2026-10-11T16:28:27Z https://api.figshare.com/v2/oai

oai:figshare.com:article/33937865 2026-09-18T17:29:11Z category_146 category_734 category_931 category_106 portal_5 item_type_3 month_year_09_2026

<p>Ablation Experiment Results.</p> YiZhong Yang (25073180) YeXue Li (25073183) ShengWei Li (25073186) MaoHu Tao (25073189) Xuzhi Chen (25073192) Space Science Biological Sciences not elsewhere classified Information Systems not elsewhere classified Science Policy task alignment principle proposed lightweight design novel improved algorithm yolo increases map50 insufficient recognition accuracy construction waste detection construction waste detection head based detection xlink "> public datasets parameter count paper proposes model size model performance hinders real effective balance deep learning constructed 10 complex scenarios category dataset c3k2 module approximately 20 also validated 23 mb 1 %, <div><p>To tackle the challenges in construction waste detection under complex scenarios—such as insufficient recognition accuracy, significant feature variations among identical waste categories, limited publicly available CDW datasets, and excessive computational resource consumption that hinders real-time performance—this paper proposes a novel improved algorithm, GTS-YOLO. Built on YOLOv11, GTS-YOLO achieves model lightweighting by optimizing the C3K2 module in the backbone network, enhances detection accuracy effectively through integrating spatial attention mechanisms between the backbone and neck, and redesigns the detection head with reference to the task alignment principle to better handle object detection of construction waste under occlusion and deformation. On our self-constructed 10-category dataset, compared with YOLOv11n, GTS-YOLO increases mAP50 by 3.24% to 67.47%, improves Precision by 3.1%, and reduces the parameter count by 19.4%, In addition, the model size is only 4.23 MB, which is approximately 20.6% smaller than YOLOv11n, demonstrating the effectiveness of the proposed lightweight design.achieving an effective balance between accuracy and efficiency.We have also validated the model performance on public datasets, demonstrating its generalization ability across diverse scenarios.</p></div> 2026-09-18T17:28:52Z Dataset Dataset 10.1371/journal.pone.0356914.t002 https://figshare.com/articles/dataset/_p_Ablation_Experiment_Results_p_/33937865 CC BY 4.0