面向目标检测的尺度增强特征金字塔网络
作者:
作者单位:

作者简介:

通讯作者:

中图分类号:

基金项目:

国家自然科学基金(U1803262)


Scale-enhanced Feature Pyramid Network for Object Detection
Author:
Affiliation:

Fund Project:

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 增强出版
  • |
  • 文章评论
    摘要:

    基于特征金字塔网络的目标检测算法没有充分考虑不同目标间的尺度差异以及跨层特征融合过程中高频信息损失问题, 使网络无法充分融合全局多尺度信息, 导致检测效果不佳. 针对这些问题, 提出了尺度增强特征金字塔网络. 该方法对特征金字塔网络的侧向连接和跨层特征融合方式进行了改进, 设计具有动态感受野的多尺度卷积组作为侧向连接来充分提取每一个目标的特征信息, 引入基于注意力机制的高频信息增强模块来促进高层特征与底层特征融合. 基于MS COCO数据集的实验结果表明, 该方法能有效提高各尺度目标的检测精度, 整体性能优于现有方法.

    Abstract:

    The object detection algorithms based on the feature pyramid network do not give due consideration to the scale differences among different objects and the high-frequency information loss during cross-layer feature fusion, denying the network sufficient fusion of global multi-scale information and consequently resulting in poor detection effects. To solve these problems, this study proposes a scale-enhanced feature pyramid network. This method improves the lateral connection and cross-layer feature fusion modes of the feature pyramid network. Specifically, a multi-scale convolution group with the dynamic receptive field is designed to serve as a lateral connection so that the feature information of each object can be extracted sufficiently, and a high-frequency information enhancement module based on the attention mechanism is introduced to promote the fusion of high-layer features with low-layer ones. The experimental results on the MS COCO dataset show that the proposed method can effectively improve the detection accuracy on objects at each scale and its overall performance is better than that of the existing methods.

    参考文献
    相似文献
    引证文献
引用本文

张轩,王晓峰,张文尉,黄煜婷,陈东方.面向目标检测的尺度增强特征金字塔网络.计算机系统应用,2023,(1):127-134

复制
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2022-05-12
  • 最后修改日期:2022-06-15
  • 录用日期:
  • 在线发布日期: 2022-08-26
  • 出版日期:
您是第位访问者
版权所有:中国科学院软件研究所 京ICP备05046678号-3
地址:北京海淀区中关村南四街4号 中科院软件园区 7号楼305房间,邮政编码:100190
电话:010-62661041 传真: Email:csa (a) iscas.ac.cn
技术支持:北京勤云科技发展有限公司

京公网安备 11040202500063号