Volume 29 Issue 6
Dec.  2020
Turn off MathJax
Article Contents
ZHANG Yun, WANG Nianbin, CAI Shaobin, “Learning Domain-Invariant and Discriminative Features for Homogeneous Unsupervised Domain Adaptation,” Chinese Journal of Electronics, vol. 29, no. 6, pp. 1119-1125, 2020, doi: 10.1049/cje.2020.09.013
Citation: ZHANG Yun, WANG Nianbin, CAI Shaobin, “Learning Domain-Invariant and Discriminative Features for Homogeneous Unsupervised Domain Adaptation,” Chinese Journal of Electronics, vol. 29, no. 6, pp. 1119-1125, 2020, doi: 10.1049/cje.2020.09.013

Learning Domain-Invariant and Discriminative Features for Homogeneous Unsupervised Domain Adaptation

doi: 10.1049/cje.2020.09.013
Funds:  This work is supported by the National Natural Science Foundation of China (No.61772152), the National Key Research and Development Program of China (No.2018YFC0806800), the Technical Basic Research Project (No.JSQB2017206C002), the Project funded by China Postdoctoral Science Foundation (No.2019M651262), the Youth Fund Project of Humanities and Social Sciences Research of the Ministry of Education of China (No.20YJCZH172), and the Postdoctoral Foundation of Heilongjiang Province (No.LBH-Z19015).
More Information
  • Corresponding author: WANG Nianbin (corresponding author) was born in 1967. He received the Ph.D. degree in computer science and technology from Harbin Institute of Technology. He is currently a professor with the College of Computer Science and Technology, Harbin Engineering University. He is a member of China Computer Federation (CCF). His main research interests include dataspace, deep learning, and data integration. (Email:wangnianbin@hrbeu.edu.cn)
  • Received Date: 2019-10-30
  • Publish Date: 2020-12-25
  • A classifier trained on the label-rich source dataset tends to perform poorly on the unlabeled target dataset because of the distribution discrepancy across different datasets. Unsupervised domain adaptation aims to transfer knowledge from the labeled source dataset to the unlabeled target dataset to solve this problem. Most of the existing unsupervised domain adaptation methods only concentrate on learning domain-invariant features across different domains, but they neglect the discriminability of the learned features to satisfy the cluster assumption. In this paper, we propose Semantic pairwise centroid alignment (SPCA), which is a point-wise method to learn both domain-invariant and discriminative features for homogeneous unsupervised domain adaptation. SPCA utilizes a novel semantic centroid loss to reduce the intraclass distance in feature space by using source data and target High-confidence centroid points (HCCPs). Then a classifier trained on source features is expected to generalize well on target features. Extensive experiments on visual recognition tasks verify the effectiveness of the proposed SPCA and also demonstrate that both domaininvariant and discriminative features learned by SPCA can significantly boost the performance of homogeneous unsupervised domain adaptation.
  • loading
  • L. Yu, X. Wu and Y. Yang, "An online education data classification model based on tr_madaboost algorithm", Chinese Journal of Electronics, Vol.28, No.1, pp.21-28, 2019.
    X. Wang, Y. Ma, Y. Cheng, et al., "Domain adaptation network based on autoencoder", Chinese Journal of Electronics, Vol.27, No.6, pp.1258-1264, 2018.
    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.
    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.
    K. Saito, K. Watanabe, Y. Ushiku, et al., "Maximum classifier discrepancy for unsupervised domain adaptation", Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, Utah, USA, pp.3723-3732, 2018.
    M. Long, Y. Cao, J. Wang, et al., "Learning transferable features with deep adaptation networks", Proc. of the 32nd International Conference on Machine Learning, Lille, France, pp.97-105, 2015.
    E. Tzeng, J. Hoffman, K. Saenko, et al., "Adversarial discriminative domain adaptation", Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, Hawaii, USA, pp.2962-2971, 2017.
    X. Chen, S. Wang, M. Long, et al., "Transferability vs. discriminability:Batch spectral penalization for adversarial domain adaptation", Proc. of the 36th International Conference on Machine Learning, Long Beach, California, USA, pp.1081-1090, 2019.
    S. Lee, D. Kim, N. Kim, et al., "Drop to adapt:Learning discriminative features for unsupervised domain adaptation", Proc. of IEEE International Conference on Computer Vision, Seoul, Korea, pp.91-100, 2019.
    S. Xie, Z. Zheng, L. Chen, et al., "Learning semantic representations for unsupervised domain adaptation", Proc. of the 35th International Conference on Machine Learning, Stockholm, Sweden, pp.5419-5428, 2018.
    S. Ben-David, J. Blitzer, K. Crammer, et al., "A theory of learning from different domains", Machine Learning, Vol.79, No.1-2, pp.151-175, 2010.
    J. Zhang, W. Li and P. Ogunbona, "Joint geometrical and statistical alignment for visual domain adaptation", Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, Hawaii, USA, pp.5150-5158, 2017.
    S. Li, S. Song, G. Huang, et al., "Domain invariant and class discriminative feature learning for visual domain adaptation", IEEE Transactions on Image Processing, Vol.27, No.9, pp.4260-4273, 2018.
    Y. Cao, M. Long and J. Wang, "Unsupervised domain adaptation with distribution matching machines", Proc. of the Thirty-Second AAAI Conference on Artificial Intelligence, New Orleans, Louisiana, USA, pp.2795-2802, 2018.
    E. Tzeng, J. Hoffman, N. Zhang, et al., "Deep domain confusion:Maximizing for domain invariance", arXiv preprint arXiv:1412.3474, 2014.
    B. Sun and K. Saenko, "Deep coral:Correlation alignment for deep domain adaptation", Proc. of the 14th European Conference on Computer Vision Workshops, Amsterdam, Netherlands, pp.443-450, 2016.
    J. Shen, Y. Qu, W. Zhang, et al., "Wasserstein distance guided representation learning for domain adaptation", Proc. of the Thirty-Second AAAI Conference on Artificial Intelligence, New Orleans, Louisiana, USA, pp.4058-4065, 2018.
    Y. Ganin, E. Ustinova, H. Ajakan, et al., "Domain-adversarial training of neural networks", The Journal of Machine Learning Research, Vol.17, No.1, pp.2096-2030, 2016.
    M. Long, H. Zhu, J. Wang, et al., "Unsupervised domain adaptation with residual transfer networks", Advances in Neural Information Processing Systems 29, Curran Associates, Inc., New York, NY, USA, pp.136-144, 2016.
    M. Long, H. Zhu, J. Wang, et al., "Deep transfer learning with joint adaptation networks", Proc. of the 34th International Conference on Machine Learning, Sydney, Australia, pp.2208-2217, 2017.
    Z. Pei, Z. Cao, M. Long, et al., "Multi-adversarial domain adaptation", Proc. of the Thirty-Second AAAI Conference on Artificial Intelligence, New Orleans, Louisiana, USA, pp.3934-3941, 2018.
    M. Long, Z. Cao, J. Wang, et al., "Conditional adversarial domain adaptation", Advances in Neural Information Processing Systems 31, Curran Associates, Inc., New York, NY, USA, pp.1640-1650, 2018.
    C. Yu, J. Wang, Y. Chen, et al., "Transfer learning with dynamic adversarial adaptation network", Proc. of the 2019 IEEE International Conference on Data Mining, Beijing, China, pp.778-786, 2019.
    A. Paszke, S. Gross, F. Massa, et al., "Pytorch:An imperative style, high-performance deep learning library", Advances in Neural Information Processing Systems 32, Curran Associates, Inc., New York, NY, USA, pp.8026-8037, 2019.
  • 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 (559) PDF downloads(89) Cited by()
    Proportional views
    Related

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return