计算机科学

计算机科学 ›› 2024, Vol. 51 ›› Issue (5): 125-133.doi: 10.11896/jsjkx.230300018

• 计算机图形学&多媒体 • 上一篇    下一篇

基于特征注意力提纯的显著性目标检测模型

白雪飞1, 申悟呈1, 王文剑1,2   

  1. 1 山西大学计算机与信息技术学院 太原 030006
    2 计算智能与中文信息处理教育部重点实验室(山西大学) 太原 030006
  • 收稿日期:2023-03-02 修回日期:2023-08-17 出版日期:2024-05-15 发布日期:2024-05-08
  • 通讯作者: 王文剑(wjwang@sxu.edu.cn)
  • 作者简介:(baixuefei@sxu.edu.cn)
  • 基金资助:
    国家自然科学基金(61703252,U21A20513,62076154,62276161);山西省重点研发项目(202102150401013);山西省回国留学人员科研资助项目(2022-008)

Salient Object Detection Based on Feature Attention Purification

BAI Xuefei1, SHEN Wucheng1, WANG Wenjian1,2   

  1. 1 School of Computer and Information Technology,Shanxi University,Taiyuan 030006,China
    2 Key Laboratory of Computational Intelligence and Chinese Information Processing of Ministry of Education(Shanxi University),Taiyuan 030006,China
  • Received:2023-03-02 Revised:2023-08-17 Online:2024-05-15 Published:2024-05-08
  • About author:BAI Xuefei,born in 1980,Ph.D,asso-ciate professor,is a member of CCF(No.22413M).Her main research interests include image processing and machine learning.
    WANG Wenjian,born in 1968,Ph.D,professor,is a member of CCF(No.16143D).Her main research interests include image processing,machine learning and computing intelligence.
  • Supported by:
    National Natural Science Foundation of China(61703252,U21A20513,62076154,62276161),Key Research and Development Program of Shanxi Province(202102150401013) and Research Project Supported by Shanxi Scholarship Council of China(2022-008).

PDF (PC)

36

摘要： 近年来,显著性目标检测技术取得了巨大进展,其中如何选择并有效集成多尺度特征扮演了重要角色。针对现有特征集成方法可能导致的信息冗余问题,提出了一种基于特征注意力提纯的显著性检测模型。首先,在解码器中采用一个全局特征注意力引导模块(GAGM)对带有语义信息的深层特征进行注意力机制处理,得到全局上下文信息;然后,通过全局引导流将其送入解码器各层进行监督训练;最后,利用多尺度特征融合模块(FAM)对编码器提取出的多尺度特征与全局上下文信息进行有效集成,并在网格状特征提纯模块(MFPM)中进行进一步细化,以生成清晰、完整的显著图。在5个公开数据集上进行实验,结果表明,所提模型优于现有的其他显著性检测方法,并且处理速度快,当处理 320 × 320 尺寸的图像时,能以 30 帧以上的速度运行。

关键词: 显著性目标检测, 注意力机制, 多尺度特征融合, 特征选择, 网格状特征提纯

Abstract: In recent years,salient object detection technology has made great progress,and how to select and effectively integrate multi-scale features plays an important role.Aiming at the information redundancy problem that may be caused by existing feature integration methods,a saliency detection model based on feature attention refinement is proposed.First,in the decoder,a global feature attention guidance module(GAGM) is used to process the deep features with semantic information through the attention mechanism to obtain global context information,and then these information is sent to each layer of the decoder for supervision through the global guidance flow train.The multi-scale features extracted by the encoder and the global context information are then effectively integrated using the multi-scale feature aggregation module(FAM),and further refined in the mesh feature purification module(MFPM) to generate clear and complete salient features.Experimental results on 5 public datasets demonstrate that the proposed model outperforms other existing saliency object detection methods.Besides,the processing speed of our approach is also very fast,it can run at a speed of more than 30 FPS when processing a 320 × 320 image.

Key words: Salient object detection, Attention mechanism, Multi-scale feature fusion, Feature selection, Mesh feature purification

中图分类号: 

  • TP391
[1]JIANG H,WANG J,YUAN Z,et al.Salient object detection:A discriminative regional feature integration approach[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.IEEE,2013:2083-2090.
[2]LI J,FU K,ZHAO S,et al.Spatiotemporal knowledge distil-lation for efficient estimation of aerial video saliency [J].IEEE Transactions on Image Processing,2019,29:1902-1914.
[3]GE S,LI J,YE Q,et al.Detecting masked faces in the wild with lle-cnns[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2017:2682-2690.
[4]LI X X,QIANG J,LIU W J,et al.Research on Traffic Object Detection Method in Fog Based on Dual Backbone Network[J].Journal of Chongqing Technology and Business University(Na-tural Science Edition),2023,40(4):25-34..
[5]GAO Y,WANG M,TAO D,et al.3-D object retrieval and re-cognition with hypergraph analysis [J].IEEE Transactions on Image Processing,2012,21(9):4290-4303.
[6]YAO Q,GONG X.Saliency guided self-attention network forweakly and semi-supervised semantic segmentation [J].IEEE Access,2020,8:14413-14423.
[7]CHENG M M,MITRA N J,HUANG X,et al.Global contrast based salient region detection [J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2014,37(3):569-582.
[8]JIANG Z,DAVIS L S.Submodular salient region detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.IEEE,2013:2043-2050.
[9]HE S,LAU R W,LIU W,et al.Supercnn:A superpixelwiseconvolutional neural network for salient object detection [J].International Journal of Computer Vision,2015,115:330-344.
[10]LI G,YU Y.Visual saliency based on multiscale deep features[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.IEEE,2015:5455-5463.
[11]HOU Q,CHENG M M,HU X,et al.Deeply supervised salient object detection with short connections[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.IEEE,2017:3203-3212.
[12]LIU N,HAN J.Dhsnet:Deep hierarchical saliency network for salient object detection[C]//Proceedings of the IEEE Confe-rence on Computer Vision and Pattern Recognition.IEEE,2016:678-686.
[13]ZHANG X,WANG T,QI J,et al.Progressive attention guided recurrent network for salient object detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.IEEE,2018:714-722.
[14]WU Z,SU L,HUANG Q.Cascaded partial decoder for fast and accurate salient object detection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.IEEE,2019:3907-3916.
[15]ZHAO T,WU X.Pyramid feature attention network for saliency detection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.IEEE,2019:3085-3094.
[16]ZHANG P,WANG D,LU H,et al.Amulet:Aggregating multi-level convolutional features for salient object detection[C]//Proceedings of the IEEE International Conference on Computer Vision.IEEE,2017:202-211.
[17]LIN T Y,DOLLÁR P,GIRSHICK R,et al.Feature pyramidnetworks for object detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.IEEE,2017:2117-2125.
[18]LIU J J,HOU Q,CHENG M M,et al.A simple pooling-based design for real-time salient object detection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.IEEE,2019:3917-3926.
[19]TAN M,PANG R,LE Q V.Efficientdet:Scalable and efficient object detection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.IEEE,2020:10781-10790.
[20]QIAO S,CHEN L C,YUILLE A.Detectors:Detecting objectswith recursive feature pyramid and switchable atrous convolution[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.IEEE,2021:10213-10224.
[21]LIU J J,HOU Q,LIU Z A,et al.Poolnet+:Exploring the potential of pooling for salient object detection [J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2022,45(1):887-904.
[22]ZEILER M D,FERGUS R.Visualizing and understanding con-volutional networks[C]//Computer Vision－ECCV 2014:13th European Conference,Zurich,Switzerland,Part I 13.Springer,2014:818-833.
[23]HU J,SHEN L,SUN G.Squeeze-and-excitation networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.IEEE,2018:7132-7141.
[24]CHEN L C,PAPANDREOU G,SCHROFF F,et al.Rethinking atrous convolution for semantic image segmentation [J].arXiv:1706.05587,2017.
[25]GE S,ZHAO S,LI C,et al.Low-resolution face recognition in the wild via selective knowledge distillation [J].IEEE Transactions on Image Processing,2018,28(4):2051-2062.
[26]ZHANG K,ZHANG C,LI S,et al.Student network learning via evolutionary knowledge distillation [J].IEEE Transactions on Circuits and Systems for Video Technology,2021,32(4):2251-2263.
[27]WANG Z,SIMONCELLI E P,BOVIK A C.Multiscale structu-ral similarity for image quality assessment[C]//The Thrity-Seventh Asilomar Conference on Signals,Systems & Computers,2003.IEEE,2003:1398-1402.
[28]WANG L,LU H,WANG Y,et al.Learning to detect salient objects with image-level supervision[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.IEEE,2017:136-145.
[29]YAN Q,XU L,SHI J,et al.Hierarchical saliency detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.IEEE,2013:1155-1162.
[30]LI Y,HOU X,KOCH C,et al.The secrets of salient object segmentation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.IEEE,2014:280-287.
[31]YANG C,ZHANG L,LU H,et al.Saliency detection via graph-based manifold ranking[C]//Proceedings of the IEEE Confe-rence on Computer Vision and Pattern Recognition.IEEE,2013:3166-3173.
[32]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.IEEE,2016:770-778.
[33]ZHANG M,LIU T,PIAO Y,et al.Auto-msfnet:Search multi-scale fusion network for salient object detection[C]//Procee-dings of the 29th ACM International Conference on Multimedia.Association for Computing Machinery.2021:667-676.
[34]WU Z,SU L,HUANG Q.Decomposition and completion network for salient object detection [J].IEEE Transactions onImage Processing,2021,30:6226-6239.
[35]LIU N,ZHANG N,WAN K,et al.Visual saliency transformer[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision.2021:4722-4732.
[36]ZHAO Z,XIA C,XIE C,et al.Complementary trilateral decoder for fast and accurate salient object detection[C]//Proceedings of the 29th ACM International Conference on Multimedia.Association for Computing Machinery,2021:4967-4975.
[37]PANG Y,ZHAO X,ZHANG L,et al.Multi-scale interactivenetwork for salient object detection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.IEEE,2020:9413-9422.
[38]WEI J,WANG S,HUANG Q.F3Net:fusion,feedback and focus for salient object detection[C]//Proceedings of the AAAI Conference on Artificial Intelligence.AAAI,2020:12321-12328.
[39]ZHAO X,PANG Y,ZHANG L,et al.Suppress and balance:Asimple gated network for salient object detection[C]//Computer Vision－ECCV 2020:16th European Conference,Glasgow,UK,Part II 16.Springer,2020:35-51.
[40]MOHAMMADI S,NOORI M,BAHRI A,et al.CAGNet:Content-aware guidance for salient object detection [J].Pattern Recognition,2020,103:107303.
[41]FANG X,ZHU J,SHAO X,et al.LC3Net:Ladder context correlation complementary network for salient object detection [J].Knowledge-Based Systems,2022,242:108372.
[42]QIN X,ZHANG Z,HUANG C,et al.Basnet:Boundary-awaresalient object detection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.IEEE,2019:7479-7489.
[43]ZHAO J X,LIU J J,FAN D P,et al.EGNet:Edge guidance network for salient object detection[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision.IEEE,2019:8779-8788.
[44]LIU N,HAN J,YANG M H.Picanet:Learning pixel-wise contextual attention for saliency detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.IEEE,2018:3089-3098.
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