WANG Xuesong, MA Yuting, CHENG Yuhu. Domain Adaptation Network Based on Autoencoder[J]. Chinese Journal of Electronics, 2018, 27(6): 1258-1264. doi: 10.1049/cje.2018.09.001
Citation: WANG Xuesong, MA Yuting, CHENG Yuhu. Domain Adaptation Network Based on Autoencoder[J]. Chinese Journal of Electronics, 2018, 27(6): 1258-1264. doi: 10.1049/cje.2018.09.001

Domain Adaptation Network Based on Autoencoder

doi: 10.1049/cje.2018.09.001
Funds:  This work is supported by the National Natural Science Foundation of China (No.61472424).
More Information
  • Corresponding author: CHENG Yuhu (corresponding author) received the Ph.D. degree from the Institute of Automation, Chinese Academy of Sciences in 2005. He is currently a professor in the School of Information and Control Engineering, China University of Mining and Technology. His main research interests include machine learning and intelligent system. (Email:chengyuhu@163.com)
  • Received Date: 2016-05-12
  • Rev Recd Date: 2016-07-07
  • Publish Date: 2018-11-10
  • The domain adaptation uses labeled source domain data to train a classifier to be used in the target domain with no or small amount of labeled data. Usually there exists discrepancy in terms of marginal and conditional distributions for both source and target domains, which is of critical importance to minimize the distribution discrepancy between domains. As a classical model in deep learning, the autoencoder is capable of realizing distribution matching and enhancing classification accuracy by extracting more abstract and effective features from data. A Domain adaptation network based on autoencoder (DANA) is proposed. The DANA structure consists of a couple of encoding layers:a feature extraction layer and a classification layer. For the feature extraction layer, the marginal distributions of source and target domains are matched by using the nonparametric maximum mean discrepancy measurement. For the classification layer, the softmax regression model is applied to encode the label information of source domains meanwhile to match the conditional distribution. Experimental results on ImageNet, Corel and Leaves datasets have shown the enhanced classification accuracy by our proposed algorithm compared with the classical methods.
  • loading
  • S.J. Pan and Q. Yang, “A survey on transfer learning”, IEEE Transactions on Knowledge and Data Engineering, Vol.22, No.10, pp.1345-1359, 2010.
    G. Matasci, M. Volpi, M. Kanevski, et al., “Semisupervised transfer component analysis for domain adaptation in remote sensing image classification”, IEEE Transactions on Geoscience and Remote Sensing, Vol.53, No.7, pp.3550-3564, 2015.
    J. Gao and L. Huang, “Maximum local weighted mean discrepancy embedding”, Acta Electronica Sinica, Vol.41, No.8, pp.1462-1468, 2013. (in Chinese)
    J.X. Zhang, S.T. Wang, Z.H. Deng, et al., “Symbiosis transfer learning method with collaborative constraints”, Acta Electronica Sinica, Vol.42, No.3, pp.556-560, 2014. (in Chinese)
    Q. Qiu and R. Chellappa, “Compositional dictionaries for domain adaptive face recognition”, IEEE Transactions on Image Processing, Vol.24, No.12, pp.5152-5165, 2015.
    H. Yin, F. Pine and Z. Sun, “Face feature selection and recognition using separability criterion and binary particle swarm optimization slgorithm”, Chinese Journal of Electronics, Vol.23, No.2, pp.361-365, 2014.
    A. Bewley and B. Upcroft, “From ImageNet to mining: Adapting visual object detection with minimal supervision”, Proc. of International Conference on Field and Service Robotics, Toronto, ON, Canada, Vol.113, No.30, pp.501-514, 2016.
    W.S. Chu, I.T.F. De and J.F. Cohn, “Selective transfer machine for personalized facial action unit detection”, Proc. of IEEE Conference on Computer Vision and Pattern Recognition, Portland, OR, USA, pp.3515-3522, 2013.
    S.J. Pan, I.W. Tsang, J.T. Kwok, et al., “Domain adaptation via transfer component analysis”, IEEE Transactions on Neural Networks, Vol.22, No.2, pp.199-210, 2011.
    B. Gong, K. Grauman and F. Sha, “Connecting the dots with landmarks: Discriminatively learning domain-invariant features for unsupervised domain adaptation”, Proc. of the 30th International Conference on Machine Learning, Atlanta, GA, USA, pp.222-230, 2013.
    M. Long, J. Wang, G. Ding, et al., “Transfer feature learning with joint distribution adaptation”, Proc. of IEEE International Conference on Computer Vision, Sydney, NSW, Australia, pp.2200-2207, 2013.
    M. Long, J. Wang, G. Ding, et al., “Transfer joint matching for unsupervised domain adaptation”, Proc. of IEEE Conference on Computer Vision and Pattern Recognition, Columbus, OH, USA, pp.1410-1417, 2014.
    Z. Lian, X. Jing, X. Wang, et al., “DropConnect regularization method with sparsity constraint for neural networks”, Chinese Journal of Electronics, Vol.25, No.1, pp.152-158, 2016.
    P. Li, L. Peng and J. Wen, “Rejecting character recognition errors using CNN based confidence estimation”, Chinese Journal of Electronics, Vol.25, No.3, 2016.
    P. Vincent, H. Larochelle, I. Lajoie, et al., “Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion”, The Journal of Machine Learning Research, Vol.11, No.6, pp.3371-3408, 2010.
    M. Chen, Z. Xu, K. Weinberger, et al., “Marginalized denoising autoencoders for domain adaptation”, Proc. of the 29th International Conference on Machine Learning, Edinburgh, United kingdom, pp.767-774, 2012.
    F. Zhuang, X. Cheng, P. Luo, et al., “Supervised representation learning: Transfer learning with deep autoencoders”, Proc. of the 24th International Conference on Artificial Intelligence, Buenos Aires, Argentina, pp.4119-4125, 2015.
    X. Zhang, X.F. Yu, S.F. Chang, et al., “Deep transfer network: Unsupervised domain adaptation”, arXiv Preprint arXiv:1503.00591, 2015.
    B. Schőlkopf, J. Platt, T. Hofmann, et al., “A kernel method for the two-sample-problem”, Proc. of Advances in neural information processing systems, Vancouver, BC, Canada, pp.513-520, 2006.
    J. Friedman, T. Hastie and R. Tibshirani, “Regularization paths for generalized linear models via coordinate descent”, Journal of Statistical Software, Vol.33, No.1, pp.1-22, 2010.
    L. Van der Maaten and G. Hinton, “Visualizing data using tSNE”, Journal of Machine Learning, Vol.9, pp.2579-2625, 2008.
  • 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 (124) PDF downloads(251) Cited by()
    Proportional views
    Related

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return