Abstract
Recently, by exploiting asymmetric learning mechanism, asymmetric hashing methods achieve superior performance in image retrieval. However, due to the discrete binary constraint, these methods typically rely on a special optimization strategy of discrete cyclic coordinate descent (DCC), which is time-consuming since it must learn the binary codes bit by bit. To address this problem, we propose a novel deep supervised hashing method called Fast Deep Asymmetric Hashing (FDAH), which learns the binary codes of training and query sets in an asymmetric way. FDAH designs a novel asymmetric hash learning framework using the inner product of the output of deep network and semantic label regression to approximate the similarity and minimize the discriminant reconstruction error between the deep representation and the binary codes. Instead of using the DCC optimization strategy, FDAH avoids using the quadratic term of binary variables and the binary code of all bits can be optimized simultaneously in one step. Moreover, by incorporating the semantic information in binary code learning and the quantization process, FDAH can obtain more discriminative and efficient binary codes. Extensive experiments on three well-known datasets show that the proposed FDAH can achieve state-of-the-art performance with less training time.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Andoni, A., Razenshteyn, I.P.: Optimal data-dependent hashing for approximate near neighbors. In: STOC, pp. 793ā801 (2015)
Chatfield, K., Simonyan, K., Vedaldi, A., Zisserman, A.: Return of the devil in the details: delving deep into convolutional nets. In: BMVC (2014)
Chen, Y., Lai, Z., Ding, Y., Lin, K., Wong, W.K.: Deep supervised hashing with anchor graph. In: ICCV, pp. 9795ā9803 (2019)
Cui, H., Zhu, L., Li, J., Yang, Y., Nie, L.: Scalable deep hashing for large-scale social image retrieval 29, 1271ā1284 (2020)
Datar, M., Indyk, P., Immorlica, N., Mirrokni, V.: Locality-sensitive hashing scheme based on p-stable distributions. In: ASCG, pp. 253ā262 (2004)
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), 2916ā2929 (2013)
Gui, J., Liu, T., Sun, Z., Tao, D., Tan, T.: Fast supervised discrete hashing. IEEE Trans. Pattern Anal. Mach. Intell. 40, 490ā496 (2018)
Jiang, Q., Cui, X., Li, W.: Deep discrete supervised hashing. IEEE Trans. Image Process. 27, 5996ā6009 (2018)
Jiang, Q., Li, W.: Asymmetric deep supervised hashing. In: AAAI, pp. 3342ā3349 (2018)
Kang, W., Li, W., Zhou, Z.: Column sampling based discrete supervised hashing. In: AAAI, pp. 1230ā1236 (2016)
Kulis, B., Darrell, T.: Learning to hash with binary reconstructive embeddings. In: NIPS, pp. 1042ā1050 (2009)
Lai, H., Pan, Y., Liu, Y., Yan, S.: Simultaneous feature learning and hash coding with deep neural networks. In: CVPR, pp. 3270ā3278 (2015)
Lai, Z., Chen, Y., Wu, J., Wong, W.K., Shen, F.: Jointly sparse hashing for image retrieval. IEEE Trans. Image Process. 27(12), 6147ā6158 (2018)
Li, Q., Sun, Z., He, R., Tan, T.: Deep supervised discrete hashing. In: NIPS, pp. 2482ā2491 (2017)
Li, W., Wang, S., Kang, W.: Feature learning based deep supervised hashing with pairwise labels. In: IJCAI, pp. 1711ā1717 (2016)
Liu, W., Wang, J., Ji, R., Jiang, Y., Chang, S.: Supervised hashing with kernels. In: CVPR, pp. 2074ā2081 (2012)
Liu, W., Wang, J., Kumar, S., Chang, S.: Hashing with graphs. In: ICML, pp. 1ā8 (2011)
Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning representations by back propagating errors. Nature 323, 533ā536 (1986)
Shen, F., Gao, X., Liu, L., Yang, Y., Shen, H.T.: Deep asymmetric pairwise hashing. In: ACM MM, pp. 1522ā1530 (2017)
Shen, F., Shen, C., Liu, W., Shen, H.T.: Supervised discrete hashing. In: CVPR, pp. 37ā45 (2015)
Shen, Y., Liu, L., Shen, F., Shao, L.: Zero-shot sketch-image hashing. In: CVPR, pp. 3598ā3607 (2018)
Wang, X., Shi, Y., Kitani, K.M.: Deep supervised hashing with triplet labels. In: Lai, S.-H., Lepetit, V., Nishino, K., Sato, Y. (eds.) ACCV 2016. LNCS, vol. 10111, pp. 70ā84. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-54181-5_5
Weiss, Y., Torralba, A., Fergus, R.: Spectral hashing. In: NIPS, pp. 1753ā1760 (2008)
Xia, R., Pan, Y., Lai, H., Liu, C., Yan, S.: Supervised hashing for image retrieval via image representation learning. In: AAAI, pp. 2156ā2162 (2014)
Xie, G., et al.: Attentive region embedding network for zero-shot learning. In: CVPR, pp. 9384ā9393 (2019)
Zhang, Z., Liu, L., Shen, F., Shen, H.T., Shao, L.: Binary multi-view clustering. IEEE Trans. Pattern Anal. Mach. Intell. 41, 1774ā1782 (2019)
Zhao, S., Wu, D., Zhang, W., Zhou, Y., Li, B., Wang, W.: Asymmetric deep hashing for efficient hash code compression. In: ACM MM, pp. 763ā771 (2020)
Acknowledgement
This work was supported in part by the Natural Science Foundation of China under Grant 61976145, Grant 62076164 and Grant 61802267, in part by the Guangdong Basic and Applied Basic Research Foundation (No. 2021A1515011861), and in part by the Shenzhen Municipal Science and Technology Innovation Council under Grants JCYJ20180305124834854 and JCYJ20190813100801664.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
Ā© 2022 Springer Nature Switzerland AG
About this paper
Cite this paper
Lin, C., Lai, Z., Lu, J., Zhou, J. (2022). Fast Deep Asymmetric Hashing forĀ Image Retrieval. In: Wallraven, C., Liu, Q., Nagahara, H. (eds) Pattern Recognition. ACPR 2021. Lecture Notes in Computer Science, vol 13189. Springer, Cham. https://doi.org/10.1007/978-3-031-02444-3_31
Download citation
DOI: https://doi.org/10.1007/978-3-031-02444-3_31
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-02443-6
Online ISBN: 978-3-031-02444-3
eBook Packages: Computer ScienceComputer Science (R0)