JIN Guoqing, ZHANG Yongdong, LU Ke, “Deep Hashing Based on VAE-GAN for Efficient Similarity Retrieval,” Chinese Journal of Electronics, vol. 28, no. 6, pp. 1191-1197, 2019, doi: 10.1049/cje.2019.08.001
Citation: JIN Guoqing, ZHANG Yongdong, LU Ke, “Deep Hashing Based on VAE-GAN for Efficient Similarity Retrieval,” Chinese Journal of Electronics, vol. 28, no. 6, pp. 1191-1197, 2019, doi: 10.1049/cje.2019.08.001

Deep Hashing Based on VAE-GAN for Efficient Similarity Retrieval

doi: 10.1049/cje.2019.08.001
Funds:  This work is supported by the National Key Research and Development Program of China (No.2017YFB1002203), the National Nature Science Foundation of China (No.61525206, No.61672495, No.61771458, No.61702479, No.61571424).
More Information
  • Corresponding author: ZHANG Yongdong (corresponding author) received the Ph.D.degree in electronics engineering from Tianjin University,Tianjin,in 2002.He is currently a Professor with University of Science and Technology of China,Hefei.His current research interests are in the fields of multimedia content analysis and understanding,multimedia content security and video encoding.He serves as an Editorial Board Member of the Multimedia Systems Journal and IEEE Transactions on Multimedia (TMM).(Email:zhyd73@ustc.edu.cn)
  • Received Date: 2018-04-09
  • Rev Recd Date: 2018-04-28
  • Publish Date: 2019-11-10
  • Inspired by the recent advances in generative networks, we propose a VAE-GAN based hashing framework for fast image retrieval. The method combines a Variational autoencoder (VAE) with a Generative adversarial network (GAN) to generate content preserving images for pairwise hashing learning. By accepting real image and systhesized image in a pairwise form, a semantic perserving feature mapping model is learned under a adversarial generative process. Each image feature vector in the pairwise is converted to a hash codes, which are used in a pairwise ranking loss that aims to preserve relative similarities on images. Extensive experiments on several benchmark datasets demonstrate that the proposed method shows substantial improvement over the state-of-the-art hashing methods.
  • loading
  • S. Wan, P. Jin, Y. Xia, et al., "Incorporating Spatial Distribution Feature with Local Patterns for Content-Based Image Retrieval", Chinese Journal of Electronics, Vol.25, No.5, pp.873-879, 2016.
    X. Gong, C. Wang, Y. Xiong, et al., "Similar Time Series Retrieval Using Only Important Segments", Chinese Journal of Electronics, Vol.26, No.1, pp.22-26, 2017.
    R. Xia, Y. Pan, H. Lai, Cong Liu, et al., "Supervised hashing for image retrieval via image representation learning", Proc. of AAAI Conference on Artificial Intelligence, Québec City, Québec, Canada, pp.2156-2162, 2014.
    H. Lai, Y. Pan, Y. Liu, et al., "Simultaneous feature learning and hash coding with deep neural networks", Proc. of IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA, pp.3270-3278, 2015.
    H. Zhu, M. Long, J. Wang, et al., "Deep hashing network for efficient similarity retrieval", Proc. of AAAI Conference on Artificial Intelligence, Phoenix, Arizona USA, pp.2415-2421, 2016.
    S. Zhu, J. Du and R. Nan, "A novel simple visual tracking algorithm based on hashing and deep learning", Chinese Journal of Electronics, Vol.26, No.5, pp.1073-1078, 2017.
    Q. Guo, L. Wang and S. Shen, "Multiple-channel local binary fitting model for medical image segmentation", Chinese Journal of Electronics, Vol.24, No.4, pp.802-806, 2015.
    I. Goodfellow, J. Pouget-Abadie, M. Mirza, et al., "Generative adversarial nets", Proc. of International Conference on Neural Information Processing Systems, Montréal, Canada, pp.2672-2680, 2014.
    D. Kingma and M. Welling, "Auto-encoding variational bayes", arXiv:1312.6114, 2013.
    Y. Gong, S. Lazebnik, A. Gordo, et al., "Iterative quantization:A procrustean approach to learning binary codes for large-scale image retrieval", IEEE Transactions on Pattern Analysis Machine Intelligence, Vol.35, No.12, pp.2916-2929, 2013.
    J. Hou, D. Li, C. Qiu, et al., "A semantic retrieval model based on domain ontology of orchard disease and pests", Chinese Journal of Electronics, Vol.25, No.3, pp.460-466, 2016.
    B. Kulis and T. Darrell, "Learning to hash with binary reconstructive embeddings", Proc. of International Conference on Neural Information Processing Systems, Vancouver, B.C., Canada, pp.1042-1050, 2009.
    Norouzi M, "Minimal loss hashing for compact binary codes", Proc. of International Conference on Neural Information Processing Systems, Granada, Spain, pp.353-360, 2011.
    S. Chang, "Supervised hashing with kernels", Proc. of IEEE Conference on Computer Vision and Pattern Recognition, Providence, Rhode Island, pp.2074-2081, 2012.
    J. Wang, S. Kumar and S. Chang, "Semi-supervised hashing for scalable image retrieval", Proc. of IEEE Conference on Computer Vision and Pattern Recognition, San Francisco, Usa, pp.3424-3431, 2010.
    F. Zhao, Y. Huang, L. Wang, et al., "Deep semantic ranking based hashing for multi-label image retrieval", Proc. of IEEE Conference on Computer Vision and Pattern Recognition, Boston, USA, pp.1556-1564, 2015.
    Z. Cao, M. Long, J. Wang, et al., "Hashnet:Deep learning to hash by continuation", Proc. of IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, Hawaii, USA, pp.5609-5618, 2017.
    Z. Qiu, Y. Pan, T Yao, et al., "Deep semantic hashing with generative adversarial networks", Proc. of International ACM SIGIR Conference on Research and Development in Information Retrieval, Tokyo, Japan, pp.225-234, 2017.
    B. Wang, Y. Yang, X. Xu, et al., "HT Shen. adversarial crossModal retrieval", Proc. of ACM on Multimedia Conference, Mountain View, CA USA, pp.154-162, 2017.
    Song J, "Binary generative adversarial networks for image retrieval", arXiv:1708.04150v1, 2017.
    G. Hinton and R Salakhutdinov, "Reducing the dimensionality of data with neural networks", Science, Vol.313, No.5786, pp.504, 2006.
    Vinod Nair and G. Hinton, "Rectified linear units improve restricted boltzmann machines", Proc. of International Conference on International Conference on Machine Learning, Haifa, Israel, pp.807-814, 2010.
    Y. Bengio, E. Thibodeau-Laufer, G. Alain, et al., "Deep generative stochastic networks trainable by backprop", Computer Science, Vol.2, pp.226-234, 2013.
    M. Mirza and S. Osindero, "Conditional generative adversarial nets", arXiv:1411.1784, 2014.
    E. Denton, S. Chintala, R. Fergus, "Deep generative image models using a laplacian pyramid of adversarial networks", Proc. of International Conference on Neural Information Processing Systems, Montréal Canada, pp.1486-1494, 2015.
    A. Radford, L. Metz, and S. Chintala, "Unsupervised representation learning with deep convolutional generative adversarial networks", arXiv:1511.06434, 2015.
    M. Arjovsky, S. Chintala, and L. Bottou, "Wasserstein gan", arXiv:1701.07875, 2017.
    J. Bao, D. Chen, F. Wen, et al., "Cvae-gan:Finegrained image generation through asymmetric training", arXiv:1703.10155, 2017.
    A. Gionis, P. Indyk, and R. Motwani, "Similarity search in high dimensions via hashing", Proc. of International Conference on Very Large Data Bases, Edinburgh, Scotland, pp.518-529, 1999.
    Y. Weiss, A. Torralba, and R. Fergus, "Spectral hashing", Proc. of International Conference on Neural Information Processing Systems, Vancouver, B.C., Canada, pp.1753-1760, 2008.
    M. Abadi, A. Agarwal, P. Barham, et al., "TensorFlow:Large-scale machine learning on heterogeneous distributed systems", arXiv:1603.04467, 2016.
  • 加载中

Catalog

    通讯作者: 陈斌, bchen63@163.com
    • 1. 

      沈阳化工大学材料科学与工程学院 沈阳 110142

    1. 本站搜索
    2. 百度学术搜索
    3. 万方数据库搜索
    4. CNKI搜索

    Article Metrics

    Article views (677) PDF downloads(279) Cited by()
    Proportional views
    Related

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return