLE-YOLO: An efficient object detection algorithm with dual-branch lightweight excitation network
title_short DLE-YOLO: An efficient object detection algorithm with dual-branch lightweight excitation network
title_sort dle yolo an efficient object detection algorithm with dual branch lightweight excitation network
topic Object detection
Lightweight network
Attention mechanism
Loss function
url http://www.sciencedirect.com/science/article/pii/S2949715924000751
work_keys_str_mv AT peitaocheng dleyoloanefficientobjectdetectionalgorithmwithdualbranchlightweightexcitationnetwork
AT xuanjiaolei dleyoloanefficientobjectdetectionalgorithmwithdualbranchlightweightexcitationnetwork
AT haoranchen dleyoloanefficientobjectdetectionalgorithmwithdualbranchlightweightexcitationnetwork
AT xiumeiwang dleyoloanefficientobjectdetectionalgorithmwithdualbranchlightweightexcitationnetwork