Abstract
The existing hashing methods mainly handle either the feature based nearest-neighbour search or the category-level image retrieval, whereas a few efforts are devoted to instance retrieval problem. Besides, although multi-view hashing methods are capable of exploring the complementarity among multiple heterogeneous visual features, they heavily rely on massive labeled training data, and somewhat affects the real-world applications. In this paper, we propose a binary multi-view fusion framework for directly recovering a latent Hamming subspace from the multi-view features. More specifically, the multi-view subspace reconstruction and the binary quantization are integrated in a unified framework so as to minimize the discrepancy between the original multi-view high-dimensional Euclidean space and the resulting compact Hamming subspace. In addition, our method is amenable to efficient iterative optimization for learning a compact similarity-preserving binary code. The resulting binary codes demonstrate significant advantage in retrieval precision and computational efficiency at the cost of limited memory footprint. More importantly, our method is essentially an unsupervised learning scheme without any labeled data involved, and thus can be used in the cases when the supervised information is unavailable or insufficient. Experiments on public benchmark and large-scale datasets reveal that our method achieves competitive retrieval performance comparable to the state-of-the-art and has excellent scalability in large-scale scenario.
This work was supported by the Natural Science Foundation of China (NSFC) under Grants 61703096, 61273246 and the Natural Science Foundation of Jiangsu Province under Grant BK20170691.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: NIPS, pp. 1097–1105 (2012)
Razavian, A.S., Azizpour, H., Sullivan, J., Carlsson, S.: CNN features off-the-shelf: an astounding baseline for recognition. In: CVPRW, pp. 512–519 (2014)
Wan, J., et al.: Deep learning for content-based image retrieval: a comprehensive study. In: ACM MM, pp. 157–166 (2014)
Yandex, A.B., Lempitsky, V.: Aggregating local deep features for image retrieval. In: ICCV, pp. 1269–1277 (2015)
Li, J., Yang, B., Yang, W., Sun, C., Zhang, H.: When deep meets shallow: subspace-based multi-view fusion for instance-level image retrieval. In: ROBIO, pp. 486–492 (2018)
Zhou, W., Li, H., Sun, J., Tian, Q.: Collaborative index embedding for image retrieval. IEEE TPAMI 40(5), 1154–1166 (2018)
Strecha, C., Bronstein, A.M., Bronstein, M.M., Fua, P.: LDAHash: improved matching with smaller descriptors. IEEE TPAMI 34(1), 66–78 (2012)
Zhang, J., Peng, Y.: SSDH: semi-supervised deep hashing for large scale image retrieval. IEEE TCSVT 29(1), 212–225 (2019)
Liu, X., Huang, L., Deng, C., Lu, J., Lang, B.: Multi-view complementary hash tables for nearest neighbor search. In: ICCV, pp. 1107–1115 (2015)
Zhu, L., Lu, X., Cheng, Z., Li, J., Zhang, H.: Deep collaborative multi-view hashing for large-scale image search. IEEE TIP 29, 4643–4655 (2020)
Zheng, L., Yang, Y., Tian, Q.: SIFT meets CNN: a decade survey of instance retrieval. IEEE TPAMI 40(5), 1224–1244 (2018)
Wang, J., Zhang, T., Song, J., Sebe, N., Shen, H.T.: A survey on learning to hash. IEEE TPAMI 40(4), 769–790 (2018)
Gong, Y., Lazebnik, S.: Iterative quantization: a procrustean approach to learning binary codes. In: CVPR, pp. 817–824 (2011)
Jegou, H., Douze, M., Schmid, C.: Hamming embedding and weak geometric consistency for large scale image search. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008. LNCS, vol. 5302, pp. 304–317. Springer, Heidelberg (2008). https://doi.org/10.1007/978-3-540-88682-2_24
Nister, D., Stewenius, H.: Scalable recognition with a vocabulary tree. In: CVPR, pp. 2161–2168 (2006)
Philbin, J., Chum, O., Isard, M., Sivic, J., Zisserman, A.: Object retrieval with large vocabularies and fast spatial matching. In: CVPR, pp. 1–8 (2007)
Li, J., Xu, C., Gong, M., Xing, J., Yang, W., Sun, C.: SERVE: soft and equalized residual vectors for image retrieval. Neurocomputing 207, 202–212 (2016)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: ICLR, pp. 1–14 (2015)
Arandjelović, R., Zisserman, A.: All about VLAD. In: CVPR, pp. 1578–1585 (2013)
Alzubi, A., Amira, A., Ramzan, N.: Content-based image retrieval with compact deep convolutional features. Neurocomputing 249, 95–105 (2017)
Ng, J.Y., Yang, F., Davis, L.S.: Exploiting local features from deep networks for image retrieval. In: CVPRW, pp. 53–61 (2015)
Jiang, Q., Li, W.: Scalable graph hashing with feature transformation. In: IJCAI, pp. 2248–2254 (2015)
Yu, F.X., Kumar, S., Gong, Y., Chang, S.: Circulant binary embedding. In: ICML, pp. 946–954 (2014)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Wu, Z., Li, J., Xu, J. (2020). Efficient Binary Multi-view Subspace Learning for Instance-Level Image Retrieval. In: Yang, H., Pasupa, K., Leung, A.CS., Kwok, J.T., Chan, J.H., King, I. (eds) Neural Information Processing. ICONIP 2020. Communications in Computer and Information Science, vol 1332. Springer, Cham. https://doi.org/10.1007/978-3-030-63820-7_7
Download citation
DOI: https://doi.org/10.1007/978-3-030-63820-7_7
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-63819-1
Online ISBN: 978-3-030-63820-7
eBook Packages: Computer ScienceComputer Science (R0)