Abstract
To solve the current problem of low retrieval accuracy in deep hashing image retrieval, an improved generative adversarial network (GAN)-based image hashing retrieval method using supervised contrast learning (SconGAN) is proposed. The method augments training samples by introducing dense residual blocks and content fidelity items into the generative network to synthesize more diverse images with higher quality; moreover, it enhances the feature discrimination ability of the discriminative network by introducing pyramidal convolution and supervised contrast learning. Meanwhile, it improves the hashing code generation quality by introducing new pairwise similarity loss, semantic retention loss and quantization loss into the hashing network. In addition, discriminative networks and hashing networks share the core network structure to reduce resource consumption and improve training efficiency. Comprehensive experiments on the CIFAR-10 and NUS-WIDE benchmark datasets show that the proposed method greatly outperforms the comparison methods and obtains the best mean average precision (MAP).
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.References
Wang J, Zhang T, Song J, Sebe N, Shen HT (2018) A survey on learning to hash. IEEE Trans Pattern Anal Mach Intell 40(4):769–790
Pan Z, Wang L, Wang Y, Liu Y (2020) Product quantization with dual codebooks for approximate nearest neighbor search. Neurocomputing 401:59–68
Shen X, Zhang H, Li L, Zhang Z, Chen D, Liu L (2021) Clustering-driven deep adversarial hashing for scalable unsupervised cross-modal retrieval. Neurocomputing 459:152–164
Qin Q, Xian L, Xie K, Zhang W, Liu Y, Dai J, Wang C (2022) Deep multi-similarity hashing with semantic-aware preservation for multi-label image retrieval. Expert Syst Appl:117674
Cao Y, Liu B, Long M, Wang J (2018) Hashgan: Deep learning to hash with pair conditional wasserstein gan. In: 2018 IEEE/CVF conference on computer vision and pattern recognition, pp 1287–1296
Wang S, Kang X, Liu F, Nie X, Liu X (2022) Supervised discrete hashing for hamming space retrieval. Pattern Recogn Lett 154:16–21
Chen Y, Lu X, Li X (2020) Supervised deep hashing with a joint deep network. Pattern Recogn 105:107368
Gulrajani I, Ahmed F, Arjovsky M, Dumoulin V, Courville A (2017) Improved training of wasserstein gans. In: Proceedings of the 31st international conference on neural information processing systems, pp 5769–5779
Lopez-Martin M, Sanchez-Esguevillas A, Arribas JI, Carro B (2022) Supervised contrastive learning over prototype-label embeddings for network intrusion detection. Inf Fusion 79:200–228
Jie F, Nie Q, Li M, Yin M, Jin T (2021) Atrous spatial pyramid convolution for object detection with encoder-decoder. Neurocomputing 464:107–118
Chua T, Tang J, Hong R, Li H, Luo Z, Zheng Y (2009) Nus-wide: a real-world web image database from national university of singapore. In: Inproceedings of ACM international conference on image and video retrieval, pp 1–9
Krizhevsky A, Hinton G (2012) Learning multiple layers of features from tiny images. In: Tech report
Xia R, Pan Y, Lai H, Liu C, Yan S (2014) Supervised hashing for image retrieval via image representation learning. In: Proceedings of the Twenty-eighth AAAI conference on artificial intelligence, pp 2156–2162
Zhu H, Long M, Wang J, Cao Y (2016) Deep hashing network for efficient similarity retrieval. In: Proceedings of the srtieth AAAI conference on artificial intelligence, pp 2415–2421
Cao Z, Long M, Wang J, Yu PS (2017) Hashnet: Deep learning to hash by continuation. In: 2017 IEEE international conference on computer vision (ICCV), pp 5609–5618
Shi X, Xing F, Zhang Z, Sapkota M, Guo Z, Yang L (2021) A scalable optimization mechanism for pairwise based discrete hashing. IEEE Trans Image Process 30:1130–1142
Yang H-F, Tu C-H, Chen C-S (2021) Learning binary hash codes based on adaptable label representations. IEEE Trans Neural Netw Learn Syst (7):1–15
Yan C, Gong B, Wei Y, Gao Y (2021) Deep multi-view enhancement hashing for image retrieval. IEEE Trans Pattern Anal Mach Intell 43(04):1445–1451
Li X, Yu J, Wang Y, Chen J, Chang P, Li Z (2021) Dahp: deep attention-guided hashing with pairwise labels. IEEE Trans Circuits Syst Video Technol(3):1–14
Guo D, Xia Y, Xu L, Li W, Luo X (2021) Remote sensing image super-resolution using cascade generative adversarial nets. Neurocomputing 443:117–130
Odena A, Olah C, Shlens J (2017) Conditional image synthesis with auxiliary classifier gans. In: International conference on learning representations, p 15
Xu L, Zeng X, Li W, Bai L (2021) Idhashgan: deep hashing with generative adversarial nets for incomplete data retrieval. IEEE Trans Multimedia 10(1):1–12
Guo D, Xia Y, Luo X (2021) Self-supervised gans with similarity loss for remote sensing image scene classification. IEEE J Sel Top Appl Earth Obs Remote Sens 14:2508–2521
Qiu Z, Pan Y, Yao T (2017) Deep semantic hashing with generative adversarial networks. In: Proceedings of the 40th international ACM SIGIR Conference on research and development in information retrieval, pp 225–234
Ledig C, Theis L, Huszar F, Caballero J, Cunningham A, Acosta A, Aitken A, Tejani A, Totz J, Wang Z (2017) Photo-realistic single image super-resolution using a generative adversarial network. In: IEEE conference on computer vision and pattern recognition, pp 105–114
Xu L, Zeng X, Zhang H, Li W, Lei J, Huang Z (2020) Bpgan: bidirectional ct-to-mri prediction using multi-generative multi-adversarial nets with spectral normalization and localization. Neural Netw 128:82–96
Lai H, Pan Y, Liu Y, Yan S (2015) Simultaneous feature learning and hash coding with deep neural networks
Acknowledgements
The authors would like to thank the editors and reviewers for their outstanding comments and suggestions, which provide us with momentum and guidance to make deeper research into our subject matter and further improve our paper.This work was supported by the National Natural Science Foundation of China under Grants 41871226 and 41571401, the Science and Technology Research Project of Henan Province under Grants 212102210492, and the Science and Technology Research Project of Nanyang City under Grants KJGG102.
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
Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Lei, L., Guo, D., Shen, Z. et al. Image hashing retrieval based on generative adversarial networks. Appl Intell 53, 9056–9067 (2023). https://doi.org/10.1007/s10489-022-03970-x
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-022-03970-x