Abstract
Deep hashing methods have achieved impressive results due to the powerful nonlinear mapping ability brought by deep neural network. However, existing deep hashing algorithms treat label information as the only measurement for image similarity, which degenerated the task from retrieval to classification. In this paper, to address this problem, we propose a joint learning framework that learns semantic hash codes from both supervised and unsupervised information. We divide the K-bits hash codes into semantic branch and content branch. The codes from semantic branch are generated with general deep supervised training procedure, while the content branch constructs hash codes by autoencoder incorporated within the hashing model. Experimental results show that the semantic retrieval performance of our framework is compatible to the state of the art. In addition, more semantic information can be embedded into the generated hash codes, which demonstrates the effectiveness of our joint framework for CBIR tasks.
This research is partly supported by NSFC, China (No:61375048).
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2005), San Diego, USA, vol. 1, pp. 886–893. IEEE (2005). 24705
Gionis, A., Indyk, P., Motwani, R.: Similarity search in high dimensions via hashing. Vldb 99(6), 12 (1999)
Gong, Y., Lazebnik, S.: Iterative quantization: a procrustean approach to learning binary codes. In: Computer Vision and Pattern Recognition (CVPR), pp. 817–824, June 2011
Hu, Z., Chen, J., Lu, H., Zhang, T.: Bayesian supervised hashing. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6348–6355 (2017)
Indyk, P., Motwani, R.: Approximate nearest neighbors: towards removing the curse of dimensionality. In: Proceedings of the Thirtieth Annual ACM Symposium on Theory of Computing, STOC 1998, pp. 604–613. ACM, New York (1998)
Jia, Y., et al.: Caffe: convolutional architecture for fast feature embedding. In Proceedings of the 22nd ACM international conference on Multimedia, pp. 675–678. ACM (2014). 09357
Jiang, Q.-Y., Li, W.-J.: Scalable graph hashing with feature transformation. In: IJCAI, pp. 2248–2254 (2015)
Krizhevsky, A., Hinton, G.: Learning multiple layers of features from tiny images, p. 03040. Citeseer, Technical report (2009)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097–1105 (2012)
Lai, H., Pan, Y., Liu, Y., Yan, S.: Simultaneous feature learning and hash coding with deep neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3270–3278. IEEE, June 2015
Li, Q., Sun, Z., He, R., Tan, T.: Deep supervised discrete hashing. pp. 2482–2491, June 2017
Li, W.-J., Wang, S., Kang, W.-C.: Feature Learning based Deep Supervised Hashing with Pairwise Labels. arXiv:1511.03855 [cs], November 2015
Li, X., Ma, C., Yang, J., Qiao, Y.: Teach to hash: a deep supervised hashing framework with data selection. In: Cheng, L., Leung, A.C.S., Ozawa, S. (eds.) ICONIP 2018. LNCS, vol. 11301, pp. 120–129. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-04167-0_11
Liu, W., Mu, C., Kumar, S., Chang, S.-F.: Discrete graph hashing. In: Advances in Neural Information Processing Systems, pp. 3419–3427 (2014)
Liu, W., Wang, J.R., Ji, R., Jiang, Y.G., Chang, S.F.: Supervised hashing with kernels. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp. 2074–2081 (2012)
Shen, F., Shen, C., Liu, W.,Tao Shen, H. : Supervised discrete hashing. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 37–45 (2015)
Weiss, Y., Torralba, A., Fergus, R.: Spectral hashing. In: Advances in Neural Information Processing Systems, pp. 1753–1760 (2009)
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, pp. 2156–2162. AAAI Press (2014)
Xu, K., Qiao, Y.: Randomized sampling-based fly local sensitive hashing. In: 2018 25th IEEE International Conference on Image Processing (ICIP), pp. 1293–1297. IEEE (2018). 00000
Xu, K., Qiao, Y., Niu, X., Fang, X., Han, Y., Yang, J.: Bone scintigraphy retrieval using sift-based fly local sensitive hashing. In: 2018 IEEE 27th International Symposium on Industrial Electronics (ISIE), pp. 735–740. IEEE (2018). 00000
Yang, H.F., Lin, K., Chen, C.S.: Supervised learning of semantics-preserving hash via deep convolutional neural networks. IEEE Trans. Pattern Anal. Mach. Intell. 99, 1 (2017)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Xu, K. et al. (2019). Joint Semantic Hashing Using Deep Supervised and Unsupervised Methods. In: Gedeon, T., Wong, K., Lee, M. (eds) Neural Information Processing. ICONIP 2019. Lecture Notes in Computer Science(), vol 11955. Springer, Cham. https://doi.org/10.1007/978-3-030-36718-3_2
Download citation
DOI: https://doi.org/10.1007/978-3-030-36718-3_2
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-36717-6
Online ISBN: 978-3-030-36718-3
eBook Packages: Computer ScienceComputer Science (R0)