Small-object detection in remote sensing images using multi-scale feature fusion
Wei Mingjun
Ge Yihui
Yang Xuan
Liu Yazhi
Li Hui
Abstract：Objectives Small objects in remote sensing images often lack sufficient discriminative features and are highly susceptible to interference from complex backgrounds,leading to frequent false and missed detections.To address this,a multi-scale feature fusion network is proposed to improve small-object detec-tion accuracy in remote sensing images.Methods A sparse attention-guided feature fusion module is first in-troduced into the medium-scale feature maps to enhance the network's sensitivity to small objects and sup-press background interference.Furthermore,to effectively integrate contextual information across different scales and improve localization accuracy,a multi-step dilated convolution fusion module is designed.This module applies multiple parallel convolutions with varying dilation rates to aggregate semantic information from features at multiple levels.Results Extensive experiments conducted on the NWPU VHR-10,RSOD,and HRSID datasets demonstrate that the proposed method achieves significantly improved detection accu-racy for small objects while maintaining or slightly enhancing performance on medium-and large-scale ob-jects.The mAP@50 values on the NWPU VHR-10,RSOD,and HRSID datasets reached 63.1%,96.92%,and 92.5%,respectively.Conclusions These results demonstrate that the proposed method,which incorpo-rates two multi-scale feature fusion strategies based on attention guidance and dilated convolution,can ef-fectively enhance the detection accuracy of small objects in remote sensing targets.
Keywords：small-object detectionmulti scaleremote sensing imagedeep learningfeature fusion
Publication Date：2025-07-31
Online Publishing Date：2025-08-15(First online date of this platform, not the publication date of the document)
Pages：8( 40-47 )