计算机工程与应用2025，Vol.61Issue(10)：247-257,11.DOI:10.3778/j.issn.1002-8331.2401-0262
ResFPN:扩增实际感受野和改进FPN的多尺度目标检测方法
ResFPN:Multi-Scale Object Detection Algorithm for Expanding Actual Receptive Field and Improving FPN
摘要
Abstract
In view of the problems that the actual receptive field of the backbone network is much smaller than the theo-retical receptive field,the sparse receptive field distribution,and the unified channel number of the feature pyramid net-work(FPN)in the horizontal connection process affect the performance of the model,ResFPN is proposed,which is a multi-scale object detection algorithm that expands the actual receptive field and improves the FPN by multi-feature fusion.In view of the fact that the actual receptive field of the backbone network is much smaller than the theoretical receptive field,a multi-branch dilated convolutional(MBD)module and a multi-branch pooling(MBP)module are de-signed to expand the receptive field by learning different scale spatial fusion.To solve the problem of sparse receptive field distribution,a lightweight channel interactive fusion(CIF)module is proposed,and the feature representation is enhanced by a two-branch structure,and the dependency relationship between separable convolution learning pixels is superimposed on each branch with different number of depths.In order to solve the problem that FPN will lose channel information through the unified channel number of 1×1 convolution,SubPixel convolution is tried to extract C5 layer features,retain the original rich semantic information and induce additional bidirectional paths to supplement the FPN channel information,but this may produce redundant information.Therefore,the global context(GC)module is intro-duced after the additional bidirectional path,and the GC bottleneck conversion module is used to further fuse the feature information and reduce the information redundancy.Experiments show that the proposed ResFPN effectively solves the problem of sparse receptive field distribution,and doubles the receptive field of the backbone network.Meanwhile,the proposed method to improve the FPN channel loss problem also achieves good performance in multi-scale object detec-tion.Compared with the typical network Faster R-CNN,the average accuracy of large,medium and small object detection on the challenging MS COCO dataset is improved by 2.2,1.6 and 2.0 percentage points,respectively,and the detection effect is also improved compared with other detectors.关键词
目标检测/卷积神经网络/多尺度目标检测/感受野/特征金字塔网络(FPN)Key words
object detection/convolutional neural network/multi-scale object detection/receptive field/feature pyramid network(FPN)分类
信息技术与安全科学引用本文复制引用
杨扬,唐晓芬..ResFPN:扩增实际感受野和改进FPN的多尺度目标检测方法[J].计算机工程与应用,2025,61(10):247-257,11.基金项目
国家自然科学基金(61966029) （61966029）
宁夏回族自治区重点研发计划(2021BEB04065). （2021BEB04065）
