2.765

2022影响因子

(CJCR)

  • 中文核心
  • EI
  • 中国科技核心
  • Scopus
  • CSCD
  • 英国科学文摘

留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

基于点对相似度的深度非松弛哈希算法

汪海龙 禹晶 肖创柏

汪海龙, 禹晶, 肖创柏. 基于点对相似度的深度非松弛哈希算法.自动化学报, 2021, 47(5): 1077-1086 doi: 10.16383/j.aas.c180571
引用本文: 汪海龙, 禹晶, 肖创柏. 基于点对相似度的深度非松弛哈希算法.自动化学报, 2021, 47(5): 1077-1086 doi: 10.16383/j.aas.c180571
Wang Hai-Long, Yu Jing, Xiao Chuang-Bai. Deep non-relaxing hashing based on point pair similarity. Acta Automatica Sinica, 2021, 47(5): 1077-1086 doi: 10.16383/j.aas.c180571
Citation: Wang Hai-Long, Yu Jing, Xiao Chuang-Bai. Deep non-relaxing hashing based on point pair similarity. Acta Automatica Sinica, 2021, 47(5): 1077-1086 doi: 10.16383/j.aas.c180571

基于点对相似度的深度非松弛哈希算法

doi: 10.16383/j.aas.c180571
基金项目: 

北京市教育委员会科技计划 KM201910005029

北京市自然科学基金 4212014

详细信息
    作者简介:

    汪海龙  北京工业大学信息学部硕士研究生. 主要研究方向为图像处理与机器学习. E-mail: 18810815820@163.com

    禹晶  北京工业大学信息学部副教授. 2011年获清华大学电子工程系博士学位. 主要研究方向为图像处理与模式识别. E-mail: jing.yu@bjut.edu.cn

    通讯作者:

    肖创柏  北京工业大学信息学部教授. 主要研究方向为数字信号处理, 音视频信号处理与网络通信. 本文通信作者. E-mail: cbxiao@bjut.edu.cn

Deep Non-relaxing Hashing Based on Point Pair Similarity

Funds: 

Scientific Research Common Program of Beijing Municipal Commission of Education KM201910005029

Beijing Municipal Natural Science Foundation 4212014

More Information
    Author Bio:

    WANG Hai-Long  Master student at the Faculty of Information Technology, Beijing University of Technology. His research interest covers image processing and machine learning

    YU Jing  Associate professor at the Faculty of Information Technology, Beijing University of Technology. She received her Ph. D. degree from Tsinghua University in 2011. Her research interest covers image processing and pattern recognition

    Corresponding author: XIAO Chuang-Bai  Professor at the Faculty of Information Technology, Beijing University of Technology. His research interest covers digital signal processing, audio and video signal processing, and network communication. Corresponding author of this paper
  • 摘要: 哈希学习能够在保持数据之间语义相似性的同时, 将高维数据投影到低维的二值空间中以降低数据维度实现快速检索. 传统的监督型哈希学习算法主要是将手工设计特征作为模型输入, 通过分类和量化生成哈希码. 手工设计特征缺乏自适应性且独立于量化过程使得检索的准确率不高. 本文提出了一种基于点对相似度的深度非松弛哈希算法, 在卷积神经网络的输出端使用可导的软阈值函数代替常用的符号函数使准哈希码非线性接近-1或1, 将网络输出的结果直接用于计算训练误差, 在损失函数中使用$\ell_1$范数约束准哈希码的各个哈希位接近二值编码. 模型训练完成之后, 在网络模型外部使用符号函数, 通过符号函数量化生成低维的二值哈希码, 在低维的二值空间中进行数据的存储与检索. 在公开数据集上的实验表明, 本文的算法能够有效地提取图像特征并准确地生成二值哈希码, 且在准确率上优于其他算法.
    Recommended by Associate Editor ZHANG Min-Ling
    1)  本文责任编委 张敏灵
  • 图  1  ${\rm soft}\left({ x} \right) $的函数曲线

    Fig.  1  The function curve of the ${\rm soft}\left({ x} \right)$

    图  2  本文算法使用的网络模型

    Fig.  2  The network model of our algorithm

    图  3  不同正则项系数$\lambda$下准哈希码的分布

    Fig.  3  The distribution of hash code with different regularization coefficient $\lambda$

    图  4  参数$\eta$取不同值时准哈希码的分布

    Fig.  4  The distribution of hash code with different $\eta$

    表  1  各种算法在CIFAR-10上的MAP

    Table  1  The MAP of different algorithms on CIFAR-10

    算法12 bit24 bit32 bit48 bit
    DNRH0.7260.7490.7530.768
    DPSH0.7130.7270.7440.757
    DSH0.6160.6510.6610.676
    DHN0.5550.5940.6030.621
    FP-CNNH0.6120.6390.6250.616
    NINH0.5520.5660.5580.581
    CNNH0.4390.5110.5090.532
    SDH0.2850.3290.3410.356
    KSH0.3160.3900.4120.458
    MLH0.1820.1950.2070.211
    BRE0.1590.1810.1930.196
    ITQ0.1620.1690.1720.175
    SH0.1270.1280.1260.129
    下载: 导出CSV

    表  2  各种算法在NUS-WIDE上的MAP

    Table  2  The MAP of different algorithms on NUS-WIDE

    算法12 bit24 bit32 bit48 bit
    DNRH0.7690.7920.8040.814
    DPSH0.7470.7880.7920.806
    DSH0.5480.5510.5580.562
    DHN0.7080.7350.7480.758
    FP-CNNH0.6220.6280.6310.625
    NINH0.6740.6970.7130.715
    CNNH0.6180.6210.6190.620
    SDH0.5680.6000.6080.637
    KSH0.5560.5720.5810.588
    MLH0.5000.5140.5200.522
    BRE0.4850.5250.5300.544
    ITQ0.4520.4680.4720.477
    SH0.4540.4060.4050.400
    下载: 导出CSV

    表  3  $\ell_1$范数和软阈值函数约束在CIFAR-10上的MAP

    Table  3  The MAP of $\ell_1$-norm and soft threshold function constraint on CIFAR-10

    算法12 bit24 bit36 bit48 bit
    交叉熵$+~\ell_1$范数+软阈值0.7260.7490.7530.768
    DPSH0.7130.7270.7440.757
    交叉熵+软阈值0.6130.6360.6620.688
    交叉熵$+~\ell_1$范数0.6060.6210.6600.671
    下载: 导出CSV

    表  4  $\lambda$的不同取值对应的MAP

    Table  4  The MAP on different $\lambda$

    $\lambda$CIFAR-10数据集NUS-WIDE数据集
    00.6350.661
    0.010.7200.773
    0.050.7680.814
    0.10.7420.756
    0.50.6950.680
    下载: 导出CSV
  • [1] 李武军, 周志华. 大数据哈希学习: 现状与趋势. 科学通报, 2015, 60(5-6): 485-490 https://www.cnki.com.cn/Article/CJFDTOTAL-KXTB2015Z1011.htm

    Li Wu-Jun, Zhou Zhi-Hua. Learning to hash for big data: current status and future trends. Chinese Science Bulletin, 2015, 60(5-6): 485-490 https://www.cnki.com.cn/Article/CJFDTOTAL-KXTB2015Z1011.htm
    [2] Raginsky M, Lazebnik S. Locality-sensitive binary codes from shift-invariant kernels. In: Proceedings of the 2009 Neural Information Processing Systems. Vancouver, BC, Canada: Curran Associates, Inc, 2009. 1509-1517
    [3] Indyk P, Motwani R. Approximate nearest neighbor: towards removing the curse of dimensionality. In: Proceedings of the 30th Annual ACM Symposium on Theory of Computing. New York, NY, USA: ACM, 1998. 604-613
    [4] Datar M, Immorlica N, Indyk P, Mirrokni V. Locality-sensitive hashing scheme based on p-stable distributions. In: Proceedings of the 20th Annual Symposium on Computational Geometry. New York, NY, USA: ACM, 2004. 253-262
    [5] Kulis B, Grauman K. Kernelized locality-sensitive hashing. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 34(6): 1092-1104 doi: 10.1109/TPAMI.2011.219
    [6] Weiss Y, Torralba A, Fergus R. Spectral hashing. In: Proceedings of the 22nd Annual Conference on Neural Information Processing Systems. British Columbia, Canada: MIT, 2008. 1753-1760
    [7] Wold S, Esbensen K, Geladi P. Principal component analysis. Chemometrics Intelligent Laboratory Systems, 1987, 2(13): 37-52 http://www.stat.columbia.edu/~fwood/Teaching/w4315/Fall2009/pca.pdf
    [8] Gong Y, Lazebnik S. Iterative quantization: a procrustean approach to learning binary codes. In: Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition. Colorado, USA: IEEE, 2011. 817-824
    [9] Norouzi M, Fleet D. Minimal loss hashing for compact binary codes. In: Proceedings of the 2011 International Conference on Machine Learning. Bellevue, Washington, USA: Omnipress, 2011. 353-360
    [10] Liu W, Wang J, Ji R, Jiang Y, Chang S. Supervised hashing with kernels. In: Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition. Providence, Rhode Island, USA: IEEE, 2012. 2074-2081
    [11] Shen F, Shen C, Liu W, Shen H. Supervised discrete hashing. In: Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition. Boston, USA: IEEE, 2015. 37-45
    [12] Alex K, Ilya S, Geoffrey E. ImageNet Classification with deep convolutional neural networks. In: Proceedings of the 25th International Conference on Neural Information Processing. USA: Curran Associates Inc, 2012. 1097-1105
    [13] Zhao F, Huang Y, Wang L, Tan T. Deep semantic ranking based hashing for multi-label image retrieval. In: Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition. Boston, MA, USA: IEEE, 2015. 1556-1564
    [14] 罗建豪, 吴建鑫. 基于深度卷积特征的细粒度图像分类研究综述. 自动化学报, 2017, 43(8): 1306-1318 doi: 10.16383/j.aas.2017.c160425

    Luo Jian-Hao, Wu Jian-Xin. A survey on fine-grained image categorization using deep convolutional features. Acta Automatica Sinica, 2017, 43(8): 1306-1318 doi: 10.16383/j.aas.2017.c160425
    [15] 张慧, 王坤峰, 王飞跃. 深度学习在目标视觉检测中的应用进展与展望. 自动化学报, 2017, 43(8): 1289-1305 doi: 10.16383/j.aas.2017.c160822

    Zhang Hui, Wang Kun-Feng, Wang Fei-Yue. Advances and perspectives on applications of deep learning invisual object detection. Acta Automatica Sinica, 2017, 43(8): 1289-1305 doi: 10.16383/j.aas.2017.c160822
    [16] 尹宏鹏, 陈波, 柴毅, 刘兆栋. 基于视觉的目标检测与跟踪综述. 自动化学报, 2016, 42(10): 1466-1489 doi: 10.16383/j.aas.2016.c150823

    Yin Hong-Peng, Chen Bo, Chai Yi, Liu Zhao-Dong. Vision-based object detection and tracking: a review. Acta Automatica Sinica, 2016, 42(10): 1466-1489 doi: 10.16383/j.aas.2016.c150823
    [17] Xia R, Pan Y, Lai H, Liu C, Yan S. Supervised hashing for image retrieval via image representation learning. In: Proceedings of the 28th AAAI Conference on Artificial Intelligence. CA: AAAI, 2014. 2156-2162
    [18] Liu H, Wang R, Shan S, Chen X. Deep supervised hashing for fast image retrieval. In: Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. New York, USA: IEEE, 2016. 2064-2072
    [19] Li W, Wang S, Kang W. Feature learning based deep supervised hashing with pairwise labels. In: Proceedings of the 25th International Joint Conference on Artificial Intelligence. New York, USA: AAAI Press, 2016. 1711-1717
    [20] Cao Z, Long M, Wang J, Philip S. HashNet: deep learning to hash by continuation. In: Proceedings of the 2017 International Conference on Computer Vision. Venice, Italy: IEEE, 2017. 5609-5618
    [21] Zhang P, Zhang W, Li W, Guo M. Supervised hashing with latent factor models. In: Proceedings ofthe 37th international ACM SIGIR conference on Research and development in information retrieval. New York, NY, USA: ACM, 2014. 173-182
    [22] Kulis B, Darrell T. Learning to hash with binary reconstructive embeddings. In: Proceedings of the 2009 Advances in Neural Information Processing Systems. USA: Curran Associates Inc, 2009, 22: 1042-1050
    [23] 刘冶, 潘炎, 夏榕楷, 刘荻, 印鉴. FP-CNNH: 一种基于深度卷积神经网络的快速图像哈希算法. 计算机科学, 2016, 43(9): 39-46 https://www.cnki.com.cn/Article/CJFDTOTAL-JSJA201609008.htm

    Liu Ye, Pan Yan, Xia Rong-Kai, Liu Di, Yin Jian. FP-CNNH: A fast image hashing algorithm based on deep convolutional neural network. Computer Science, 2016, 43(9): 39-46 https://www.cnki.com.cn/Article/CJFDTOTAL-JSJA201609008.htm
    [24] Lai H, Pan Y, Liu Y, Yan S. Simultaneous feature learning and hash coding with deep neural networks. In: Proceedings of the 2015 International Conference on Computer Vision and Pattern Recognition. Boston, MA, USA: IEEE, 2015. 3270-3278
    [25] Zhu H, Long M, Wang J, Cao Y. Deep hashing network for efficient similarity retrieval. In: Proceedings of the 30th AAAI Conference on Artificial Intelligence. Phoenix, Arizona: AAAI Press, 2016. 2415-2421
    [26] Abouelnaga Y, Ali O, Rady H, Moustafa M. CIFAR-10: KNN-Based ensemble of classifiers. In: Proceedings of the 2016 International Conference on Computational Science and Computational Intelligence. Las Vegas, NV, USA: IEEE, 2016. 1192-1195
    [27] Chua T, Tang J, Hong R, Li H, Luo Z, Zheng Y. NUS-WIDE: A real-world web image database from National University of Singapore. In: Proceedings of the 2009 ACM International Conference on Image and Video Retrieval. New York, NY, USA: ACM, 2009. 368-375
    [28] 姚涛, 孔祥维, 付海燕, Tian Qi. 基于映射字典学习的跨模态哈希检索. 自动化学报, 2018, 44(8): 1475-1485 doi: 10.16383/j.aas.2017.c160433

    Yao Tao, Kong Xiang-Wei, Fu Hai-Yan, Tian Qi. Projective dictionary learning hashing for cross-modal retrieval. Acta Automatica Sinica, 2018, 44(8): 1475-1485 doi: 10.16383/j.aas.2017.c160433
  • 加载中
图(4) / 表(4)
计量
  • 文章访问数:  1130
  • HTML全文浏览量:  194
  • PDF下载量:  146
  • 被引次数: 0
出版历程
  • 收稿日期:  2018-08-27
  • 录用日期:  2019-02-03
  • 刊出日期:  2021-05-21

目录

    /

    返回文章
    返回