Transfer Learning Based on Joint Feature Matching and Adversarial Networks

被引：0
作者：
Zhong H. [1 ]
Wang C. [1 ]
Tuo H. [1 ]
Hu J. [1 ]
Qiao L. [1 ]
Jing Z. [1 ]
机构：
[1] School of Aeronautics and Astronautics, Shanghai Jiao Tong University, Shanghai
来源：
Journal of Shanghai Jiaotong University (Science) | 2019年 / 24卷 / 06期
关键词：
A; adversarial networks; domain-invariant features; feature matching; TP; 181; transfer learning;
D O I：
10.1007/s12204-019-2132-0
中图分类号：
学科分类号：
摘要：
Domain adaptation and adversarial networks are two main approaches for transfer learning. Domain adaptation methods match the mean values of source and target domains, which requires a very large batch size during training. However, adversarial networks are usually unstable when training. In this paper, we propose a joint method of feature matching and adversarial networks to reduce domain discrepancy and mine domaininvariant features from the local and global aspects. At the same time, our method improves the stability of training. Moreover, the method is embedded into a unified convolutional neural network that can be easily optimized by gradient descent. Experimental results show that our joint method can yield the state-of-the-art results on three common public datasets. © 2019, Shanghai Jiao Tong University and Springer-Verlag GmbH Germany, part of Springer Nature.
引用
收藏
页码：699 / 705
页数：6
相关论文
共 24 条
  • [1] Pan S.J., Yang Q., A survey on transfer learning [J], IEEE Transactions on Knowledge and Data Engineering, 22, 10, pp. 1345-1359, (2010)
  • [2] Pan S.J., Tsang I.W., Kwok J.T., Et al., Domain adaptation via transfer component analysis [J], IEEE Transactions on Neural Networks, 22, 2, pp. 199-210, (2011)
  • [3] Gong B., Shi Y., Sha F., Et al., Geodesic flow kernel for unsupervised domain adaptation [C]//IEEE Conference on Computer Vision and Pattern Recognition, pp. 2066-2073, (2012)
  • [4] Long M.S., Cao Y., Wang J.M., Et al., Learning transferable features with deep adaptation networks [C]//32nd International Conference on Machine Learning, pp. 97-105, (2015)
  • [5] Long M.S., Zhu H., Wang J.M., Et al., Unsupervised domain adaptation with residual transfer networks [C]//30th Conference on Neural Information Processing Systems (NIPS 2016), pp. 136-144, (2016)
  • [6] Long M.S., Zhu H., Wang J.M., Et al., Deep transfer learning with joint adaptation networks [C]//34th International Conference on Machine Learning, pp. 2208-2217, (2017)
  • [7] Gretton A., Borgwardt K.M., Rasch M.J., Et al., A kernel two-sample test [J], Journal of Machine Learning Research, 13, 3, pp. 723-773, (2012)
  • [8] Ganin Y., Ustinova E., Ajakan H., Et al., Domainadversarial training of neural networks [J], Journal of Machine Learning Research, 17, 1, pp. 1-35, (2016)
  • [9] Tzeng E., Hoffman J., Saenko K., Et al., Adversarial discriminative domain adaptation [C]//IEEE Conference on Computer Vision and Pattern Recognition, pp. 7167-7176, (2017)
  • [10] Liu M.Y., Tuzel O., Coupled generative adversarial networks [C]//29th Conference on Neural Information Processing Systems (NIPS 2016), pp. 469-477, (2016)
123