Abstract
Deep hashing is effective and efficient for large-scale image retrieval. Most of existing deep hashing methods train a single hash table by utilizing the output of the penultimate fully-connected layer of a convolutional neural network as the deep feature of images. They concentrate on the semantic information but neglect the fine-grain image structure. To address this issue, this paper proposes an advanced image hashing method, Bit-wise Attention Deep Complementary Supervised Hashing (BADCSH). It is an end-to-end system that trains a sequence of hash tables in a boosting manner, each of which is trained by correcting errors caused by all previous ones. Features from different levels of the network are used to train different hash tables. The hash table trained with features at one level reveals a level of semantic content of the image, while the hash table trained with features at a lower level contains structural information of the image that makes up the semantic content. Moreover, the hash layer is used as an embedded layer of the network to generate hash codes. A dense attention layer is added to the hash layer to treat various hash bits differently, in order to reduce hash code redundancy and maximize overall similarity preservation. Finally, the hash tables trained on different levels of features are fused by weights computed based on their respective performance. Experiments on three real-world image databases demonstrate that the proposed method achieves the best performance among state-of-the-art comparative hashing methods.
Similar content being viewed by others
References
Anastasios D, Nikolaos D, Stefanos K (2000) A fuzzy video content representation for video summarization and content-based retrieval. Signal Process 80 (6):1049–1067
Babenko A, Lempitsky V (2015) Aggregating deep convolutional features for image retrieval. In: Proc. of the IEEE Conference on Computer Vision, pp 1269–1277
Babenko A, Slesarev A, Chigorin A, Lempitsky VS (2014) Neural codes for image retrieval. In: European Conference on Computer Vision, pp 584–599
Bell S, Zitnick CL, Bala K, Girshick R (2016) Inside-Outside Net: Detecting objects in context with skip pooling and recurrent neural networks. In: IEEE Conference on Computer Vision and Pattern Recognition, pp 2874–2883
Cordelia S, Mohr R (1997) Local grayvalue invariants for image retrieval. IEEE Trans Pattern Anal Machine Intell 19(5):530–535
Datar M, Immorlica N, Indyk P, Mirrokni VS (2004) Locality-sensitive hashing scheme based on p-stable distributions. In: Proc. the Twentieth Annual Symposium on Computational Geometry, pp 253–262
Dniz G, Bueno J, Salido, La Torre FD (2011) Face recognition using histograms of oriented gradients. in Proc Pattern Recognit Lett 32(12):1598–1603
Gordo A, Almazn J, Revaud J, Larlus D (2016) Deep image retrieval: Learning global representations for image search. European conference on computer vision 241–257
Gong Y, Lazebnik S, Gordo A, Perronnin F (2013) Iterative quantization: a procrustean approach to learning binary codes for large-scale image retrieval. IEEE Trans Pattern Anal Mach Intell 35(12):2916–2929
Gong Y, Wang L, Guo R, Lazebnik S (2014) Multi-scale orderless pooling of deep convolutional activation features. In: 13th European Conference on Computer Vision, pp 392–407
Hu D, Nie F, Li X (2019) Deep binary reconstruction for cross-modal hashing. IEEE Trans Multimed 21(4):973–985
Huang D, Shan C, Ardabilian M, Wang Y, Chen L (2011) Local binary patterns and its application to facial image analysis: A survey. IEEE Trans on Syst Man Cybern 41(6):765–781
Jing C, Dong Z, Pei M, Jia Y (2019) Heterogeneous hashing network for face retrieval across image and video domains. IEEE Trans Multimed 21 (3):782–794
Kafai M, Eshghi K, Bhanu B (2014) Discrete cosine transform locality-sensitive hashes for face retrieval. IEEE Trans Multimed 16(4):1090–1103
Kang WC, Li WJ, Zhou ZH (2016) Column sampling based discrete supervised hashing. Thirtieth AAAI conference on artificial intelligence
Kang C, Zhu L, Qian X, Han J, Wang M, Tang YY (2019) Geometry and topology preserving hashing for sift feature. IEEE Trans Multimed 21 (6):1563–1576
Kim S, Choi S (2013) Multi-view anchor graph hashing. In: Proc IEEE Int Conf Acoust Speech Signal Process, pp 3123–3127
Kim S, Kang Y, Choi S (2012) Sequential spectral learning to hash with multiple representations. In: Proc European conference on computer vision, pp 538–551
Kong W, Li WJ, Guo M (2012) Manhattan hashing for large-scale image retrieval. In: Proceedings of the 35th international ACM SIGIR conference on Research and development in information retrieval, pp 45–54
Krizhevsky A, Sutskever I, Hinton G (2012) ImageNet classification with deep convolutional neural networks. Neural Information Processing Systems
Kulis B, Darrell T (2009) Learning to hash with binary reconstructive embeddings. In: Proc Neural Information Processing Systems, pp 1042–1050
Kulis B, Grauman K (2009) Kernelized locality-sensitive hashing for scalable image search. In: Proc IEEE International Conference on Computer Vision, pp 2130–2137
Lai H, Pan Y, Liu Y, Yan S (2015) Simultaneous feature learning and hash coding with deep neural networks. In: Proc IEEE conference on computer vision and pattern recognition, pp 3270–3278
Li J, Ng WWY, Xing T, Kwong S, Wang H (2019) Weighted multi-deep ranking supervised hashing for efficient image retrieval 1st Nov.
Li P, Cheng J, Lu H (2013) Hashing with dual complementary projection learning for fast image retrieval, in Proc. Neurocomputing 120(10):83–89
Li P, Wang M, Cheng J, Xu C, Lu H (2013) Spectral hashing with semantically consistent graph for image indexing. IEEE Trans Multimed 15(1):141–152
Li X, Lin G, Shen C, et al. (2013) And learning hash functions using column generation[J]. Computer ence 142–150
Lin J, Li Z, Tang J (2017) Discriminative deep hashing for scalable face image retrieval. In: Proc International Joint Conference on Artificial Intelligence, pp 2266–2272
Liong VE, Jiwen Lu, Gang W, Moulin P, Jie Z (2015) Deep hashing for compact binary codes learning. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston MA, pp 2475–2483
Liu H, Wang R, Shan S, Chen X (2016) Deep supervised hashing for fast image retrieval. In: Proc IEEE Conference on Computer Vision and Pattern Recognition, pp 2064–2072
Liu W, Mu C, Kumar S, Chang S-F (2014) Discrete graph hashing. Advances in Neural Information Processing Systems 27:3419–3427
Liu W, Wang J, Ji R, Jiang YG, Chang SF (2012) Supervised hashing with kernels. In: Proc Computer Vision and Pattern Recognition, pp 2074–C2081
Lv Y, Ng WW, Zeng Z, Yeung DS, Chan PP (2015) Asymmetric cyclical hashing for large scale image retrieval. IEEE Trans Multimedia 17(8):1225–1235
Ma L, Li H, Meng F, Wu Q, Ngan KN (2017) Learning efficient binary codes from high-level feature representations for multilabel image retrieval. IEEE Trans Multimed 19(11):2545–2560
Ng WWY, Li J, Tian T, Wang H, Kwong S, Wallace J (2020) Multi-level supervised hashing with deep features for efficient image retrieval. Neurocomputing
Ng YH, Yang F, Davis LS (2015) Exploiting local features from deep networks for image retrieval. In: Proc. of the IEEE conference on computer vision and pattern recognition, pp 53–61
Norouzi M, Fleet DJ (2011) Minimal loss hashing for compact binary codes. In: Proc. International Conference on Machine Learning, pp 353–360
Oliva A, Torralba A (2001) Modeling the shape of the scene: a holistic representation of the spatial envelope. International Journal of Computer Vision 42(3):145–175
Radenovic F, Tolias G, Chum O (2019) Fine-Tuning CNN image retrieval with no human annotation. IEEE Trans Pattern Anal Machine Intell 41 (7):1655–1668
Raginsky M, Lazebnik S (2009) Locality-sensitive binary codes from shift-invariant kernels. In: Proc Conf. and Workshop on Neural Information Processing Systems, pp 1509–1517
Shen F, Shen C, Liu W, Shen HT (2015) Supervised discrete hashing. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition, pp 37–45
Shen F, Yang Y, Liu L, Liu W, Tao D, Shen HT (2017) Asymmetric binary coding for image search. IEEE Trans Multimed 19(9):2022–2032
Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. Computer Science
Song D, Liu W, Ji R, Meyer DA, Smith JR (2015) Top rank supervised binary coding for visual search. In: 2015 IEEE international conference on computer vision (ICCV) Santiago, pp 1922–1930
Tiakas E, Rafailidis D, Dimou A, Daras P (2013) MSIDX: multi-sort indexing for efficient content-based image search and retrieval. IEEE Trans Multimed 15(6):1415–1430
Tiana X, Zhoua X, Ng WWY, Li J, Wang H (2019) Bootstrap dual complementary hashing with semi-supervised re-ranking for image retrieval, Neurocomputing, 31st Oct.
Tieu K, Paul V (2004) Boosting image retrieval. Int J Comput Vis 56(1-2):17–36
Tolias G, Sicre R, Jgou H (2015) Particular object retrieval with integral max-pooling of CNN activations. Computer Science
Tzelepi M, Tefas A (2017) Deep convolutional learning for content based image retrieval. Neurocomputing
Venters C, Cooper M (2000) A review of content-based image retrieval systems, JISC Technology Applications Programme, http://www.jtap.ac.uk/reports/htm/jtap-054.html
Wang D, Cui P, Ou M, Zhu W (2015) Deep multimodal hashing with orthogonal regularization. In: Proc 24th conference on artificial intelligence, pp 2291–2297
Wang J, Kumar S, Chang S-F (2010) Semi-supervised hashing for scalable image retrieval. In: Proc. IEEE Conference on Computer Vision and Pattern Recognition
Wang X, Shi Y, Kitani K (2016) Deep supervised hashing with triplet labels. In: Proc Asian Conference on Computer Vision, pp 70–84
Wang Y, Zhang L, Nie F, Li X, Chen Z, Wang F (2019) WeGAN: deep image hashing with weighted generative adversarial networks. In: IEEE Transactions on Multimedia
Weiss Y, Torralba A, Fergus R (2009) Spectral hashing. In: Proc advances in neural information processing systems, pp 1753–1760
Wu C, Zhu J, Cai D, Chen C, Bu J (2013) Semi-supervised nonlinear hashing using bootstrap sequential projection learning. IEEE Transaction Knowledge and Data Engneering 25(6):1380–1393
Xia R, Pan Y, Lai H, Liu C, Yan S (2014) Supervised hashing for image retrieval via image representation learning. In: Proc Conference on Artificial Intelligence, pp 2156–2162
Xu H, Wang J, Li Z, Zeng G, Li S, Yu N (2011) Complementary hashing for approximate nearest neighbor search. In: Proc International Conference on Computer Vision
Yandex AB, Lempitsky V (2015) Aggregating local deep features for image retrieval. IEEE International Conference on Computer Vision 1269–1277
Yao T, Long F, Mei T, Rui Y (2016) Deep semantic-preserving and ranking-based hashing for image retrieval. In: Proc International Joint Conference on Artificial Intelligence, pp 3931–3937
Yong R, Huang TS, Chang S-F (1999) Image retrieval: Past, present, and future. J Vis Commun Image Represent 10(1):1–23
Zhang D, Wang F, Si L (2011) Composite hashing with multiple information sources. In: Proc 34th Int ACM SIGIR Conf Res Develop Inf Retr, pp 225–234
Zhang J, Peng Y (2018) Query-Adaptive image retrieval by deep-weighted hashing. IEEE Trans Multimed 20(9):2400–2414
Zhang R, Lin L, Zhang R, Zuo W, Zhang L (2015) Bit-scalable deep hashing with regularized similarity learning for image retrieval and person re-identification. IEEE Trans Image Processing 24(12):4766–4779
Zhang Z, Zou Q, Lin Y, Chen L, Wang S (2019) Improved deep hashing with soft pairwise similarity for multi-label image retrieval. In: IEEE Transactions on Multimedia
Zheng L, Wang SJ, Wang JD, Tian Q (2016) Accurate image search with multi-scale contextual evidences. Int J Comput Vis 1:1–3
Zheng L, Zhao YL, Wang SJ, Wang JD, Tian Q (2016) Good practice in CNN feature transfer
Acknowledgements
This work is supported by National Natural Science Foundation of China under Grant 61876066, the 67th Chinese Postdoctoral Science Foundation (2020M672631), Guangdong Province Science and Technology Plan Project (Collaborative Innovation and Platform Environment Construction) 2019A050510006, Guangdong Science and Technology Plan Project 2018B050502006, and the EU Horizon 2020 Programme (700381, ASGARD).
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Ng, W.W.Y., Li, J., Tian, X. et al. Bit-wise attention deep complementary supervised hashing for image retrieval. Multimed Tools Appl 81, 927–951 (2022). https://doi.org/10.1007/s11042-021-11494-8
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-021-11494-8