Mask R-CNN中特征不平衡问题的全局信息融合方法

doi:10.19678/j.issn.1000-3428.0056469

计算机工程 ›› 2021, Vol. 47 ›› Issue (3): 256-260,268. doi: 10.19678/j.issn.1000-3428.0056469

Mask R-CNN中特征不平衡问题的全局信息融合方法

文韬, 周稻祥, 李明

太原理工大学大数据学院, 山西晋中 030600

收稿日期:2019-11-01 修回日期:2020-01-14 发布日期:2020-02-26
作者简介:文韬(1993-),男,硕士研究生,主研方向为深度学习、机器视觉;周稻祥,讲师、博士;李明,教授、博士。
基金资助:
国家自然科学基金（11771321）；山西省科技厅社会发展科技攻关计划（201703D321032）。

Global Information Fusion Method for Feature Imbalance Problem in Mask R-CNN

WEN Tao, ZHOU Daoxiang, LI Ming

Collage of Data Science, Taiyuan University of Technology, Jinzhong, Shanxi 030600, China

Received:2019-11-01 Revised:2020-01-14 Published:2020-02-26

摘要/Abstract

摘要： 特征不平衡问题是影响神经网络检测效率的关键因素。针对Mask R-CNN中的特征不平衡问题，提出一种基于全局特征金字塔网络（GFPN）的信息融合方法。通过将GFPN产生的不同大小特征相融合，生成包含全局语义信息的特征网络，并采用反向过程对原始特征层进行重新标度，从而使得每个特征层均含有全局语义信息。实验结果表明，与原始基于Mask R-CNN的方法相比，该方法的检测精度提升4~6个百分点，而检测时间仅增加0.112 s。

关键词: 特征不平衡, 全局特征金字塔网络, 语义信息, Mask R-CNN方法, 深度学习

Abstract: The feature imbalance is a key factor affecting detection efficiency of neural networks.To address the feature imbalance in Mask R-CNN,this paper proposes an information fusion method based on Global Feature Pyramid Network(GFPN).By fusing the different features generated by GFPN,the feature network that contains global semantic information is generated.Then the original feature layer is re-scaled by using the reverse process to make each feature layer contained global semantic information.Experimental results show that compared with the original method based on Mask R-CNN,the proposed method improves the detection accuracy by 4 percentage points to 6 percentage points, while the detection time only increases by 0.112 s.

Key words: feature imbalance, Global Feature Pyramid Network(GFPN), semantic information, Mask R-CNN method, deep learning

中图分类号:

TP391.41

文韬, 周稻祥, 李明. Mask R-CNN中特征不平衡问题的全局信息融合方法[J]. 计算机工程, 2021, 47(3): 256-260,268.

WEN Tao, ZHOU Daoxiang, LI Ming. Global Information Fusion Method for Feature Imbalance Problem in Mask R-CNN[J]. Computer Engineering, 2021, 47(3): 256-260,268.

https://www.ecice06.com/CN/Y2021/V47/I3/256

图/表 8

20210322174223

20210322174226

20210322174229

20210322174233

20210322174236

20210322174242

20210322174249

20210322174253

参考文献

[1] LIU W,ANGUELOV D,ERHAN D,et al.SSD:single shot multi-box detector[M].Berlin,Germany:Springer,2016:21-37.
[2] KRIZHEVSKY A,SUTSKEVER I,HINTON G. ImageNet classification with deep convolutional neural networks[C]//Proceedings of the 25th International Conference on Neural Information Processing Systems. Washington D.C.,USA:IEEE Press,2012:1097-1105.
[3] REDMON J,DIVVALA S,GIRSHICK R,et al.You only look once:unified,real-time object detection[C]//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2016:1-8.
[4] REDMON J,FARHADI A.YOLO9000:better,faster,stronger[C]//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2017:6517-6525.
[5] REDMON J,FARHADI A.YOLOv3:an incremental improvement[EB/OL].[2019-09-28].https://arxiv.org/abs/1804.02767.
[6] IOFFE S,SZEGEDY C.Batch normalization:accelerating deep network training by reducing internal covariate shift[EB/OL].[2019-09-28].https://arxiv.org/abs/1502.03167.
[7] LIN T Y,DOLLAR P,GIRSHICK R,et al.Feature pyramid networks for object detection[C]//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2017:936-944.
[8] GAO Hongwei,HAN Xiaohong,ZHOU Daoxiang. Supernova object detection method based on improved Faster R-CNN[J].Computer Engineering,2020,46(10):282-288.(in Chinese)高宏伟,韩晓红,周稻祥.基于改进Faster R-CNN的超新星目标检测方法[J].计算机工程,2020,46(10):282-288.
[9] GIRSHICK R.Fast R-CNN[C]//Proceedings of 2015 IEEE International Conference on Computer Vision. Washington D.C.,USA:IEEE Press,2015:1440-1448.
[10] REN S Q,HE K M,GIRSHICK R,et al.Faster R-CNN:towards real-time object detection with region proposal networks[J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017,39(6):1137-1149.
[11] HE K M,GKIOXARI G,DOLLAR P,et al.Mask R-CNN[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2020,42(2):386-397.
[12] HE Kaiming,ZHANG Xiangyu,REN Shaoqing,et al.Deep residual learning for image recognition[C]//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2016:770-778.
[13] LIU Shu,QI Lu,QIN Haifang,et al.Path aggregation network for instance segmentation[C]//Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press, 2018:1-9.
[14] ZHOU Peng,NI Bingbing,GENG Cong,et al.Scale-transferrable object detection[C]//Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2018:528-537.
[15] HUANG G,LIU Z,VAN D M L,et al.Densely connected convolutional networks[C]//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2017:2261-2269.
[16] QIN Z,LI Z M,ZHANG Z N,et al.ThunderNet:towards real-time generic object detection[EB/OL].[2019-09-28].https://arxiv.org/abs/1903.11752.
[17] SHELHAMER E,LONG J,DARRELL T.Fully convolutional networks for semantic segmentation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(4):640-651.
[18] LIN T Y,MAIRE M,BELONGIE S,et al.Microsoft COCO:common objects in context[M].Berlin,Germany:Springer,2014:740-755.
[19] DENG J,DONG W,SOCHER R,et al.ImageNet:a large-scale hierarchical image database[C]//Proceedings of 2009 IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2009:248-255.
[20] LIN T Y,GOYAL P,GIRSHICK R,et al.Focal loss for dense object detection[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2020,42(2):318-327.
[21] PANG Jiangmiao,CHEN Kai,SHI Jianping,et al.Libra R-CNN:towards balanced learning for object detection[EB/OL].[2019-09-28].https://arxiv.org/abs/1904.02701.

选择文件类型/文献管理软件名称

选择包含的内容

Mask R-CNN中特征不平衡问题的全局信息融合方法

Global Information Fusion Method for Feature Imbalance Problem in Mask R-CNN

RichHTML

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

图/表 8

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	牛瑞婷, 严天峰, 高锐, 王映植. 低信噪比下基于深度学习TCNN-MobileNet的调制识别[J]. 计算机工程, 2024, 50(7): 204-215.
[2]	肖慈, 徐杨, 张永丹, 冯明文, 黄易仟. 结合注意力和低光增强的夜间语义分割[J]. 计算机工程, 2024, 50(7): 271-281.
[3]	张诗婧, 莫绪涛, 赵行, 董杨林. 基于球面折反射成像和YOLOv7的内螺纹缺陷检测[J]. 计算机工程, 2024, 50(7): 282-292.
[4]	徐明亮, 李芳媛, 马浩然, 何飞. 大规模神经记录的峰电位聚类算法(特邀)[J]. 计算机工程, 2024, 50(6): 1-34.
[5]	魏琢艺, 罗迈, 李文兵, 曾远松, 余伟江, 杨跃东. 基于多源域适应的单细胞智能分类[J]. 计算机工程, 2024, 50(6): 48-55.
[6]	李子杰, 周菊香, 韩晓瑜, 甘健侯, 鹿泽光, 王俊. 序列特征与学习过程融合的知识追踪模型[J]. 计算机工程, 2024, 50(6): 77-85.
[7]	李永飞, 李铭洋, 常鑫, 曹可欣. 基于可解释性深度学习的物联网水质监测数据异常检测[J]. 计算机工程, 2024, 50(6): 179-187.
[8]	武星, 殷浩宇, 姚骏峰, 李卫民, 钱权. 面向视频数据的多模态情感分析[J]. 计算机工程, 2024, 50(6): 218-227.
[9]	李致金, 汤佳辉, 闫金凤. 基于边缘计算的轻量化识别方法[J]. 计算机工程, 2024, 50(6): 287-295.
[10]	李雪, 王雅文, 张前进. 基于信息检索的源代码自动命名[J]. 计算机工程, 2024, 50(6): 304-310.
[11]	孙帮勇, 马铭, 于涛. 基于区域特征强化的多尺度伪装目标检测方法[J]. 计算机工程, 2024, 50(5): 209-219.
[12]	郑娟毅, 张庆珏, 董嘉豪, 郭梦月, 杨溥江. 一种深度学习的波束空间信道估计算法[J]. 计算机工程, 2024, 50(5): 298-305.
[13]	赵逸飞, 张俊华. 虚拟脊柱侧凸病例腰椎自动生成方法[J]. 计算机工程, 2024, 50(5): 323-329.
[14]	刘仲民, 严梁. 融合动态特征与注意力的敦煌壁画修复模型[J]. 计算机工程, 2024, 50(5): 342-353.
[15]	隗昊, 刁宏悦, 孔亮宸, 邓耀臣. 东北亚舆情文本细粒度命名实体识别方法研究[J]. 计算机工程, 2024, 50(5): 354-362.

模态框（Modal）标题

选择文件类型/文献管理软件名称

选择包含的内容

Mask R-CNN中特征不平衡问题的全局信息融合方法

Global Information Fusion Method for Feature Imbalance Problem in Mask R-CNN

RichHTML

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

图/表 8

参考文献

相关文章 15

编辑推荐

Metrics

本文评价