Abstract It is difficult to obtain high-quality hash codes for unsupervised deep hashing methods due to the lack of similarity supervised information. Therefore, an end-to-end deep unsupervised hashing model based on pseudo-pairwise labels is proposed. Statistical analysis is performed on the image features extracted by the pre-trained deep convolutional neural network to construct the semantic similarity labels for data. Supervised deep hashing based on pairwise labels is then conducted. Experiments on commonly used image datasets CIFAR-10 and NUS-WIDE indicate that hash codes obtained by the proposed method perform better on image retrieval.
[1] BELLMAN R. Dynamic Programming. Science, 1966, 153(3731): 34-37. [2] WANG B, LI Z W, LI M J, et al. Large-Scale Duplicate Detection for Web Image Search // Proc of the IEEE International Conference on Multimedia and Expo. Washington, USA: IEEE, 2006: 353-356. [3] BERLIN K, KOREN S, CHIN C S, et al. Assembling Large Genomes with Single-Molecule Sequencing and Locality-Sensitive Ha-shing. Nature Biotechnology, 2015, 33(6): 623-630. [4] GIONIS A, INDYK P, MOTWANI R, et al. Similarity Search in High Dimensions via Hashing // Proc of the 25th International Conference on Very Large Data Bases. Cambridge, USA: Morgan Kaufmann Publishers, 1999: 518-529. [5] LOWE D G. Object Recognition from Local Scale-Invariant Features // Proc of the 7th IEEE International Conference on Computer Vision. Washington, USA: IEEE, 1999: 1150-1157. [6] OLIVA A, TORRALBA A. Modeling the Shape of the Scene: A Holistic Representation of the Spatial Envelope. International Journal of Computer Vision, 2001, 42(3): 145-175. [7] LIU W, WANG J, JI R R, et al. Supervised Hashing with Kernels // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2012: 2074-2081. [8] LIN G, SHEN C, SHI Q, et al. Fast Supervised Hashing with Decision Trees for High-Dimensional Data // Proc of the IEEE Confe-rence on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2014: 1971-1978. [9] SHEN F M, SHEN C H, LIU W, et al. Supervised Discrete Ha-shing // Proc of the IEEE Conference on Computer Vision and Pa-ttern Recognition. Washington, USA: IEEE, 2015: 37-45. [10] KRIZHEVSKY A, SUTSKEVER I, HINTON G E. ImageNet Classi-fication with Deep Convolutional Neural Networks // PEREIRA F, BURGES C J C, BOTTOU L, et al., eds. Advances in Neural Information Processing Systems 25. Cambridge, USA: The MIT Press, 2012: 1097-1105. [11] LECUN Y, BENGIO Y, HINTON G. Deep Learning. Nature, 2015, 521(7553): 436-444. [12] XIA R, PAN Y, LAI H J, et al. Supervised Hashing for Image Retrieval via Image Representation Learning // Proc of the 28th AAAI Conference on Artificial Intelligence. Palo Alto, USA: AAAI Press, 2014: 2156-2162. [13] LAI H J, PAN Y, LIU Y, et al. Simultaneous Feature Learning and Hash Coding with Deep Neural Networks // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2015: 3270-3278. [14] LI W J, WANG S, KANG W C. Feature Learning Based Deep Supervised Hashing with Pairwise Labels // Proc of the 25th International Joint Conference on Artificial Intelligence. Palo Alto, USA: AAAI Press, 2016: 1711-1717. [15] LI Q, SUN Z N, HE R, et al. Deep Supervised Discrete Hashing[C/OL]. [2019-11-15]. http://papers.nips.cc/paper/6842-deep-supervised-discrete-hashing.pdf. [16] WEISS Y, TORRALBA A, FERGUS R. Spectral Hashing // KO-LLER D, SCHUURMANS D, BENGIO Y, et al., eds. Advances in Neural Information Processing Systems 21. Cambridge, USA: The MIT Press, 2008: 1753-1760. [17] GONG Y C, LAZEBNIK S. Iterative Quantization: A Procrustean Approach to Learning Binary Codes // Proc of the IEEE Confe-rence on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2011: 817-824 [18] HEO J P, LEE Y, HE J F, et al. Spherical Hashing // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2012: 2957-2964. [19] LIN K, LU J W, CHEN C S, et al. Learning Compact Binary Descriptors with Unsupervised Deep Neural Networks // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2016: 1183-1192. [20] DAI B, GUO R Q, KUMAR S, et al. Stochastic Generative Ha-shing[C/OL]. [2019-11-15]. http://proceedings.mlr.press/v70/dai17a/dai17a.pdf. [21] YANG E, DENG C, LIU T L, et al. Semantic Structure-Based Unsupervised Deep Hashing // Proc of the 27th International Joint Conference on Artificial Intelligence. Palo Alto, USA: AAAI Press, 2018: 1064-1070. [22] SIMONYAN K, ZISSERMAN A. Very Deep Convolutional Networks for Large-Scale Image Recognition[C/OL]. [2019-11-15].http://arxiv.org/abs/1409.1556. [23] RUSSAKOVSKY O, DENG J, SU H, et al. ImageNet Large Scale Visual Recognition Challenge. International Journal of Computer Vision, 2015, 115(3): 211-252. [24] SMEULDERS A W M, WORRING M, SANTINI S, et al. Content-Based Image Retrieval at the End of the Early Years. IEEE Tran-sactions on Pattern Analysis and Machine Intelligence, 2000, 22(12): 1349-1380. [25] GIRSHICK R, DONAHUE J, DARRELL T, et al. Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2014: 580-587. [26] ZHANG P C, ZHANG W, LI W J, et al. Supervised Hashing with Latent Factor Models // Proc of the 37th International ACM SIGIR Conference on Research and Development in Information Retrieval. New York, USA: ACM, 2014: 173-182. [27] KRIZHEVSKY A. Learning Multiple Layers of Features from Tiny Images[C/OL]. [2019-11-15]. http://www.cs.toronto.edu/~kriz/learning-features-2009-TR.pdf. [28] CHUA T S, TANG J, HONG R C, et al. NUS-WIDE: A Real-World Web Image Database from National University of Singapore // Proc of the 8th ACM International Conference on Image and Video Retrieval. New York, USA: ACM, 2009. DOI:10.1145/1646396.1646452. [29] YANG E, LIU T L, DENG C, et al. DistillHash: Unsupervised Deep Hashing by Distilling Data Pairs // Proc of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2019: 2941-2950. [30] PASZKE A, GROSS S, MASSA F, et al. PyTorch: An Imperative Style, High-Performance Deep Learning Library // WALLACH H,LAROCHELLE H, BEYGELZIMER A, et al., eds. Advances in Neural Information Processing Systems 32. Cambridge, USA: The MIT Press, 2019: 8024-8035.
2020, Vol. 33 
