Journal of Jilin University(Engineering and Technology Edition) ›› 2019, Vol. 49 ›› Issue (6): 2045-2050.doi: 10.13229/j.cnki.jdxbgxb20181057

Previous Articles     Next Articles

Similarity retention instance retrieval method

Hong-wei ZHAO1,2(),Peng WANG1,Li-li FAN1,Huang-shui HU3,Ping-ping LIU1()   

  1. 1. College of Computer Science and Technology，Jilin University，Changchun 130012，China
    2. State Key Laboratory of Applied Optics，Chinese Academy of Science，Changchun 130033，China
    3. School of Computer Science and Engineering，Changchun University of Technology，Changchun 130012，China
  • Received:2018-10-22 Online:2019-11-01 Published:2019-11-08
  • Contact: Ping-ping LIU E-mail:zhaohw@jlu.edu.cn;liupp@jlu.edu.cn

RICH HTML

 3   

PDF (PC)

129

Abstract:

Aiming at the network training of multi-input samples, a similarity retention instance retrieval method is proposed. Firstly, the input image features are extracted by the convolution structure in the depth network and pooled. Then, according to the benchmark order, the similarity relationship between the low correlation image and the query image is corrected, and the low correlation image contrast loss coefficient is obtained, and the loss value within the loss reference value is retained. The loss value is performed to maintain contrast loss training based on similarity. Finally, the post-training network is used to extract image features for instance-level image retrieval. The experimental results show that the loss comparison function based on similarity is feasible, and the method significantly improves the accuracy of instance-level image retrieval.

Key words: computer application, image retrieval, convolutional neural network(CNN), loss function, sorting learning, similarity retention

CLC Number: 

  • TP391

Fig.1

Overall flow chart for depth image retrievalwith similarity retention"

Fig.2

Schematic diagram of similarity retentioncontrast loss network"

Fig.3

Loss curves"

Fig.4

Select low correlation image"

Table 1

Pooling method selection"

池化方法 初始k 数据集
Oxford5k Paris6k
MAC 正无穷 54.93 66.06
SPoC 1 45.63 66.46
GeM 3 57.95 69.29

Fig.5

Curves comparison on the dataset"

Table 2

Post training phase effect"

网络主干 特征维度 后处理方法

Oxford5k

数据集

Paris6k

数据集
MAC GeM MAC Gem
AlexNet 256 - 54.93 57.95 66.18 68.19
PCA 58.21 66.15 67.61 71.78

Table 3

Comparison of experimental results"

方法 特征维度 数据集
Oxford5k Paris6k
文献[19] 1024 56.0 -
文献[19] 128 43.3 -
文献[20] 128 55.7 -
文献[21] 256 53.3 67.0
文献[13] 256 53.1 -
文献[22] 128 59.3 59.0
文献[23] 256 56.5 -
本文 256 66.15 71.78
1 王方石, 王坚, 李兵, 等 . 基于深度属性学习的交通标志检测[J]. 吉林大学学报：工学版, 2018, 48(1): 319-329.
1 Wang Fang-shi , Wang Jian , Li Bing , et al . Deep attribute learning based traffic sign detection[J]. Journal of Jilin University (Engineering and Technology Edition), 2018, 48(1): 319-329.
2 李琳辉，伦智梅，连静，等 . 基于卷积神经网络的道路车辆检测方法[J]. 吉林大学学报：工学版，2017，47(2):384-391.
2 Li Lin-hui , Zhi-mei Lun , Lian Jing , et al . Convolution neural network-based vehicle detection method[J]. Journal of Jilin University (Engineering and Technology Edition), 2017, 47(2): 384-391.
3 Wang Zhi-peng , Xiang Xuan-lu , Zhao Zhi-cheng , et al . Deep image retrieval: indicator and gram matrix weighting for aggregated convolutional features[C]∥2018 IEEE International Conference on Multimedia and Expo (ICME), San Diego, CA, USA， 2018: 1-6.
4 Xia Zhi-hua , Wang Xin-hui , Zhang Lian-gao , et al . A privacy-preserving and copy-deterrence content-based image retrieval scheme in cloud computing[J]. IEEE Transactions on Information Forensics & Security, 2016, 11(11): 2594-2608.
5 刘富, 宗宇轩, 康冰, 等 . 基于优化纹理特征的手背静脉识别系统[J]. 吉林大学学报：工学版, 2018, 48(6): 1844-1850.
5 Liu Fu , Zong Yu-xuan , Kang Bing , et al . Dorsal hand vein recognition system based on optimized texture features[J]. Journal of Jilin University (Engineering and Technology Edition), 2018, 48(6): 1844-1850.
6 Wang J , Song Y , Leung T , et al . Learning fine-grained image similarity with deep ranking[C]∥Computer Vision and Pattern Recognition, Columbus, OH, 2014: 1386-1393.
7 Hadsell R , Chopra S , LeCun Y . Dimensionality reduction by learning an invariant mapping[C]∥IEEE Computer Society Conference on Computer Vision and Pattern Recognition, New York, NY, USA, 2006: 1735-1742.
8 Radenovi? F , Tolias G , Chum O . Fine-tuning CNN image retrieval with no human annotation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2019, 41(7): 1655-1668.
9 Krizhevsky A , Sutskever I , Hinton G E . Imagenet classification with deep convolutional neural networks[J/OL]. [2018-10-10].https:∥iphysresearch.github.io/paper_summary/ImageNet%20Classification%20with%20Deep%20Convolutional%20Neural%20Networks.pdf.
10 Simonyan K , Zisserman A . Very deep convolutional networks for large-scale image recognition[J/OL].[2018-10-10]. https:∥.
11 He K , Zhang X , Ren S , et al . Deep residual learning for image recognition[C]∥IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA, 2016: 770-778.
12 Razavian A S , Sullivan J , Carlsson S , et al . Visual instance retrieval with deep convolutional networks[J]. ITE Transactions on Media Technology and Applications, 2016, 4(3): 251-258.
13 Babenko A , Lempitsky V . Aggregating deep convolutional features for image retrieval[J/OL].[2018-10-11].https:∥arxiv.org/pdf/ 1510.07493.pdf.
14 Luukka P , Lepp?lampi T . Similarity classifier with generalized mean applied to medical data[J]. Computers in Biology and Medicine, 2006, 36(9): 1026-1040.
15 Philbin J , Chum O , Isard M , et al . Lost in quantization: Improving particular object retrieval in large scale image databases[J/OL]. [2018-10-15].http:∥.
16 Kingma D P , Ba J l . Adam: a method for stochastic optimization[J/OL].[2018-10-11]. https:∥arxiv.org/pdf/ 1412.6980.pdf.
17 Donahue J , Jia Y , Vinyals O , et al . DeCAF: a deep convolutional activation feature for generic visual recognition[J]. International Conference on Machine Learning, 2013, 32: 647-655.
18 Philbin J , Chum O , Isard M , et al . Object retrieval with large vocabularies and fast spatial matching[C]∥2007 IEEE Conference on Computer Vision and Pattern Recognition, Minneapolis, MN, USA, 2007: 9738061.
19 Jégou H , Zisserman A . Triangulation embedding and democratic aggregation for image search[J/OL].[2018-10-09]. https:∥.
20 Babenko A , Slesarev A , Chigorin A , et al . Neural codes for image retrieval[J/OL].[2018-10-09]. https:∥arxiv.org/pdf/ 1404.1777.pdf.
21 Sharif R A , Sullivan J , Maki A , et al . A baseline for visual instance retrieval with deep convolutional networks[C]∥International Conference on Learning Representations, San Diego, CA, 2015:165765.
22 Ng J Y H , Yang F , Davis L S . Exploiting local features from deep networks for image retrieval[C]∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, Boston, MA, USA, 2015: 53-61.
23 Paulin M , Douze M , Harchaoui Z , et al . Local convolutional features with unsupervised training for image retrieval[C]∥Proceedings of the IEEE International Conference on Computer vision, Santiago, Chile, 2015: 91-99.
[1] Jun SHEN,Xiao ZHOU,Zu-qin JI. Implementation of service dynamic extended network and its node system model [J]. Journal of Jilin University(Engineering and Technology Edition), 2019, 49(6): 2058-2068.
[2] Xiang-jiu CHE,Hua-luo LIU,Qing-bin SHAO. Fabric defect recognition algorithm based onimproved Fast RCNN [J]. Journal of Jilin University(Engineering and Technology Edition), 2019, 49(6): 2038-2044.
[3] You ZHOU,Sen YANG,Da-lin LI,Chun-guo WU,Yan WANG,Kang-ping WANG. Acceleration platform for face detection and recognition based on field⁃programmable gate array [J]. Journal of Jilin University(Engineering and Technology Edition), 2019, 49(6): 2051-2057.
[4] Bing-hai ZHOU,Qiong WU. Balancing and optimization of robotic assemble lines withtool and space constraint [J]. Journal of Jilin University(Engineering and Technology Edition), 2019, 49(6): 2069-2075.
[5] Bin LI,Xu ZHOU,Fang MEI,Shuai-ning PAN. Location recommendation algorithm based on K-means and matrix factorization [J]. Journal of Jilin University(Engineering and Technology Edition), 2019, 49(5): 1653-1660.
[6] Yan-jun SUN,Xuan-jing SHEN,Hai-peng CHEN,Yong-zhe ZHAO. Recaptured image forensics algorithm based on local plane linear point [J]. Journal of Jilin University(Engineering and Technology Edition), 2019, 49(4): 1320-1328.
[7] Xiong-fei LI,Lu SONG,Xiao-li ZHANG. Remote sensing image fusion based on cooperative empirical wavelet transform [J]. Journal of Jilin University(Engineering and Technology Edition), 2019, 49(4): 1307-1319.
[8] Feng⁃wen ZHAI,Jian⁃wu DANG,Yang⁃ping WANG,Jing JIN,Wei⁃wei LUO. Extended contour⁃based fast affine invariant feature extracting [J]. Journal of Jilin University(Engineering and Technology Edition), 2019, 49(4): 1345-1356.
[9] Yuan-ning LIU,Shuai LIU,Xiao-dong ZHU,Guang HUO,Tong DING,Kuo ZHANG,Xue JIANG,Shu-jun GUO,Qi-xian ZHANG. Iris secondary recognition based on decision particle swarm optimization and stable texture [J]. Journal of Jilin University(Engineering and Technology Edition), 2019, 49(4): 1329-1338.
[10] Bin LI,Guo⁃jun SHEN,Geng SUN,Ting⁃ting ZHENG. Improved chicken swarm optimization algorithm [J]. Journal of Jilin University(Engineering and Technology Edition), 2019, 49(4): 1339-1344.
[11] Nan WANG,Jin⁃bao LI,Yong LIU,Yu⁃jie ZHANG,Ying⁃li ZHONG. TPR⁃TF： time⁃aware point of interest recommendation model based on tensor factorization [J]. Journal of Jilin University(Engineering and Technology Edition), 2019, 49(3): 920-933.
[12] LIU Fu,ZONG Yu-xuan,KANG Bing,ZHANG Yi-meng,LIN Cai-xia,ZHAO Hong-wei. Dorsal hand vein recognition system based on optimized texture features [J]. Journal of Jilin University(Engineering and Technology Edition), 2018, 48(6): 1844-1850.
[13] WANG Li-min,LIU Yang,SUN Ming-hui,LI Mei-hui. Ensemble of unrestricted K-dependence Bayesian classifiers based on Markov blanket [J]. Journal of Jilin University(Engineering and Technology Edition), 2018, 48(6): 1851-1858.
[14] JIN Shun-fu,WANG Bao-shuai,HAO Shan-shan,JIA Xiao-guang,HUO Zhan-qiang. Synchronous sleeping based energy saving strategy of reservation virtual machines in cloud data centers and its performance research [J]. Journal of Jilin University(Engineering and Technology Edition), 2018, 48(6): 1859-1866.
[15] ZHAO Dong,SUN Ming-yu,ZHU Jin-long,YU Fan-hua,LIU Guang-jie,CHEN Hui-ling. Improved moth-flame optimization method based on combination of particle swarm optimization and simplex method [J]. Journal of Jilin University(Engineering and Technology Edition), 2018, 48(6): 1867-1872.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
[1] Liu Qing-min，Wang Long-shan，Chen Xiang-wei，Li Guo-fa. Ball nut detection by machine vision[J]. 吉林大学学报(工学版), 2006, 36(04): 534 -538 .
[2] Yang Zhijun, Tian Di, Zhou Bin. Network monitor based on NDIS intermediate driver[J]. 吉林大学学报(工学版), 2006, 36(02): 224 -0226 .
[3] Li Hai-bo，Liu Li-hua，Liu Mei，Zheng Wei-tao. Structure and resistance temperature property of nano-sized Fe-Cu system[J]. 吉林大学学报(工学版), 2006, 36(04): 476 -479 .
[4] Qin Zheng-kun, Ma Chun-sheng, Li De-lu, Zhang Hai-ming, Zhang Da-ming, Liu Shi-yong . Effect of waveguide bending on transmission characteristics of
arrayed waveguide grating multiplexers[J]. 吉林大学学报(工学版), 2007, 37(02): 448 -0452 .
[5] Hu Xing-jun;Zhang Ying-chao;Li Sheng;Lin You-zhi;Wang Jia-xue;Yang Yong-bai . Numerical simulation of vehicle aerodynamic characteristics based on DRSM[J]. 吉林大学学报(工学版), 2008, 38(03): 504 -0507 .
[6] Wang Bo, Wei Wei-jie, Zhang Bin, Zhang Ming-wei . Support vector clustering based on rough set[J]. 吉林大学学报(工学版), 2007, 37(04): 851 -853 .
[7] Wu Yun-zhu, He Bao-qin, Fu Li-min . Influence of velocity on transient aerodynamic characteristics
of overtaking and overtaken vehicles
[J]. 吉林大学学报(工学版), 2007, 37(05): 1009 -1013 .
[8] Xu Guan, Su Jian, Chen Rong, Zhang Li-bin, Su Li-li . Error analysis of measurement model and calibration method for automobile caster[J]. 吉林大学学报(工学版), 2008, 38(01): 17 -020 .
[9] Cheng Jingyuan，Song Kezhu，Yang Junfeng. inglecable checking system for timelapse marine seismic data acquisition and recording system[J]. 吉林大学学报(工学版), 2006, 36(02): 237 -0241 .
[10] Liao Qing-bin, Li Shun-ming, Qin Xiao-pan . Comparison of feature extraction methods of vehicle vibration signal[J]. 吉林大学学报(工学版), 2007, 37(04): 910 -915 .
Copyright © Journal of Jilin University(Engineering and Technology Edition), All Rights Reserved.
Tel: +86-431-85095297　Fax: +86-431-85094074　E-mail: xbgxb@jlu.edu.cn
Powered by Beijing Magtech Co. Ltd