Abstract
Unsupervised domain adaptation aims to transfer the knowledge of source domain to a related but not labeled target domain. Due to the lack of label information of target domain, most existing methods train a weak classifier and directly apply to pseudo-labeling which may downgrade adaptation performance. To address this problem, in this paper, we propose a novel discriminative and selective pseudo-labeling (DSPL) method for domain adaptation. Specifically, we first match the marginal distributions of two domains and increase inter-class distance simultaneously. Then a feature transformation method is proposed to learn a low-dimensional transfer subspace which is discriminative enough. Finally, after data has formed good clusters, we introduce a structured prediction based selective pseudo-labeling strategy which is able to sufficiently exploit target data structure. We conduct extensive experiments on three popular visual datasets, demonstrating the good domian adaptation performance of our method.
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
Wang, Q., Breckon, T.P.: A survey on transfer learning. IEEE Trans. Knowl. Data Eng. 22(10), 1345–1359 (2010)
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)
Long, M., Wang, J., Ding, G., Sun, J., Yu, P.S.: Transfer feature learning with joint distribution adaptation. In: ICCV, pp. 2200–2207 (2013)
Wang, J., Chen, Y., Hao, S., Feng, W., Shen, Z.: Balanced distribution adaptation for transfer learning. In: ICDM, pp. 1129–1134 (2017)
Zhang, J., Li, W., Ogunbona, P.: Joint geometrical and statistical alignment for visual domain adaptation. In: CVPR, pp. 5150–5158 (2017)
Liang, J., He, R., Sun, Z., Tan, T.: Aggregating randomized clustering-promoting invariant projections for domain adaptation. IEEE Trans. Pattern Anal. Mach. Intell. 41(5), 1027–1042 (2019)
Li, S., Song, S., Huang, G., Ding, Z., Wu, C.: Domain invariant and class discriminative feature learning for visual domain adaptation. IEEE Trans. Image Process. 27(9), 4260–4273 (2018)
Wang, J., Feng, W., Chen, Y., Yu, H., Huang, M., Yu, P.S.: Visual domain adaptation with manifold embedded distribution alignment. In: ACM MM, pp. 402–410 (2018)
David, S.B., Blitzer, J., Crammer, K., Pereira, F.: Analysis of representations for domain adaptation. In: NIPS, pp. 137–144 (2006)
Tahmoresnezhad, Jafar, Hashemi, Sattar: Visual domain adaptation via transfer feature learning. Knowl. Inf. Syst. 50(2), 585–605 (2016). https://doi.org/10.1007/s10115-016-0944-x
Wang, Q., Breckon, T.P.: Unsupervised domain adaptation via structured prediction based selective Pseudo-Labeling. In: AAAI, pp. 6243–6250 (2020)
He, X., Niyogi, P.: Locality preserving projections. In: NIPS, pp. 153–160 (2003)
Fernando, B., Habrard, A., Sebban, M., Tuytelaars, T.: Unsupervised visual domain adaptation using subspace alignment. In: ICCV, pp. 2960–2967 (2013)
Sun, B., Feng, J., Saenko, K.: Return of frustratingly easy domain adaptation. In: AAAI, pp. 2058–2065 (2016)
Gong, B., Shi, Y., Sha, F., Grauman, K.: Geodesic flow kernel for unsupervised domain adaptation. In: CVPR, pp. 2066–2073 (2012)
Tzeng, E., Hoffman, J., Zhang, N., Saenko, K.: Darrell, T.: Deep domain confusion: maximizing for domain invariance. arXiv preprint arXiv:1412.3474abs/1412.3474 (2014)
Gretton, A., Borgwardt, K.M., Rasch, M.J., Schölkopf, B., Smola, A.J.: A Kernel two-sample test. J. Mach. Learn. Res. 13, 723–773 (2012)
Long, M., Cao, Y., Wang, J., Jordan, M.I.: Learning transferable features with deep adaptation networks. In: ICML, pp. 97–105 (2015)
Long, M., Zhu, H., Wang, J., Jordan, M.I.: Deep transfer learning with joint adaptation networks. In: ICML, pp. 2208–2217 (2017)
Kang, G., Jiang, L., Yang, Y., Hauptmann, A.G.: Unsupervised domain adaptation with similarity learning. In: CVPR, pp. 4893–4902 (2018)
Ganin, Y., Lempitsky, V.S.: Unsupervised domain adaptation by backpropagation. In: ICML, pp. 1180–1189 (2015)
Zhang, W., Ouyang, W., Li, W., Xu, D.: Collaborative and adversarial network for unsupervised domain adaptation. In: CVPR, pp. 3801–3809 (2018)
Luo, L., Chen, L., Lu, Y., Hu, S.: Discriminative label consistent domain adaptation. arXiv preprint arXiv:1802.08077 (2018)
Yu, W., Teng, X., Liu, C.: Face recognition using discriminant locality preserving projections. Image Vis. Comput. 24(3), 239–248 (2006)
Zhang, Z., Saligrama, V.: Zero-shot recognition via structured prediction. In: ECCV, pp. 533–548 (2016)
Donahue, J., Jia, Y., Vinyals, O., Hoffman, J., Zhang, N., Tzeng, E.: DeCAF: a deep convolutional activation feature for generic visual recognition. In: ICML, pp. 647–655 (2014)
Wang, Q., Bu, P., Breckon, T.P.: Unifying unsupervised domain adaptation and zero-shot visual recognition. In: IJCNN, pp. 1–8 (2019)
Acknowledgment
This work was funded by the National Natural Science Foundation of China (Grant No. 61303093, 61402278).
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
Wang, F., Ding, Y., Liang, H., Wen, J. (2021). Discriminative and Selective Pseudo-Labeling for Domain Adaptation. In: Lokoč, J., et al. MultiMedia Modeling. MMM 2021. Lecture Notes in Computer Science(), vol 12572. Springer, Cham. https://doi.org/10.1007/978-3-030-67832-6_30
Download citation
DOI: https://doi.org/10.1007/978-3-030-67832-6_30
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-67831-9
Online ISBN: 978-3-030-67832-6
eBook Packages: Computer ScienceComputer Science (R0)