计算机科学 ›› 2020, Vol. 47 ›› Issue (11): 179-185.doi: 10.11896/jsjkx.190900008
温静, 李雨萌
WEN Jing, LI Yu-meng
摘要: 传统的显著性检测方法大多在单一的尺度上分辨感兴趣的目标和背景,无法有效地获取多分辨率下的局部细节信息,为此提出多尺度反卷积的深度学习网络模型。首先,在多尺度下对各层特征及各层对比特征进行反卷积,充分利用反卷积层中的卷积核对输入物体的形状进行重建,在多种分辨率特征图上利用反卷积网络来学习细节特征,减少信息的丢失,以此保持不同尺寸特征图的细节信息;然后,将各尺度下的反卷积特征进行融合,形成多层次局部信息;最后,与VGG16网络提取的全局信息融合后,计算各个像素的显著值,从而获得最终的显著性结果。实验结果表明,多尺度反卷积结构表现出较优的性能,与传统方法相比,可以相对增强突出物体与背景之间的对比,保持细节方面的特征;与最新深度学习的方法相比,可以检测出相对清晰准确的区域,一定程度上减少了信息的损失,还原出了更多的细节,能够有效地获取各种分辨率下的显著性目标,而且各反卷积层的独立性也显著提高了本文算法的运算速度。
中图分类号:
[1] ITTI L,KOCH C,NIEBUR E.A Model of Saliency-Based Visual Attention for Rapid Scene Analysis [J].IEEE Transactions on Pattern Analysis & Machine Intelligence,1998,20(11):1254-1259. [2] HOU X,ZHANG L.Saliency Detection:A Spectral ResidualApproach[C] //IEEE Conference on Computer Vision & Pattern Recognition.IEEE Computer Society,2007:1-8. [3] FU H,CAO X,TU Z.Cluster-Based Co-Saliency Detection[J].IEEE Transactions Image Processing,2013,22(10):3766-3778. [4] HORNUNG A,PRITCH Y,KRAHENBUHL P,et al.Saliency filters:Contrast based filtering for salient region detection[C]//IEEE Conference on Computer Vision & Pattern Recognition.IEEE Computer Society,2012:733-740. [5] WEI Y,WEN F,ZHU W,et al.Geodesic Saliency Using Background Priors[C]//European Conference on Computer Vision.Springer,Berlin,Heidelberg,2012:29-42. [6] YANG C,ZHANG L,LU H,et al.Saliency Detection viaGraph-Based Manifold Ranking[C]//IEEE Conference on Computer Vision & Pattern Recognition.2013:3166-3173. [7] ZHU W,LIANG S,WEI Y,et al.Saliency Optimization from Robust Background Detection[C]//IEEE Conference on Computer Vision & Pattern Recognition.IEEE Computer Society,2014:2814-2821. [8] WANG L,LU H,RUAN X,et al.Deep networks for saliencydetection via local estimation and global search[C]//IEEE Conference on Computer Vision and Pattern Recognition.IEEE Computer Society,2015:3183-3192. [9] LUO Z,MISHRA A,ACHKAR A,et al.Non-local Deep Features for Salient Object Detection[C]//IEEE Conference on Computer Vision and Pattern Recognition.IEEE Computer Society,2017:6593-6601. [10] ZHANG X,WANG T,QI J,LU H,et al.Progressive attention guided recurrent network for salient object detection[C]//IEEE Conf.Comput.Vis.Pattern Recognit,2018:714-722. [11] ZHANG L,DAI J,LU H,et al.A bi-directional message passing model for salient object detection[C]//IEEE Conf.Comput.Vis.Pattern Recognit.2018:1741-1750. [12] LIU J J,HOU Q,CHENG M M,et al.A Simple Pooling-Based Design for Real-Time Salient Object Detection[C]//Proceedings of International Conference on Computer Vision and Pattern Recognition.2019. [13] SIMONYAN K,ZISSERMAN A,et al.Very Deep Convolutional Networks for Large-Scale Image Recognition[C]//Proceedings of the International Conference on Learning Representations.2015. [14] LIU F,GLEICHER M,et al.Region Enhanced Scale-Invariant Saliency Detection[C]//Proceedings of the 2006 IEEE International Conference on Multimedia and Expo(ICME 2006).Toronto,Ontario,Canada.IEEE,2006:1477-1480. [15] ZEILER M,KRISHNAN D,TAYLOR W,et al.Deconvolutional net-works[C]//Computer Vision & Pattern Recognition.2010:2528-2535. [16] MUMFORD D,SHAH J,et al.Optimal approximations bypiecewise smooth functions and associated variational problems[J].Communica tion Pure & Applied Mathematics,1989,42(5):577-685. [17] ZHANG J,HUANG M,JIN X,et al.A Real-Time ChineseTraffic Sign Detection Algorithm Based on Modified YOLOv2[J].Algorithms,2017,10(4):127. [18] Abadi M,Barham P,et al.TensorFlow:a system for large-scale machine learning[C]//Usenix Symposium on Operating Systems Design and Implementation.2016:265-283. [19] KINGMA P,BA J.Adam:A Method for Stochastic Optimization[C]//Proceedings of the International Conference on Learning Representations.2015. [20] RADHAKRISHNA A,SHEILA H,Francisco E,et al.Frequency-tuned Salient Region Detection[C]//IEEE Conference on Computer Vision and Pattern Recognition.IEEE,2009. [21] BUSCHMAN T J,MILLER E K.Top-dow n versus bottom-up control of attention in the prefrontal and posterior parietal cortices[J].Science,2007,315(30):1860-1862. [22] ITTI L.Models of bottomup and top-down visual attention[D].California Institute of Technology,2000. [23] ITTI L,KOCH C.Computational modeling of visual attention[J].Nature Reviews Neuroscience,2001,2(3):194-203. [24] MIRPOUR K,ARCIZET F,ONG W S,et al.Been There,Seen That:A Neural Mechanism for Performing Efficient Visual Search[J].Journal of Neurophysiology,2009,102(6):3481-3491. [25] DENG T,LUO E Q,ZHANG Y S,et al.Selective Attention-Based Saliency of Traffic Images and Characteristics of Eye Movement[J].Journal of University of Electronic Science and Technology of China,2014,43(4):624-628. |
[1] | 徐涌鑫, 赵俊峰, 王亚沙, 谢冰, 杨恺. 时序知识图谱表示学习 Temporal Knowledge Graph Representation Learning 计算机科学, 2022, 49(9): 162-171. https://doi.org/10.11896/jsjkx.220500204 |
[2] | 饶志双, 贾真, 张凡, 李天瑞. 基于Key-Value关联记忆网络的知识图谱问答方法 Key-Value Relational Memory Networks for Question Answering over Knowledge Graph 计算机科学, 2022, 49(9): 202-207. https://doi.org/10.11896/jsjkx.220300277 |
[3] | 汤凌韬, 王迪, 张鲁飞, 刘盛云. 基于安全多方计算和差分隐私的联邦学习方案 Federated Learning Scheme Based on Secure Multi-party Computation and Differential Privacy 计算机科学, 2022, 49(9): 297-305. https://doi.org/10.11896/jsjkx.210800108 |
[4] | 孙奇, 吉根林, 张杰. 基于非局部注意力生成对抗网络的视频异常事件检测方法 Non-local Attention Based Generative Adversarial Network for Video Abnormal Event Detection 计算机科学, 2022, 49(8): 172-177. https://doi.org/10.11896/jsjkx.210600061 |
[5] | 王剑, 彭雨琦, 赵宇斐, 杨健. 基于深度学习的社交网络舆情信息抽取方法综述 Survey of Social Network Public Opinion Information Extraction Based on Deep Learning 计算机科学, 2022, 49(8): 279-293. https://doi.org/10.11896/jsjkx.220300099 |
[6] | 郝志荣, 陈龙, 黄嘉成. 面向文本分类的类别区分式通用对抗攻击方法 Class Discriminative Universal Adversarial Attack for Text Classification 计算机科学, 2022, 49(8): 323-329. https://doi.org/10.11896/jsjkx.220200077 |
[7] | 姜梦函, 李邵梅, 郑洪浩, 张建朋. 基于改进位置编码的谣言检测模型 Rumor Detection Model Based on Improved Position Embedding 计算机科学, 2022, 49(8): 330-335. https://doi.org/10.11896/jsjkx.210600046 |
[8] | 胡艳羽, 赵龙, 董祥军. 一种用于癌症分类的两阶段深度特征选择提取算法 Two-stage Deep Feature Selection Extraction Algorithm for Cancer Classification 计算机科学, 2022, 49(7): 73-78. https://doi.org/10.11896/jsjkx.210500092 |
[9] | 程成, 降爱莲. 基于多路径特征提取的实时语义分割方法 Real-time Semantic Segmentation Method Based on Multi-path Feature Extraction 计算机科学, 2022, 49(7): 120-126. https://doi.org/10.11896/jsjkx.210500157 |
[10] | 侯钰涛, 阿布都克力木·阿布力孜, 哈里旦木·阿布都克里木. 中文预训练模型研究进展 Advances in Chinese Pre-training Models 计算机科学, 2022, 49(7): 148-163. https://doi.org/10.11896/jsjkx.211200018 |
[11] | 周慧, 施皓晨, 屠要峰, 黄圣君. 基于主动采样的深度鲁棒神经网络学习 Robust Deep Neural Network Learning Based on Active Sampling 计算机科学, 2022, 49(7): 164-169. https://doi.org/10.11896/jsjkx.210600044 |
[12] | 苏丹宁, 曹桂涛, 王燕楠, 王宏, 任赫. 小样本雷达辐射源识别的深度学习方法综述 Survey of Deep Learning for Radar Emitter Identification Based on Small Sample 计算机科学, 2022, 49(7): 226-235. https://doi.org/10.11896/jsjkx.210600138 |
[13] | 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 |
[14] | 王建明, 陈响育, 杨自忠, 史晨阳, 张宇航, 钱正坤. 不同数据增强方法对模型识别精度的影响 Influence of Different Data Augmentation Methods on Model Recognition Accuracy 计算机科学, 2022, 49(6A): 418-423. https://doi.org/10.11896/jsjkx.210700210 |
[15] | 毛典辉, 黄晖煜, 赵爽. 符合监管合规性的自动合成新闻检测方法研究 Study on Automatic Synthetic News Detection Method Complying with Regulatory Compliance 计算机科学, 2022, 49(6A): 523-530. https://doi.org/10.11896/jsjkx.210300083 |
|