Abstract
Unsupervised domain adaptation aims to transfer knowledge from a labeled source domain to an unlabeled target domain. Previous methods focus on learning domain-invariant features to decrease the discrepancy between the feature distributions as well as minimizing the source error and have made remarkable progress. However, a recently proposed theory reveals that such a strategy is not sufficient for a successful domain adaptation. It shows that besides a small source error, both the discrepancy between the feature distributions and the discrepancy between the labeling functions should be small across domains. The discrepancy between the labeling functions is essentially the cross-domain errors which are ignored by existing methods. To overcome this issue, in this paper, a novel method is proposed to integrate all the objectives into a unified optimization framework. Moreover, the incorrect pseudo labels widely used in previous methods can lead to error accumulation during learning. To alleviate this problem, the pseudo labels are obtained by utilizing structural information of the target domain besides source classifier and we propose a curriculum learning based strategy to select the target samples with more accurate pseudo-labels during training. Comprehensive experiments are conducted, and the results validate that our approach outperforms state-of-the-art methods.
Y. Chen and F. Cui—Equal contribution.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Ben-David, S., Blitzer, J., Crammer, K., Kulesza, A., Pereira, F., Vaughan, J.W.: A theory of learning from different domains. Mach. Learn. 151–175 (2009). https://doi.org/10.1007/s10994-009-5152-4
Bengio, Y., Louradour, J., Collobert, R., Weston, J.: Curriculum learning. In: ICML 2009 (2009)
Cao, Y., Long, M., Wang, J.: Unsupervised domain adaptation with distribution matching machines. AAAI (2018)
Chen, C., Chen, Z., Jiang, B., Jin, X.: Joint domain alignment and discriminative feature learning for unsupervised deep domain adaptation. AAAI (2019)
Chen, C., et al.: Progressive feature alignment for unsupervised domain adaptation. In: CVPR, pp. 627–636 (2018)
Chen, Q., Du, Y., Tan, Z., Zhang, Y., Wang, C.: Unsupervised domain adaptation with joint domain-adversarial reconstruction networks. In: ECML/PKDD (2020)
Dai, W., Yang, Q., Xue, G.R., Yu, Y.: Boosting for transfer learning. In: ICML 2007 (2007)
Delany, S.J.: k-nearest neighbour classifiers (2007)
Donahue, J., et al.: DeCAF: a deep convolutional activation feature for generic visual recognition. In: ICML (2014)
Evgeniou, T., Pontil, M.: Support vector machines: theory and applications. In: Paliouras, G., Karkaletsis, V., Spyropoulos, C.D. (eds.) ACAI 1999. LNCS (LNAI), vol. 2049, pp. 249–257. Springer, Heidelberg (2001). https://doi.org/10.1007/3-540-44673-7_12
Gong, B., Shi, Y., Sha, F., Grauman, K.: Geodesic flow kernel for unsupervised domain adaptation. In: CVPR, pp. 2066–2073 (2012)
Graf, A.B.A., Bousquet, O., Rätsch, G., Schölkopf, B.: Prototype classification: insights from machine learning. Neural Comput. 21(1), 272–300 (2009)
Griffin, G., Holub, A., Perona, P.: Caltech-256 object category dataset (2007)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770–778 (2016)
Hotelling, H.: Analysis of a complex of statistical variables into principal components. J. Educ. Psychol. 24, 498–520 (1933)
Jing, M., Li, J., Zhao, J., Lu, K.: Learning distribution-matched landmarks for unsupervised domain adaptation. In: DASFAA (2018)
Liang, J., He, R., Sun, Z., Tan, T.: Aggregating randomized clustering-promoting invariant projections for domain adaptation. IEEE Trans. Pattern Anal. Mach. Intell. 41, 1027–1042 (2019)
Liu, H., Long, M., Wang, J., Jordan, M.I.: Transferable adversarial training: a general approach to adapting deep classifiers. In: ICML (2019)
Long, M., Cao, Y., Wang, J., Jordan, M.I.: Learning transferable features with deep adaptation networks. In: ICML (2015)
Long, M., Cao, Z., Wang, J., Jordan, M.I.: Conditional adversarial domain adaptation. In: NeurIPS (2018)
Long, M., Wang, J., Ding, G., Pan, S.J., Yu, P.S.: Adaptation regularization: a general framework for transfer learning. IEEE TKDE 26, 1076–1089 (2014)
Long, M., Wang, J., Ding, G., Sun, J.G., Yu, P.S.: Transfer feature learning with joint distribution adaptation. In: ICCV, pp. 2200–2207 (2013)
Long, M., Zhu, H., Wang, J., Jordan, M.I.: Unsupervised domain adaptation with residual transfer networks. In: NIPS (2016)
Maaten, L.V.D., Hinton, G.E.: Visualizing data using T-SNE. J. Mach. Learn. Res. 9, 2579–2605 (2008)
Mansour, Y., Mohri, M., Rostamizadeh, A.: Domain adaptation: learning bounds and algorithms. In: NeurIPS (2009)
Mika, S., Rätsch, G., Weston, J., Scholkopf, B., Mullers, K.R.: Fisher discriminant analysis with kernels. In: Neural Networks for Signal Processing IX, pp. 41–48 (1999)
Pan, S.J., Tsang, I.W.H., Kwok, J.T., Yang, Q.: Domain adaptation via transfer component analysis. IEEE Trans. Neural Netw. 22, 199–210 (2011)
Pan, S.J., Yang, Q.: A survey on transfer learning. IEEE TKDE 22(10), 1345–1359 (2010)
Pei, Z., Cao, Z., Long, M., Wang, J.: Multi-adversarial domain adaptation. AAAI (2018)
Raghu, M., Zhang, C., Kleinberg, J.M., Bengio, S.: Transfusion: understanding transfer learning for medical imaging. In: NeurIPS (2019)
Saenko, K., Kulis, B., Fritz, M., Darrell, T.: Adapting visual category models to new domains. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010. LNCS, vol. 6314, pp. 213–226. Springer, Heidelberg (2010). https://doi.org/10.1007/978-3-642-15561-1_16
Sankaranarayanan, S., Balaji, Y., Castillo, C.D., Chellappa, R.: Generate to adapt: aligning domains using generative adversarial networks. In: CVPR, pp. 8503–8512 (2018)
Smith, N., Gales, M.J.F.: Speech recognition using SVMs. In: NIPS (2001)
Sun, B., Feng, J., Saenko, K.: Return of frustratingly easy domain adaptation. AAAI (2015)
Sun, B., Saenko, K.: Deep CORAL: correlation alignment for deep domain adaptation. In: Hua, G., Jégou, H. (eds.) ECCV 2016. LNCS, vol. 9915, pp. 443–450. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-49409-8_35
Tzeng, E., Hoffman, J., Zhang, N., Saenko, K., Darrell, T.: Deep domain confusion: maximizing for domain invariance. arXiv:1412.3474 (2014)
Wang, J., Chen, Y., Hao, S., Feng, W., Shen, Z.: Balanced distribution adaptation for transfer learning. In: ICDM, pp. 1129–1134 (2017)
Wang, J., Feng, W., Chen, Y., Yu, H., Huang, M., Yu, P.S.: Visual domain adaptation with manifold embedded distribution alignment. In: MM 2018 (2018)
Wang, Q., Breckon, T.P.: Unsupervised domain adaptation via structured prediction based selective pseudo-labeling. AAAI (2020)
Wang, Q., Bu, P., Breckon, T.P.: Unifying unsupervised domain adaptation and zero-shot visual recognition. In: IJCNN, pp. 1–8 (2019)
Wyner, A.J., Olson, M., Bleich, J., Mease, D.: Explaining the success of AdaBoost and random forests as interpolating classifiers. J. Mach. Learn. Res. 18, 48:1–48:33 (2017)
Yang, L., Liang, X., Wang, T., Xing, E.: Real-to-virtual domain unification for end-to-end autonomous driving. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11208, pp. 553–570. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01225-0_33
Zhang, J., Li, W., Ogunbona, P.: Joint geometrical and statistical alignment for visual domain adaptation. In: CVPR, pp. 5150–5158 (2017)
Zhang, W., Ouyang, W., Li, W., Xu, D.: Collaborative and adversarial network for unsupervised domain adaptation. In: CVPR, pp. 3801–3809 (2018)
Zhang, Y., Tang, H., Jia, K., Tan, M.: Domain-symmetric networks for adversarial domain adaptation. In: CVPR, pp. 5026–5035 (2019)
Zhang, Y., Liu, T., Long, M., Jordan, M.I.: Bridging theory and algorithm for domain adaptation. In: ICML (2019)
Zhao, H., des Combes, R.T., Zhang, K., Gordon, G.J.: On learning invariant representation for domain adaptation. In: ICML (2019)
Acknowledgements
This paper is supported by the National Key Research and Development Program of China (Grant No. 2018YFB1403400), the National Natural Science Foundation of China (Grant No. 61876080), the Collaborative Innovation Center of Novel Software Technology and Industrialization at Nanjing University.
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
Du, Y., Chen, Y., Cui, F., Zhang, X., Wang, C. (2021). Cross-Domain Error Minimization for Unsupervised Domain Adaptation. In: Jensen, C.S., et al. Database Systems for Advanced Applications. DASFAA 2021. Lecture Notes in Computer Science(), vol 12682. Springer, Cham. https://doi.org/10.1007/978-3-030-73197-7_29
Download citation
DOI: https://doi.org/10.1007/978-3-030-73197-7_29
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-73196-0
Online ISBN: 978-3-030-73197-7
eBook Packages: Computer ScienceComputer Science (R0)