Abstract
Deep hashing, which combines binary codes learning and convolutional neural network, has achieved promising performance for highly efficient image retrieval. Asymmetric deep hashing methods, which treat query points and database points in an asymmetric way perform better than symmetric deep hashing methods on retrieval tasks in both time complexity and accuracy. However, most existing asymmetric deep hashing methods do not sufficiently discover semantic correlation from label information, which results in reducing the discrimination of learned binary codes. In this paper, we propose a novel Deep Semantic Asymmetric Hashing (DSAH) approach, which exploits semantic correlation between query points and their labels in a common semantic space to form more discriminative and similarity-preserving binary codes. Experiments show that DSAH outperforms current state-of-the-art non-deep hash methods and deep hashing methods, especially asymmetric deep hashing methods.
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
Cao, Z., Long, M., Wang, J., Yu, P.S.: Hashnet: deep learning to hash by continuation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 5608–5617 (2017)
Chatfield, K., Simonyan, K., Vedaldi, A., Zisserman, A.: Return of the devil in the details: delving deep into convolutional nets. arXiv preprint arXiv:1405.3531 (2014)
Chua, T.S., 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 ACM International Conference on Image and Video Retrieval, p. 48. ACM (2009)
Gong, Y., Lazebnik, S., Gordo, A., Perronnin, F.: Iterative quantization: a procrustean approach to learning binary codes for large-scale image retrieval. IEEE Trans. Pattern Anal. Mach. Intell. 35(12), 2916–2929 (2013)
Jiang, Q.Y., Li, W.J.: Asymmetric deep supervised hashing. In: Thirty-Second AAAI Conference on Artificial Intelligence (2018)
Krizhevsky, A., Hinton, G.: Learning multiple layers of features from tiny images. Tech. rep. Citeseer (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 (2015)
Lin, G., Shen, C., Shi, Q., Van den Hengel, A., Suter, D.: Fast supervised hashing with decision trees for high-dimensional data. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1963–1970 (2014)
Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740–755. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10602-1_48
Liu, H., Wang, R., Shan, S., Chen, X.: Deep supervised hashing for fast image retrieval. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2064–2072 (2016)
Liu, W., Wang, J., 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. IEEE (2012)
Norouzi, M., Blei, D.M.: Minimal loss hashing for compact binary codes. In: Proceedings of the 28th International Conference on Machine Learning (ICML-11), pp. 353–360. Citeseer (2011)
Norouzi, M., Fleet, D.J., Salakhutdinov, R.R.: Hamming distance metric learning. In: Advances in Neural Information Processing Systems, pp. 1061–1069 (2012)
Shen, F., Gao, X., Liu, L., Yang, Y., Shen, H.T.: Deep asymmetric pairwise hashing. In: Proceedings of the 25th ACM International Conference on Multimedia, pp. 1522–1530. ACM (2017)
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)
Acknowledgment
This work is supported in part by the Innovation and Entrepreneurship Training Program for College Students of NJUPT (Grant No.XZD2018082), the Postdoctoral Research Plan of Jiangsu Province (Grant No. 1501054B), the Postdoctoral Science Foundation of China (Grant No. 2016M591840).
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
Zhang, M., Cheng, C., Long, X. (2019). Deep Semantic Asymmetric Hashing. In: Tetko, I., Kůrková, V., Karpov, P., Theis, F. (eds) Artificial Neural Networks and Machine Learning – ICANN 2019: Theoretical Neural Computation. ICANN 2019. Lecture Notes in Computer Science(), vol 11727. Springer, Cham. https://doi.org/10.1007/978-3-030-30487-4_29
Download citation
DOI: https://doi.org/10.1007/978-3-030-30487-4_29
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-30486-7
Online ISBN: 978-3-030-30487-4
eBook Packages: Computer ScienceComputer Science (R0)