Weighted parallel decoupled feature pyramid network for object detection

Han, Bo; He, Lihuo; Ke, Junjie; Tang, Chenwei; Gao, Xinbo

doi:10.1016/j.neucom.2024.127809

Search citation statements

Order By: Relevance

Paper Sections

Select...

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2024

Publication Types

Select...

Article1

Preprint1

Relationship

Self Cite0

Independent2

Authors

Journals

Cited by 2 publications

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

A Novel Dynamic Recognition Method of Rock Burst Precursor Information Based on Adaptive Denoising and Object Detection

Zhao,

Wang,

Wang

et al. 2024

Mining, Metallurgy & Exploration

View full text Add to dashboard Cite

A Novel Dynamic Recognition Method of Rock Burst Precursor Information Based on Adaptive Denoising and Object Detection

Zhao,

Wang,

Wang

et al. 2024

Mining, Metallurgy & Exploration

View full text Add to dashboard Cite

Ultra-Lightweight YOLOv8n for PCB Defect Detection: An Adaptive Approach with Enhanced Feature Extraction and Efficient Model Embedding

Zhou,

Lu,

2024

Preprint

View full text Add to dashboard Cite

To address the issues of missed and false detections caused by numerous tiny objects and complex background textures in printed circuit boards (PCBs), as well as the difficulty of embedding detection models into portable devices, this paper proposes an ultra-lightweight YOLOv8n defect detection method. Firstly, the method introduces an Uncertainty-driven Adaptive Training Sample Selection (UATSS) strategy during training to optimize model training and enhance detection accuracy. Secondly, it incorporates Details-Enhanced Convolution (DEConv) to improve the model's ability to extract detailed features of small PCB defects. Then, it employs a Sharing Lightweight Details-Enhanced Convolutional Detection Head (SLDECD) to replace the original Decoupled Head, reducing model complexity while enhancing network detection accuracy. Lastly, the Exponential Moving Average-Slide Loss (EMA-SlideLoss) function is introduced to provide more precise evaluation results during model training and enhance generalization capability. Comparative experiments on public PCB datasets demonstrate that the improved algorithm achieves an mAP of 97.6% and an accuracy of 99.6%, representing increases of 3.8% and 1.9%, respectively, compared to the original model. The model size is 4.1 MB, and the FPS reaches 144.1, meeting the requirements for portable embedded devices and real-time applications.

show abstract

Weighted parallel decoupled feature pyramid network for object detection

Cited by 2 publications

References 53 publications

A Novel Dynamic Recognition Method of Rock Burst Precursor Information Based on Adaptive Denoising and Object Detection

A Novel Dynamic Recognition Method of Rock Burst Precursor Information Based on Adaptive Denoising and Object Detection

Ultra-Lightweight YOLOv8n for PCB Defect Detection: An Adaptive Approach with Enhanced Feature Extraction and Efficient Model Embedding

Contact Info

Product

Resources

About