Abstract
Domain adaptation can effectively transfer knowledge between domains with different distributions. Most existing methods use distribution alignment to mitigate the domain shift. But they typically align the marginal and conditional distributions with equal weights. This neglects the relative importance of different distribution alignments. In this paper, we propose a double weighted domain adaptation (DWDA) method, which employs new distribution alignment weighting and sample reweighting strategies. Specifically, the distribution alignment weighting strategy explores the relative importance of marginal and conditional distribution alignments, based on the maximum mean discrepancy; the sample reweighting strategy weights the source and target samples separately based on k-means clustering. The two strategies reinforce each other in the iterative optimization procedure, thus improving the overall performance. In addition, our method also considers the geometry structure preservation. The closed-form solution of the objective function is presented, and the computational complexity and convergence analysis are given. Experimental results demonstrate that DWDA outperforms state-of-the-art domain adaptation methods on several public datasets, and it also has good performance on an imbalanced dataset. Besides, DWDA is robust to a wide range of parameters. Moreover, the convergence curves show that DWDA generally converges rapidly within five iterations. We also evaluate the components of DWDA and show that each component is necessary. Finally, we compare the computational time with the methods of the recent three years to demonstrate the efficiency of DWDA.







Similar content being viewed by others
Explore related subjects
Discover the latest articles and news from researchers in related subjects, suggested using machine learning.References
Aljundi R, Emonet R, Muselet D, Sebban M (2015) Landmarks-based kernelized subspace alignment for unsupervised domain adaptation. In: IEEE conference on computer vision and pattern recognition, pp 56–63. https://doi.org/10.1109/CVPR.2015.7298600
Belkin M, Niyogi P, Sindhwani V (2006) Manifold regularization: a geometric framework for learning from labeled and unlabeled examples. J Mach Learn Res 7:2399–2434
Bruzzone L (2010) Marconcini M Domain adaptation problems: a DASVM classification technique and a circular validation strategy. IEEE Trans Pattern Anal Mach Intell 32:770–787. https://doi.org/10.1109/TPAMI.2009.57
Cai D, He X, Han J (2007) Spectral regression: a unified approach for sparse subspace learning. In: 7th IEEE international conference on data mining, pp 73–82. https://doi.org/10.1109/ICDM.2007.89
Cao Y, Long M, Wang J (2018) Unsupervised domain adaptation with distribution matching machines. In: AAAI conference on artificial intelligence, pp 2795–2802. http://ise.thss.tsinghua.edu.cn/~mlong/doc/distribution-matching-machines-aaai18.pdf
Chung FRK (1997) Spectral graph theory. CBMS regional conference series in mathematics, vol 92. https://doi.org/10.1090/cbms/092
Donahue J, Jia Y, Vinyals O, Hoffman J, Zhang N, Tzeng E, Darrell T (2014) Decaf: a deep convolutional activation feature for generic visual recognition. In: International conference on machine learning, pp 988–996. https://doi.org/10.1097/00003643-201406001-00333
Fernando B, Habrard A, Sebban M, Tuytelaars T (2013) Unsupervised visual domain adaptation using subspace alignment. In: IEEE international conference on computer vision, pp 2960–2967. https://doi.org/10.1109/ICCV.2013.368
Ganin Y, Ustinova E, Ajakan H, Germain P, Larochelle H, Laviolette F, Marchand M, Lempitsky V (2016) Domain-adversarial training of neural networks. J Mach Learn Res (JMLR) 17:189–209. https://doi.org/10.1007/978-3-319-58347-1_10
Gedik E, Hung H (2016) Speaking status detection from body movements using transductive parameter transfer. In: ACM international joint conference on pervasive and ubiquitous, pp 69–72. https://doi.org/10.1145/2968219.2971444
Gong B, Shi Y, Sha F, Grauman K (2012) Geodesic flow kernel for unsupervised domain adaptation. In: IEEE conference on computer vision and pattern recognition, pp 2066–2073. https://doi.org/10.1109/CVPR.2012.6247911
Gopalan R, Li R, Chellappa R (2011) Domain adaptation for object recognition: an unsupervised approach. In: International conference on computer vision, pp 999–1006. https://doi.org/10.1109/ICCV.2011.6126344
He X, Yan S, Hu Y, Niyogi P, Zhang HJ (2005) Face recognition using laplacianfaces. IEEE Trans Pattern Anal Mach Intell 27(3):328–340. https://doi.org/10.1109/TPAMI.2005.55
Hou CA, Tsai YHH, Yeh YR, Wang YCF (2016) Unsupervised domain adaptation with label and structural consistency. IEEE Trans Image Process 25:5552–5562. https://doi.org/10.1109/TIP.2016.2609820
Hou CA, Yeh YR, Wang YCF (2015) An unsupervised domain adaptation approach for cross-domain visual classification. In: 12th IEEE international conference on advanced video and signal based surveillance, pp 1–6. https://doi.org/10.1109/AVSS.2015.7301758
Hsu TMH, Chen WY, Hou CA, Tsai YHH, Yeh YR, Wang YCF (2015) Unsupervised domain adaptation with imbalanced cross-domain data. In: IEEE international conference on computer vision, pp 4121–4129. https://doi.org/10.1109/ICCV.2015.469
Kouw WM, Loog M (2018) An introduction to domain adaptation and transfer learning. https://doi.org/10.13140/RG.2.2.33906.56004
Li J, Lu K, Huang Z, Zhu L, Shen HT (2019) Transfer independently together: a generalized framework for domain adaptation. IEEE Trans Cybern 49:2144–2155. https://doi.org/10.1109/TCYB.2018.2820174
Li J, Wu Y, Lu K (2017) Structured domain adaptation. IEEE Trans Circuits Syst Video Technol 27:1700–1713. https://doi.org/10.1109/TCSVT.2016.2539541
Li L, Zhan Z (2019) Semi-supervised domain adaptation by covariance matching. IEEE Trans Pattern Anal Mach Intell 41(11):2724–2739. https://doi.org/10.1109/TPAMI.2018.2866846
Liu F, Zhang G, Lu J (2020) Heterogeneous domain adaptation: an unsupervised approach. IEEE Trans Neural Netw Learn Syst (TNNLS). https://doi.org/10.1109/TNNLS.2020.2973293
Long M, Cao Y, Cao Z, Wang J, Jordan MI (2019) Transferable representation learning with deep adaptation networks. IEEE Trans Pattern Anal Mach Intell 41(12):3071–3085. https://doi.org/10.1109/TPAMI.2018.2868685
Long M, Cao Y, Wang J, Jordan MI (2015) Learning transferable features with deep adaptation networks. In: The 32nd international conference on machine learning, pp 97–105. http://arxiv.org/abs/1502.02791
Long M, Cao Z, Wang J, Jordan MI (2018) Conditional adversarial domain adaptation. In: Advances in neural information processing systems, pp 1640–1650. https://doi.org/10.1007/978-3-030-01237-3_9
Long M, Wang J, Ding G, Pan SJ, Yu PS (2014) Adaptation regularization: a general framework for transfer learning. IEEE Trans Pattern Anal Mach Intell 26:1076–1089. https://doi.org/10.1109/TKDE.2013.111
Long M, Wang J, Ding G, Sun J, Yu PS (2013) Transfer feature learning with joint distribution adaptation. In: IEEE international conference on computer vision, pp 2200–2207. https://doi.org/10.1109/ICCV.2013.274
Long M, Wang J, Ding G, Sun J, Yu PS (2014) Transfer joint matching for unsupervised domain adaptation. In: IEEE conference on computer vision and pattern recognition, pp 1410–1417. https://doi.org/10.1109/CVPR.2014.183
Long M, Wang J, Sun J, Yu PS (2015) Domain invariant transfer kernel learning. IEEE Trans Knowl Data Eng 27:1519–1532. https://doi.org/10.1109/TKDE.2014.2373376
Pan SJ, Tsang IW, Kwok JT, Yang Q (2011) Domain adaptation via transfer component analysis. IEEE Trans Neural Netw 22:199–210. https://doi.org/10.1109/TNN.2010.2091281
Pan SJ, Yang Q (2010) A survey on transfer learning. IEEE Trans Knowl Data Eng 22:1345–1359. https://doi.org/10.1109/TKDE.2009.191
Saenko K, Kulis B, Fritz M, Darrell T (2010) Transferring visual cateogry models to new domains. In: European conference on computer vision, pp 213–226
Schökopf B, Platt J, Hofmann T (2007) A kernel method for the two-sample-problem. https://doi.org/10.7551/mitpress/7503.003.0069
Shrivastava A, Shekhar S, Patel VM (2014) Unsupervised domain adaptation using parallel transport on grassmann manifold. In: IEEE winter conference on applications of computer vision, pp 277–284. https://doi.org/10.1109/WACV.2014.6836088
Sun B, Feng J, Saenko K (2016) Return of frustratingly easy domain adaptation. In: AAAI conference on artificial intelligence, pp 2058–2065. http://arxiv.org/abs/1511.05547
Tsai YHH, Yeh YR, Wang YCF (2016) Learning cross-domain landmarks for heterogeneous domain adaptation. In: IEEE conference on computer vision and pattern recognition, pp 5081–5090. https://doi.org/10.1109/CVPR.2016.549
Tzeng E, Hoffman J, Saenko K, Darrell T (2017) Adversarial discriminative domain adaptation. In: IEEE conference on computer vision and pattern recognition (CVPR), pp 2962–2971. https://doi.org/10.1109/CVPR.2017.316
van Opbroek A, Ikram MA, Vernooij MW, de Bruijne M (2015) Transfer learning improves supervised image segmentation across imaging protocols. IEEE Trans Med Imaging 34:1018–1030. https://doi.org/10.1109/TMI.2014.2366792
Wang J, Chen Y, Hao S, Feng W, Shen Z (2017) Balanced distribution adaptation for transfer learning. In: IEEE international conference on data mining, pp 1129–1134. https://doi.org/10.1109/ICDM.2017.150
Wang J, Chen Y, Yu H, Huang M, Yang Q (2019) Easy transfer learning by exploiting intra-domain structures. In: IEEE international conference on multimedia and expo, pp 1210–1215. https://doi.org/10.1109/ICME.2019.00211
Wang J, Feng W, Chen Y, Yu H, Huang M, Yu PS (2018) Visual domain adaptation with manifold embedded distribution alignment. In: ACM multimedia, pp 402–410. https://doi.org/10.1145/3240508.3240512
Wang R, Utiyama M, Liu L, Chen K, Sumita E (2017) Instance weighting for neural machine translation domain adaptation. In: Conference on empirical methods in natural language processing, pp 1482–1488. https://doi.org/10.18653/v1/D17-1155
Yan S, Xu D, Zhang B, Zhang HJ, Yang Q, Lin S (2007) Graph embedding and extensions: a general framework for dimensionality reduction. IEEE Trans Pattern Anal Mach Intell 29:40–51. https://doi.org/10.1109/TPAMI.2007.250598
You K, Long M, Cao Z, Wang J, Jordan MI (2019) Universal domain adaptation. In: IEEE conference on computer vision and pattern recognition, pp 2720–2729. http://ise.thss.tsinghua.edu.cn/~mlong/doc/universal-domain-adaptation-cvpr19.pdf
Zhang J, Li W, Ogunbona P (2017) Joint geometrical and statistical alignment for visual domain adaptation. In: IEEE conference on computer vision and pattern recognition, pp 5150–5158. https://doi.org/10.1109/CVPR.2017.547
Zhao L, Pan SJ, Yang Q (2017) A unified framework of active transfer learning for cross-system recommendation. Artif Intell 245:38–55. https://doi.org/10.1016/j.artint.2016.12.004
Acknowledgements
We sincerely thank the anonymous reviewers for their careful work and thoughtful suggestions, which have greatly improved this article. This study was funded by the National Natural Science Foundation of China (Grant No. 61802056), the National Natural Science Foundation of China (Grant No. 61300049), the Natural Science Research Foundation of Jilin Province of China (Grant No. 20180101043JC), the Natural Science Research Foundation of Jilin Province of China (Grant No. 20180101053JC), the Industrial Technology Research and Development Project of the Development and Reform Commission of Jilin Province (Grant No. 2019C053-9).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Li, J., Li, Z. & Lü, S. Unsupervised double weighted domain adaptation. Neural Comput & Applic 33, 3545–3566 (2021). https://doi.org/10.1007/s00521-020-05228-4
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-020-05228-4