2022年 02期

基于正态分布的距离保持哈希图像检索方法

Distance-keeping Hashing Image Retrieval Method Based on Normal Distribution


摘要(Abstract):

针对图像检索任务中部分监督学习部署困难,以及一般无监督学习没有利用监督信息导致检索性能劣化的问题,提出一种基于正态分布的距离保持哈希的无监督框架,使生成的哈希码保持图像的原始距离关系,在检索结果中尽可能保留相似的图像;距离保持哈希使用正态分布框架约束生成的连续码保持原始特征的距离关系,将图像的语义信息尽可能保留到哈希码中,并使用标准化欧氏距离进行特征向量的相似度计算,解决直接使用传统欧氏距离作为损失时神经网络梯度下降产生的网络波动问题。实验结果表明,与其他模型相比,距离保持哈希在大规模图像检索中检索性能更好。

关键词(KeyWords): 图像检索;距离保持哈希;正态分布;语义信息;标准化欧氏距离

基金项目(Foundation):国家自然科学基金项目(61841602);; 山东省自然科学基金项目(ZR2018PF005)

作者(Author): 闫冰琦,田爱奎,吴楠楠,孙妍,王振

DOI: 10.13349/j.cnki.jdxbn.20211025.001

参考文献(References):

[1] ANDONI A,INDYK P.Near-optimal hashing algorithms for approximate nearest neighbor in high dimensions[C]//2006 47th Annual IEEE Symposium on Foundations of Computer Science (FOCS’06),October 21-24,2006,Berkeley,USA.New York:IEEE,2006:459-468.

[2] WEISS Y,TORRALBA A,FERGUS R.Spectral hashing[C]//NIPS’08:Proceedings of the 21st International Conference on Neural Information Processing Systems,December 8,2008,Vancouver,Canada.New York:ACM,2008:1753-1760.

[3] GONG Y C,LAZEBNIK S,GORDO A,et al.Iterative quantization:a procrustean approach to learning binary codes[C]//2011 IEEE Conference on Computer Vision and Pattern Recognition,June 20-25,2011,Colorado Springs,USA.New York:IEEE,2011:2916-2929.

[4] HE K M,WEN F,SUN J.K-means hashing:an affinity-preserving quantization method for learning binary compact codes [C]//2013 IEEE Conference on Computer Vision and Pattern Recognition,June 23-28,2013,Portland,USA.New York:IEEE,2013:2938-2945.

[5] XIA R K,PAN Y,LAI H J,et al.Supervised hashing for image retrieval via image representation learning[C]// Proceedings of the Twenty-eighth AAAI Conference on Artificial Intelligence,July 27-31,2014,Québec City,Canada.Palo Alto:AAAI Press,2014:2156-2162.

[6] LAI H J,PAN Y,LIU Y,et al.Simultaneous feature learning and hash coding with deep neural networks[C]//2015 IEEE Conference on Computer Vision and Pattern Recognition(CVPR),June 7-12,2015,Boston,USA.New York:IEEE,2015:3270-3278.

[7] ZHAO F,HUANG Y Z,WANG L,et al.Deep semantic ranking based hashing for multi-label image retrieval[C]//2015 IEEE Conference on Computer Vision and Pattern Recognition,June 7-12,2015,Boston,USA.New York:IEEE,2015:1556-1564.

[8] LIU H M,WANG R P,SHAN S G,et al.Deep supervised hashing for fast image retrieval[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition,June 27-30,2016,Las Vegas,USA.New York:IEEE,2016:2064-2072.

[9] WANG R K,WANG R P,QIAO S S,et al.Deep position-aware hashing for semantic continuous image retrieval[C]//IEEE Winter Conference on Applications of Computer Vision,March 1-5,2020,Snowmass,USA.New York:IEEE,2020:2493-2502.

[10] HONG W X,CHANG Y T,QIN H F,et al.Image hashing via linear discriminant learning[C]//IEEE Winter Conference on Applications of Computer Vision,March 1-5,2020,Snowmass,USA.New York:IEEE,2020:2531-2539.

[11] KANG R,CAO Y,LONG M S,et al.Maximum-margin Hamming hashing[C]//2019 IEEE/CVF International Conference on Computer Vision(ICCV),October 27-November 2,2019,Seoul,Korea.New York:IEEE,2019:8251-8260.

[12] DIZAJI K G,ZHENG F,NOURABADI N S,et al.Unsupervised deep generative adversarial hashing network[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition,June 18-23,2018,Salt Lake City,USA.New York:IEEE,2018:3664-3673.

[13] YANG E K,LIU T L,DENG C,et al.Distill hash:unsupervised deep hashing by distilling data pairs[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR),June 15-20,2019,Long Beach,USA.New York:IEEE,2019:2946-2955.

[14] DAI B,GUO R Q,KUMAR S,et al.Stochastic generative hash-ing[C]//Proceedings of the 34th International Conference on Machine Learning,August 6-11,2017,Sydney,Australia.[S.l.]:International Machine Learning Society,2017:913-922.

[15] ZIEBA M,SEMBERECKI P,EL-GAALY T,et al.BinGAN:learning compact binary descriptors with a regularized GAN[C]//Proceedings of the 32nd International Conference on Neural Information Processing Systems,December 3-8,2018,Montréal,Canada.Red Hook:Curran Associates Inc.,2018:3612-3622.

[16] SHEN Y M,LIU L,SHAO L.Unsupervised binary representation learning with deep variational networks[J]//International Journal of Computer Vision,2019,127:1614-1628.

[17] CAO Y,LIU B,LONG M S,et al.HashGAN:deep learning to hash with pair conditional Wasserstein GAN[C]// 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition,June 18-23,2018,Salt Lake City,USA.New York:IEEE,2018:1287-1296.

[18] CAO Y,LONG M S,LIU B,et al.Deep Cauchy hashing for Hamming space retrieval[C]// 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition,June 18-23,2018,Salt Lake City,USA.New York:IEEE,2018:1229-1237.

[19] LI W J,WANG S,KANG W C.Feature learning based deep supervised hashing with pairwise labels[C]//KAMBHAMPATI S.Proceedings of the Twenty-fifth International Joint Conference on Artificial Intelligence(IJCAI-16),July 9-15,2016,New York,USA.Palo Alto:AAAI Press,2016:1711-1717.

[20] ZHU H,LONG M S,WANG J M,et al.Deep hashing network for efficient similarity retrieval[C]//SCHUURMANS D,WELLMAN M P.Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence,February 12-17,2016,Phoenix,USA.Palo Alto:AAAI Press,2016:2415-2421.

[21] SHEN Y M,QIN J,CHEN J X,et al.Auto-encoding twin-bottleneck hashing[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR),June 13-19 2020,Seattle,USA.New York:IEEE,2020:2818-2827.

[22] CAO Z J,LONG M S,WANG J M,et al.HashNet:deep learning to hash by continuation[C]//2017 IEEE International Conference on Computer Vision,October 22-29,2017,Venice,Italy.New York:IEEE,2017:5608-5617.

[23] SONG J K.Binary generative adversarial networks for image retrieval[C]//Proceedings of ACM Conference(Conference’17),July 2017,Washington,USA.New York:ACM,2017:394-401.