Abstract The image features learned by deep convolutional neural networks have an obvious hierarchical structure. As the number of layers deepens, the learned features become more and more abstract and the discrimination of classes is gradually enhanced. Based on the above, deep hamming embedding based hashing for image retrieval is proposed. A hidden layer is inserted at the end of the deep convolutional neural network and then hash codes are obtained by the activation of each unit of the layer. According to the characteristics of hash codes, hamming embedding loss is proposed to preserve the similarity between the original data better. Experiments on commonly used benchmark image datasets CIFAR-10 and NUS-WIDE indicate that the proposed model improves image retrieval performance and performs better with short encoding length.
Fund:National Natural Science Foundation of China(No.61976195,61672467), Natural Science Foundation of Zhejiang Province(No.LY18F020019)
Corresponding Authors:
LIU Huawen, Ph.D., professor. His research interests include data mining, feature selection and machine learning.
About author:: LIN Jiwen, master student. His research interests include learning to hash and large-scale image retrieval. ZHENG Zhonglong, Ph.D., professor. His research interests include pattern recognition, machine learning and image proce-ssing.
[1] 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. [2] 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. [3] 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. [4] WANG X F, SHI Y, KITANI K M. Deep Supervised Hashing with Triplet Labels // Proc of the Asian Conference on Computer Vision. Berlin, Germany: Springer, 2016: 70-84. [5] LI Q, SUN Z N, HE R, et al. Deep Supervised Discrete Hashing // GUYON I, LUXBURG U V, BENGIO S, et al., eds. Advances in Neural Information Processing Systems 30. Cambridge, USA: The MIT Press, 2017: 2482-2491. [6] 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. Burlington, USA: Morgan Kaufmann Publishers, 1999: 518-529. [7] CHARIKAR M S. Similarity Estimation Techniques from Rounding Algorithms // Proc of the 34th Annual ACM Symposium on Theory of Computing. New York, USA: ACM, 2002: 380-388. [8] DATAR M, INDYK P, IMMORLICA N, et al. Locality-Sensitive Hashing Scheme Based on p-Stable Distributions // Proc of the 20th Annual Symposium on Computational Geometry. New York, USA: ACM, 2004. DOI: 10.1145/997817.997857. [9] BAWA M, CONDIE T, GANESAN P. LSH Forest: Self-tuning Indexes for Similarity Search // Proc of the 14th International Confe-rence on World Wide Web. New York, USA: ACM, 2005: 651-660. [10] JGOU H, AMSALEG L, SCHMID C, et al. Query Adaptative Locality Sensitive Hashing // Proc of the IEEE International Conference on Acoustics, Speech and Signal Processing. Washington, USA: IEEE, 2008: 825-828. [11] LI P, HASTIE T J, CHURCH K W. Very Sparse Random Projections // Proc of the 12th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York, USA: ACM, 2006: 287-296. [12] SHRIVASTAVA A, LI P. Densifying One Permutation Hashing via Rotation for Fast Near Neighbor Search[C/OL]. [2020-02-26]. http://proceedings.mlr.press/v32/shrivastava14.pdf. [13] ZHU H, LONG M S, WANG J M, et al. Deep Hashing Network for Efficient Similarity Retrieval // Proc of the 30th AAAI Confe-rence on Artificial Intelligence. Palo Alto, USA: AAAI Press, 2016: 2415-2421. [14] CAO Y, LONG M S, WANG J M, et al. Deep Quantization Network for Efficient Image Retrieval // Proc of the 30th AAAI Conference on Artificial Intelligence. Palo Alto, USA: AAAI Press, 2016: 3457-3463. [15] 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. [16] KRIZHEVSKY A, SUTSKEVER I, HINTON G E. ImageNet Cla-ssification with Deep Convolutional Neural Networks // PEREIRA F, BURGES C J C, BOTTO0U L, et al., eds. Advances in Neural Information Processing Systems 25. Cambridge, USA: The MIT Press, 2012: 1097-1105. [17] SIMONYAN K, ZISSERMAN A. Very Deep Convolutional Networks for Large-Scale Image Recognition[C/OL]. [2020-02-26]. https://arxiv.org/pdf/1409.1556.pdf. [18] HE K M, ZHANG X Y, REN S Q, et al. Deep Residual Learning for Image Recognition // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2016: 770-778. [19] LECUN Y, BOSER B, DENKER J S, et al. Backpropagation Applied to Handwritten Zip Code Recognition. Neural Computation, 1989, 1(4): 541-551. [20] LAWRENCE S, GILES C L, TSOI A C, et al. Face Recognition: A Convolutional Neural-Network Approach. IEEE Transactions on Neural Networks, 1997, 8(1): 98-113. [21] BERGSTRA J, DESJARDINS G, LAMBLIN P, et al. Quadratic Polynomials Learn Better Image Features. Technical Report, 1337. Québec, Canada: Université de Montréal, 2009. [22] RUSSAKOVSKY O, DENG J, SU H, et al. ImageNet Large Scale Visual Recognition Challenge. International Journal of Computer Vision, 2015, 115(3): 211-252. [23] KRIZHEVSKY A. Learning Multiple Layers of Features from Tiny Images[R/OL]. [2020-02-26]. http://www.cs.toronto.edu/~kriz/learning-features-2009-TR.pdf. [24] CHUA T S, TANG J H, HONG R C, et al. NUS-WIDE: A Real-World Web Image Database from National University of Singapore // Proc of the ACM International Conference on Image and Video Retrieval. New York, USA: ACM Press, 2009. DOI:10.1145/1646396.1646452. [25] 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. [26] WEISS Y, TORRALBA A, FERGUS R. Spectral Hashing // KOLLER D, SCHUURMANS D, BENGIO Y, et al., eds. Advances in Neural Information Processing Systems 21. Cambridge, USA: The MIT Press, 2008: 1753-1760. [27] GONG Y C, LAZEBNIK S. Iterative Quantization: A Procrustean Approach to Learning Binary Codes // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2011: 817-824. [28] LIN G S, SHEN C H, SHI Q F, et al. Fast Supervised Hashing with Decision Trees for High-Dimensional Data // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2014: 1971-1978. [29] XIA R K, 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. [30] CHATFIELD K, SIMONYAN K, VEDALDI A, et al. Return of the Devil in the Details: Delving Deep into Convolutional Nets[C/OL]. [2020-02-26]. https://arxiv.org/pdf/1405.3531.pdf. [31] OLIVA A,TORRALBA A. ModelingtheShape of the Scene: A Holistic Representation of the Spatial Envelope. International Journal of Computer Vision, 2001, 42(3): 145-175. [32] 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.
2020, Vol. 33 
