计算机科学

计算机科学 ›› 2022, Vol. 49 ›› Issue (8): 157-164.doi: 10.11896/jsjkx.210600240

• 计算机图形学& 多媒体 • 上一篇    下一篇

基于软标签和样本权重优化的Anchor Free目标检测算法

王灿1,2, 刘永坚1, 解庆1,2, 马艳春1   

  1. 1 武汉理工大学计算机科学与技术学院 武汉 430070
    2 青海武汉理工大学文化科技融合产业技术研究院 青海 海东 810600
  • 收稿日期:2021-06-30 修回日期:2021-12-09 发布日期:2022-08-02
  • 通讯作者: 解庆(felixxq@whut.edu.cn)
  • 作者简介:(cam@whut.edu.cn)
  • 基金资助:
    特色民族文化矢量数字化资源复用与产业创新项目(唐卡壁画矢量数字化标注及流程标准制定)

Anchor Free Object Detection Algorithm Based on Soft Label and Sample Weight Optimization

WANG Can1,2, LIU Yong-jian1, XIE Qing1,2, MA Yan-chun1   

  1. 1 School of Computer Science and Technology,Wuhan University of Technology,Wuhan 430070,China
    2 Qinghai-WUT Industrial Technology Research Institute of Culture and Technology Integration,Haidong,Qinghai 810600,China
  • Received:2021-06-30 Revised:2021-12-09 Published:2022-08-02
  • About author:WANG Can,born in 1994,postgra-duate.His main research interests include object detection and so on.
    XIE Qing,born in 1986,Ph.D,associate professor,is a member of China Computer Federation.His main research interests include information retrieval and machine learning.
  • Supported by:
    Characteristic National Culture Vector Digital Resource Reuse and Industrial Innovation Project(Thangka and Fresco Vector Digital Annotation and Process Standard Formulation).

PDF (PC)

594

摘要： 与Anchor Based目标检测算法类似,基于特征点的Anchor Free目标检测算法也面临着在正负样本划分中存在模糊样本的问题,即根据特定阈值和特征点位置划分非正即负的训练样本,网络在对特征点位置处在临界值附近的样本进行训练时会产生较大的损失,使得网络将注意力过于集中在这些模糊样本上,降低了网络的整体检测性能。针对此情况,提出从软标签、损失函数和权重优化3个方面对基于特征点的Anchor Free目标检测算法进行改进,通过充分利用Center Ness参数来缓解模糊样本对网络性能的影响,提高目标检测的准确率。为证明所提方法的有效性,分别在经典的Pascal VOC数据集和MS COCO数据集上使用FCOS目标检测器进行对比实验,最终将检测器在Pascal VOC数据集上的mAP提升至82.16%(提升约1.31%),在MS COCO数据集上的AP50-95提升至35.8%(提升约1.3%)。

关键词: Anchor Free, Center Ness, 模糊样本, 目标检测, 样本权重优化

Abstract: Similar to the Anchor Based object detection algorithm,the Anchor Free object detection algorithm based on feature points also encounters the problem of ambiguous samples when dividing positive and negative samples.That is,the training samples are divided either positive or negative according to the specific threshold and the position of feature points,and when the model trains samples whose feature point is near the borderline,it will incur great loss,which will make the model pay too much attention to these ambiguous samples and reduce the performance of the model.In view of this situation,this paper proposes to improve the Anchor Free object detection algorithm based on feature points from the three aspects of soft label,loss function and weight optimization.By making full use of Center Ness,the impact of ambiguous samples on network performance is mitigated and the accuracy of object detection is improved.To prove the effectiveness of the proposed method,the FCOS object detector is employed in the comparative experiments on the classical Pascal VOC and MS COCO datasets,respectively.Finally,the mAP of the detector on Pascal VOC dataset increases to 82.16%(an increase of 1.31%) and the AP50-95 on MS COCO dataset increases to 35.8% (an increase of 1.3%).

Key words: Ambiguous samples, Anchor Free, Center Ness, Object detection, Sample weight optimization

中图分类号: 

  • TP183
[1]CHEN K Q,ZHU Z L,DENG X M,et al.Deep Learning for Multi-Scale Object Detection:A survey[J].Journal of Software,2021,32(4):1201-1227.
[2]LI S P,LI C L,HAN J B,et al.Application of Binocular Vision Single Step Multi-target Detection Method for Robot Grasping[J].Journal of Chongqing Technology and Business University(Natural Science Edition),2021,38(5):68-74.
[3]XUAN D D,WANG J,WANG Z.Salient target detection based on high-level priori semantics [J].Journal of Chongqing University of Posts and Telecommunications(Natural Science Edition),2020,32(2):304-312.
[4]TIAN Z,SHEN C,CHEN H,et al.FCOS:Fully Convolutional One-Stage Object Detection [C]//Proceedings of the IEEE/CVF International Conference on Computer Vision.2019:9626-9635.
[5]DUAN K,BAI S,XIE L,et al.CenterNet:Keypoint Triplets for Object Detection [C]//Proceedings of the IEEE/CVF International Conference on Computer Vision.2019:6569-6578.
[6]CARION N,MASSA F,SYNNAEVE G,et al.End-to-End Object Detection with Transformers [C]//European Conference on Computer Vision.Cham:Springer,2020:213-229.
[7]ZHANG S,CHI C,YAO Y,et al.Bridging the Gap Between Anchor-Based and Anchor-Free Detection via Adaptive Training Sample Selection [C]//Proceedings of the IEEE/CVF Confe-rence on Computer Vision and Pattern Recognition.2020:9756-9765.
[8]LIN T Y,GOYAL P,GIRSHICK R,et al.Focal Loss for Dense Object Detection [C]//Proceedings of the IEEE International Conference on Computer Vision.2017:2999-3007.
[9]TIAN Z,SHEN C,CHEN H,et al.FCOS:A Simple and Strong Anchor-Free Object Detector[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2022,44(4):1922-1933.
[10]KONG T,SUN F,LIU H,et al.FoveaBox:Beyound Anchor-Based Object Detection [J].IEEE Transactions on Image Processing,2020,29:7389-7398.
[11]ZHU C,CHEN F,SHEN Z,et al.Soft Anchor-Point Object Detection[C]//European Conference on Computer Vision.Cham:Springer,2020:91-107.
[12]REDMON J,FARHADI A.YOLOv3:An Incremental Improvement [J].arXiv:1804.02767,2018.
[13]BOCHKOVSKIY A,WANG C Y,LIAO H Y M.YOLOv4:Optimal Speed and Accuracy of Object Detection [J].arXiv:2004.10934,2020.
[14]TAN M,PANG R,LE Q V.EfficientDet:Scalable and Efficient Object Detection [C]//Proceedings of the IEEE/CVFConfe-rence on Computer Vision and Pattern Recognition.2020:10778-10787.
[15]CAI Z,VASCONCELOS N.Cascade R-CNN:Delving Into High Quality Object Detection [C]//Proceedings of the IEEE Confe-rence on Computer Vision and Pattern Recognition.2018:6154-6162.
[16]HE K,GKIOXARI G,DOLLÁR P,et al.Mask R-CNN [C]//Proceedings of the IEEE International Conference on Computer Vision.2017:2980-2988.
[17]PANG J,CHEN K,SHI J,et al.Libra R-CNN:Towards Ba-lanced Learning for Object Detection [C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2019:821-830.
[18]LAW H,DENG J.CornerNet:Detecting Objects as Paired Keypoints [C]//Proceedings of the European Conference on Computer Vision(ECCV).2018:765-781.
[19]ZHANG Z,HE T,ZHANG H,et al.Bag of Freebies for Trai-ning Object Detection Neural Networks [J].arXiv:1902.04103,2019.
[20]LI H,WU Z,ZHU C,et al.Learning From Noisy Anchors for One-Stage Object Detection [C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2020:10585-10594.
[21]QIAN Q,CHEN L,LI H,et al.DR Loss:Improving Object Detection by Distributional Ranking [C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2020:12161-12169.
[22]REN S,HE K,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.
[23]YU J,JIANG Y,WANG Z,et al.UnitBox:An Advanced Object Detection Network [C]//Proceedings of the 24th ACM International Conference on Multimedia.2016:516-520.
[24]REZATOFIGHI H,TSOI N,GWAK J Y,et al.Generalized Intersection Over Union:A Metric and a Loss for Bounding Box Regression [C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2019:658-666.
[25]ZHENG Z,WANG P,LIU W,et al.Distance-IoU Loss:Faster and Better Learning for Bounding Box Regression [C]//Proceedings of the AAAI Conference on Artificial Intelligence.2020:12993-13000.
[26]LIU W,ANGUELOV D,ERHAN D,et al.SSD:Single ShotMultiBox Detector [C]//European Conference on Computer Vision.Cham:Springer,2016:21-37.
[27]HE K,ZHANG X,REN S,et al.Deep Residual Learning forImage Recognition [C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2016:770-778.
[28]XIE S,GIRSHICK R,DOLLÁR P,et al.Aggregated Residual Transformations for Deep Neural Networks [C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2017:1492-1500.
[29]TAN M,LE Q.EfficientNet:Rethinking Model Scaling for Convolutional Neural Networks [C]//International Conference on Machine Learning.PMLR,2019:6105-6114.
[30]LIN T Y,DOLLÁR P,GIRSHICK R,et al.Feature Pyramid Networks for Object Detection [C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2017:2117-2125.
[31]GHIASI G,LIN T Y,LE Q V.NAS-FPN:Learning Scalable Feature Pyramid Architecture for Object Detection [C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2019:7036-7045.
[1] 刘冬梅, 徐洋, 吴泽彬, 刘倩, 宋斌, 韦志辉.
基于边框距离度量的增量目标检测方法
Incremental Object Detection Method Based on Border Distance Measurement
计算机科学, 2022, 49(8): 136-142. https://doi.org/10.11896/jsjkx.220100132
[2] 祝文韬, 兰先超, 罗唤霖, 岳彬, 汪洋.
改进Faster R-CNN的光学遥感飞机目标检测
Remote Sensing Aircraft Target Detection Based on Improved Faster R-CNN
计算机科学, 2022, 49(6A): 378-383. https://doi.org/10.11896/jsjkx.210300121
[3] 马宾, 付永康, 王春鹏, 李健, 王玉立.
基于GDIoU损失函数的YOLOv4绝缘子高效定位算法
High Performance Insulators Location Scheme Based on YOLOv4 with GDIoU Loss Function
计算机科学, 2022, 49(6A): 412-417. https://doi.org/10.11896/jsjkx.210600089
[4] 陈永平, 朱建清, 谢懿, 吴含笑, 曾焕强.
基于外接圆半径差损失的实时安全帽检测算法
Real-time Helmet Detection Algorithm Based on Circumcircle Radius Difference Loss
计算机科学, 2022, 49(6A): 424-428. https://doi.org/10.11896/jsjkx.220100252
[5] 陈佳舟, 赵熠波, 徐阳辉, 马骥, 金灵枫, 秦绪佳.
三维城市场景中的小物体检测
Small Object Detection in 3D Urban Scenes
计算机科学, 2022, 49(6): 238-244. https://doi.org/10.11896/jsjkx.210400174
[6] 胡伏原, 万新军, 沈鸣飞, 徐江浪, 姚睿, 陶重犇.
深度卷积神经网络图像实例分割方法研究进展
Survey Progress on Image Instance Segmentation Methods of Deep Convolutional Neural Network
计算机科学, 2022, 49(5): 10-24. https://doi.org/10.11896/jsjkx.210200038
[7] 徐涛, 陈奕仁, 吕宗磊.
基于改进YOLOv3的机坪工作人员反光背心检测研究
Study on Reflective Vest Detection for Apron Workers Based on Improved YOLOv3 Algorithm
计算机科学, 2022, 49(4): 239-246. https://doi.org/10.11896/jsjkx.210200119
[8] 张侣, 周博文, 吴亮红.
基于改进卷积注意力模块与残差结构的SSD网络
SSD Network Based on Improved Convolutional Attention Module and Residual Structure
计算机科学, 2022, 49(3): 211-217. https://doi.org/10.11896/jsjkx.201200019
[9] 赫晓慧, 邱芳冰, 程淅杰, 田智慧, 周广胜.
基于边缘特征融合的高分影像建筑物目标检测
High-resolution Image Building Target Detection Based on Edge Feature Fusion
计算机科学, 2021, 48(9): 140-145. https://doi.org/10.11896/jsjkx.200800002
[10] 袁磊, 刘紫燕, 朱明成, 马珊珊, 陈霖周廷.
融合改进密集连接和分布排序损失的遥感图像检测
Improved YOLOv3 Remote Sensing Target Detection Based on Improved Dense Connection and Distributional Ranking Loss
计算机科学, 2021, 48(9): 168-173. https://doi.org/10.11896/jsjkx.200800001
[11] 龚浩田, 张萌.
基于关键点检测的无锚框轻量级目标检测算法
Lightweight Anchor-free Object Detection Algorithm Based on Keypoint Detection
计算机科学, 2021, 48(8): 106-110. https://doi.org/10.11896/jsjkx.200700161
[12] 李琳, 刘学亮, 赵烨, 纪平.
结合乐高滤波器和SSD的低光照图像融合检测方法
Low Light Image Fusion Detection Method Based on Lego Filter and SSD
计算机科学, 2021, 48(7): 213-218. https://doi.org/10.11896/jsjkx.200800127
[13] 辛元雪, 史朋飞, 薛瑞阳.
基于区域提取与改进 LBP 特征的运动目标检测
Moving Object Detection Based on Region Extraction and Improved LBP Features
计算机科学, 2021, 48(7): 233-237. https://doi.org/10.11896/jsjkx.200600131
[14] 张曼, 李杰, 朱新忠, 沈霁, 成昊天.
基于改进DCGAN算法的遥感数据集增广方法
Augmentation Technology of Remote Sensing Dataset Based on Improved DCGAN Algorithm
计算机科学, 2021, 48(6A): 80-84. https://doi.org/10.11896/jsjkx.200700185
[15] 潘明远, 宋慧慧, 张开华, 刘青山.
学习全局引导渐进特征聚合轻量级网络的显著性目标检测
Learning Global Guided Progressive Feature Aggregation Lightweight Network for Salient Object Detection
计算机科学, 2021, 48(6): 103-109. https://doi.org/10.11896/jsjkx.200600068
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市渝北区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发