Abstract
In the past few years in computer vision and machine learning, transfer learning has become an emerging research for leveraging richly labeled data in the source domain to construct a robust and accurate classifier for the target domain. Recent work on transfer learning has focused on learning shared feature representations by minimizing marginal and conditional distributions between domains for linear data sets only. However, they produce poor results if they deal with non-linear data sets. Therefore, in this paper, we put forward a novel framework called Kernelized Transfer Feature Learning on Manifold (KTFLM). KTFLM aims to align statistical differences and preserve the intrinsic geometric structure between the labeled source domain data and unlabeled target domain data. More specifically, we consider Maximum Mean Discrepancy for statistical alignment and Laplacian Regularization term for incorporating manifold structure. We experimented using benchmark data sets such as the PIE Face Recognition and the Office-Caltech (DeCAF features) object recognition dataset to discourse the limitations of the existing classical machine learning and domain adaptation methods. The performance comparison indicates that our model gave splendid accuracy of 79.41% and 91.97% for PIE and Office-Caltech data sets using linear and Gaussian kernels, respectively.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Courty, N., Flamary, R., Tuia, D., Rakotomamonjy, A.: Optimal transport for domain adaptation. IEEE Trans. Pattern Anal. Mach. Intell. 39(9), 1853ā1865 (2016)
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(7), 1414ā1430 (2016)
Gong, B., Shi, Y., Sha, F., Grauman, K.: Geodesic flow kernel for unsupervised domain adaptation. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp. 2066ā2073. IEEE (2012)
Gretton, A., Borgwardt, K., Rasch, M.J., Scholkopf, B., Smola, A.J.: A kernel method for the two-sample problem. arXiv preprint arXiv:0805.2368 (2008)
Long, M., Wang, J., Ding, G., Pan, S.J., Philip, S.Y.: Adaptation regularization: a general framework for transfer learning. IEEE Trans. Knowl. Data Eng. 26(5), 1076ā1089 (2013)
Long, M., Wang, J., Ding, G., Sun, J., Yu, P.S.: Transfer feature learning with joint distribution adaptation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2200ā2207 (2013)
Long, M., Wang, J., Ding, G., Sun, J., Yu, P.S.: Transfer joint matching for unsupervised domain adaptation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1410ā1417 (2014)
Luo, L., Chen, L., Hu, S., Lu, Y., Wang, X.: Discriminative and geometry-aware unsupervised domain adaptation. IEEE Trans. Cybern. 50(9), 3914ā3927 (2020)
Van der Maaten, L., Hinton, G.: Visualizing data using T-SNE. J. Mach. Learn. Res. 9(11) (2008)
Pan, S.J., Tsang, I.W., Kwok, J.T., Yang, Q.: Domain adaptation via transfer component analysis. IEEE Trans. Neural Networks 22(2), 199ā210 (2010)
Pan, S.J., Yang, Q.: A survey on transfer learning. IEEE Trans. Knowl. Data Eng. 22(10), 1345ā1359 (2010)
Sanodiya, R.K., Mathew, J., Paul, B., Jose, B.A.: A kernelized unified framework for domain adaptation. IEEE Access 7, 181381ā181395 (2019)
Sanodiya, R.K., Yao, L.: A subspace based transfer joint matching with Laplacian regularization for visual domain adaptation. Sensors 20(16), 4367 (2020)
Wang, J., Feng, W., Chen, Y., Yu, H., Huang, M., Yu, P.S.: Visual domain adaptation with manifold embedded distribution alignment. In: Proceedings of the 26th ACM International Conference on Multimedia, pp. 402ā410 (2018)
Zhang, J., Li, W., Ogunbona, P.: Joint geometrical and statistical alignment for visual domain adaptation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1859ā1867 (2017)
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
Ā© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Lekshmi, R., Sanodiya, R.K., Linda, R.J., Jose, B.R., Mathew, J. (2021). Kernelized Transfer Feature Learning on Manifolds. 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_26
Download citation
DOI: https://doi.org/10.1007/978-3-030-92270-2_26
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)