Abstract
This paper proposes manifold discriminative transfer learning (MDTL) for traditional unsupervised domain adaptation. It first utilizes manifold subspace learning to reconstruct the original data in both source and target domains, which can reduce the domains shifts, then performs simultaneously structural risk minimization, discriminative class level alignment, and manifold regularization for transfer learning. More specifically, it minimizes the intra-class distribution discrepancy to improve the domain transferability, maximizes the inter-class distribution discrepancy to improve the class discriminability, and also maintains geometrical structures of the data samples. Remarkably, MDTL is a traditional transfer learning approach and it has a closed-form solution, so the computational cost is low. Extensive experiments showed that MDTL outperforms several state-of-the-art traditional domain adaptation approaches.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Borgwardt, K.M., Gretton, A., Rasch, M.J., Kriegel, H., Scholkopf, B., Smola, A.J.: Integrating structured biological data by kernel maximum mean discrepancy. In: Proceedings 14th International Conference on Intelligent Systems for Molecular Biology, Fortaleza, Brazil, pp. 49–57, August 2006
Chen, X., Wang, S., Long, M., Wang, J.: Transferability vs. discriminability: batch spectral penalization for adversarial domain adaptation. In: Proceedings 36th International Conference on Machine Learning, Long Beach, California, pp. 1081–1090, June 2019
Donahue, J., et al.: DeCAF: a deep convolutional activation feature for generic visual recognition. In: Proceedings International Conference on Machine Learning, Beijing, China, pp. 647–655, June 2014
Fernando, B., Habrard, A., Sebban, M., Tuytelaars, T.: Unsupervised visual domain adaptation using subspace alignment. In: Proceedings IEEE International Conference on Computer Vision, Sydney, Australia, pp. 2960–2967, December 2013
Ghifary, M., Balduzzi, D., Kleijn, W.B., Zhang, M.: Scatter component analysis: a unified framework for domain adaptation and domain generalization. IEEE Trans. Pattern Anal. Mach. Intell. 39, 1414–1430 (2017)
Gong, B., Shi, Y., Sha, F., Grauman, K.: Geodesic flow kernel for unsupervised domain adaptation. In: Proceedings IEEE Conference on Computer Vision and Pattern Recognition, Providence, RI, pp. 2066–2073, June 2012
Gopalan, R., Li, R., Chellappa, R.: Domain adaptation for object recognition: an unsupervised approach. In: Proceedings IEEE International Conference on Computer Vision, Barcelona, Spain, pp. 999–1006, November 2011
Hull, J.J.: A database for handwritten text recognition research. IEEE Trans Pattern Anal. Mach. Intell. 16(5), 550–554 (1994)
Kang, G., Jiang, L., Yang, Y., Hauptmann, A.G.: Contrastive adaptation network for unsupervised domain adaptation. In: Proceedings IEEE Conference on Computer Vision and Pattern Recognition, Long Beach, CA, pp. 4893–4902, June 2019
LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998)
Long, M., Wang, J., Ding, G., Pan, S.J., Yu, P.S.: Adaptation regularization: a general framework for transfer learning. IEEE Trans. Knowl. Data Eng. 26(5), 1076–1089 (2014)
Long, M., Wang, J., Ding, G., Sun, J., Yu, P.S.: Transfer feature learning with joint distribution adaptation. In: Proceedings IEEE International Conference on Computer Vision, Sydney, Australia, pp. 2200–2207, December 2013
Long, M., Wang, J., Ding, G., Sun, J., Yu, P.S.: Transfer joint matching for unsupervised domain adaptation. In: Proceedings IEEE Conference on Computer Vision and Pattern Recognition, Columbus, OH, pp. 1410–1417, June 2014
Pan, S.J., Tsang, I.W., Kwok, J.T., Yang, Q.: Domain adaptation via transfer component analysis. IEEE Trans. Neural Netw. 22(2), 199–210 (2011)
Pan, S.J., Yang, Q.: A survey on transfer learning. IEEE Trans. Knowl. Data Eng. 22(10), 1345–1359 (2010)
Scholkopf, B., Smola, A.J.: Learning with Kernels: support vector machines, regularization, optimization, and beyond. Adaptive Computation and Machine Learning Series. MIT Press (2002)
Sun, B., Feng, J., Saenko, K.: Return of frustratingly easy domain adaptation. In: Proceedings 30th AAAI Conference on Artificial Intelligence, Phoenix, Arizona, pp. 2058–2065, February 2016
Wang, J., Chen, Y., Hao, S., Feng, W., Shen, Z.: Balanced distribution adaptation for transfer learning. In: Proceedings IEEE International Conference on Data Mining, New Orleans, LA, pp. 1129–1134, November 2017
Wang, J., Feng, W., Chen, Y., Yu, H., Huang, M., Yu, P.S.: Visual domain adaptation with manifold embedded distribution alignment. In: Proceedings ACM International Conference on Multimedia, Seoul, Republic of Korea, pp. 402–410, October 2018
Wu, D., Huang, J.: Affect estimation in 3D space using multi-task active learning for regression. IEEE Trans. Affect. Comput. (2021 in Press)
Wu, D., Xu, Y., Lu, B.L.: Transfer learning for EEG-based brain-computer interfaces: a review of progress made since 2016. IEEE Trans. Cogn. Dev. Syst. (2020, in Press)
Zhang, J., Li, W., Ogunbona, P.: Joint geometrical and statistical alignment for visual domain adaptation. In: Proceedings IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, pp. 5150–5158, July 2017
Zhang, W., Deng, L., Zhang, L., Wu, D.: Overcoming negative transfer: a survey (2020). https://arxiv.org/abs/2009.00909
Zhang, W., Wu, D.: Discriminative joint probability maximum mean discrepancy (DJP-MMD) for domain adaptation. In: Proceedings International Joint Conference on Neural Networks, Glasgow, UK, pp. 1–8, July 2020
Zhang, Y., Tang, H., Jia, K., Tan, M.: Domain-symmetric networks for adversarial domain adaptation. In: Proceedings IEEE Conference on Computer Vision and Pattern Recognition, Long Beach, CA, pp. 5031–5040, June 2019
Acknowledgments
This research was supported by the Hubei Province Funds for Distinguished Young Scholars under Grant 2020CFA050, the Key Laboratory of Brain Machine Collaborative Intelligence of Zhejiang Province under Grant 2020E10010-01, the Technology Innovation Project of Hubei Province of China under Grant 2019AEA171, the National Natural Science Foundation of China under Grants 61873321 and U1913207, and the International Science and Technology Cooperation Program of China under Grant 2017YFE0128300.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Quan, X., Wu, D., Zhu, M., Xia, K., Deng, L. (2021). Manifold Discriminative Transfer Learning for Unsupervised Domain Adaptation. In: Mantoro, T., Lee, M., Ayu, M.A., Wong, K.W., Hidayanto, A.N. (eds) Neural Information Processing. ICONIP 2021. Lecture Notes in Computer Science(), vol 13109. Springer, Cham. https://doi.org/10.1007/978-3-030-92270-2_28
Download citation
DOI: https://doi.org/10.1007/978-3-030-92270-2_28
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-92269-6
Online ISBN: 978-3-030-92270-2
eBook Packages: Computer ScienceComputer Science (R0)