Skip to main content
SpringerLink
Log in

Few-shot domain adaptation through compensation-guided progressive alignment and bias reduction

  • Published:
Applied Intelligence Aims and scope Submit manuscript

Abstract

Most existing domain adaptation methods require large amounts of data in the target domain to train the model and a relatively long time to adapt different domains. Recently, few-shot domain adaptation (FDA) attracts lots of research attention, which only requires a small number of labeled target data and is more consistent with real-world applications. Previous works on FDA suffer from the risk of bias towards source domain and over-adapting on the target training data, which decreases the generalization of the model on the test data. In this paper, we propose a generalized framework to handle few-shot domain adaptation, named as compensation-guided progressive alignment and bias reduction (CPABR). Specifically, CPABR introduces source and target virtual data as compensations to deal with the scarcity of target data explicitly and fill in the gap between source and target domains, which promotes knowledge transfer. With the help of these virtual data, CPABR performs progressively distribution matching to gradually align the marginal and conditional distributions, and conducts weighted variance maximization to alleviate the bias of the model to the source domain. Moreover, CPABR integrates both homogeneous FDA and heterogeneous FDA into a unified framework. Extensive experiments on widely used benchmark datasets demonstrate the effectiveness of our method.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9

Similar content being viewed by others

References

  1. Ahmadvand M, Tahmoresnezhad J (2020) Metric transfer learning via geometric knowledge embedding. Appl Intell: 1–14

  2. Amini MR, Usunier N, Goutte C (2009) Learning from multiple partially observed views-an application to multilingual text categorization. In: Advances in neural information processing systems, pp 28–36

  3. Ben-David S, Blitzer J, Crammer K, Kulesza A, Pereira F, Vaughan JW (2010) A theory of learning from different domains. Mach Learn 79(1-2):151–175

    Article  MathSciNet  Google Scholar 

  4. Ben-David S, Blitzer J, Crammer K, Pereira F (2006) Analysis of representations for domain adaptation. Adv Neural Inf Process Syst 19:137–144

    Google Scholar 

  5. Chen C, Wang G (2020) Iosuda: an unsupervised domain adaptation with input and output space alignment for joint optic disc and cup segmentation. Appl Intell: 1–19

  6. Chen M, Xue H, Cai D (2019) Domain adaptation for semantic segmentation with maximum squares loss. In: Proceedings of the IEEE international conference on computer vision, pp 2090–2099

  7. Chu WS, De la Torre F, Cohn JF (2013) Selective transfer machine for personalized facial action unit detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3515–3522

  8. Deng J, Dong W, Socher R, Li LJ, Li K, Fei-Fei L (2009) Imagenet: A large-scale hierarchical image database. In: 2009 IEEE conference on computer vision and pattern recognition. IEEE, pp 248–255

  9. Ding Z, Nasrabadi NM, Fu Y (2018) Semi-supervised deep domain adaptation via coupled neural networks. IEEE Trans Image Process 27(11):5214–5224

    Article  MathSciNet  Google Scholar 

  10. 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 647–655

  11. Dougherty G (2012) Pattern recognition and classification: an introduction. Springer Science & Business Media, New York

    MATH  Google Scholar 

  12. Duan L, Xu D, Tsang IWH, Luo J (2011) Visual event recognition in videos by learning from web data. IEEE Trans Pattern Anal Mach Intell 34(9):1667–1680

    Article  Google Scholar 

  13. Gholenji E, Tahmoresnezhad J (2020) Joint discriminative subspace and distribution adaptation for unsupervised domain adaptation. Appl Intell: 1–17

  14. Gong B, Shi Y, Sha F, Grauman K (2012) Geodesic flow kernel for unsupervised domain adaptation. In: 2012 IEEE conference on computer vision and pattern recognition. IEEE, pp 2066– 2073

  15. Gopalan R, Li R, Chellappa R (2011) Domain adaptation for object recognition: An unsupervised approach. In: 2011 International conference on computer vision. IEEE, pp 999–1006

  16. Gretton A, Borgwardt K, Rasch M, Schölkopf B, Smola AJ (2007) A kernel method for the two-sample-problem. In: Advances in neural information processing systems, pp 513–520

  17. Griffin G, Holub A, Perona P (2007) Caltech-256 object category dataset

  18. He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770–778

  19. Hedegaard L, Sheikh-Omar OA, Iosifidis A (2020) Supervised domain adaptation: Were we doing graph embedding all along? arXiv:2004.11262

  20. Hinton GE, Roweis ST (2003) Stochastic neighbor embedding. In: Advances in neural information processing systems, pp 857– 864

  21. Hoffman J, Tzeng E, Darrell T, Saenko K (2017) Simultaneous deep transfer across domains and tasks. In: Domain adaptation in computer vision applications. Springer, pp 173–187

  22. Hu C, He S, Wang Y (2021) A classification method to detect faults in a rotating machinery based on kernelled support tensor machine and multilinear principal component analysis. Appl Intell 51 (4):2609–2621

    Article  Google Scholar 

  23. Hu C, Wang Y, Gu J (2020) Cross-domain intelligent fault classification of bearings based on tensor-aligned invariant subspace learning and two-dimensional convolutional neural networks. Knowl-Based Syst 209 (106):214

    Google Scholar 

  24. Hubert Tsai YH, Yeh YR, Frank Wang YC (2016) Learning cross-domain landmarks for heterogeneous domain adaptation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 5081–5090

  25. Jiang P, Wu A, Han Y, Shao Y, Qi M, Li B (2020) Bidirectional adversarial training for semi-supervised domain adaptation. In: IJCAI, pp 934–940

  26. Kim T, Kim C (2020) Attract, perturb, and explore: Learning a feature alignment network for semi-supervised domain adaptation. In: European conference on computer vision. Springer, pp 591–607

  27. Lee CY, Batra T, Baig MH, Ulbricht D (2019) Sliced wasserstein discrepancy for unsupervised domain adaptation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 10,285–10,295

  28. Li J, Jing M, Lu K, Zhu L, Shen HT (2019) Locality preserving joint transfer for domain adaptation. IEEE Trans Image Process 28(12):6103–6115

    Article  MathSciNet  Google Scholar 

  29. Li J, Lu K, Huang Z, Zhu L, Shen HT (2018) Transfer independently together: A generalized framework for domain adaptation. IEEE Trans Cybern 49(6):2144–2155

    Article  Google Scholar 

  30. Li S, Xie B, Wu J, Zhao Y, Liu CH, Ding Z (2020) Simultaneous semantic alignment network for heterogeneous domain adaptation. In: Proceedings of the 28th ACM international conference on multimedia, pp 3866–3874

  31. Long M, Wang J, Ding G, Sun J, Yu PS (2013) Transfer feature learning with joint distribution adaptation. In: Proceedings of the IEEE international conference on computer vision, pp 2200–2207

  32. Long M, Wang J, Ding G, Sun J, Yu PS (2014) Transfer joint matching for unsupervised domain adaptation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1410–1417

  33. Maaten Lvd, Hinton G (2008) Visualizing data using t-sne. J Mach Learn Res 9:2579–2605

    MATH  Google Scholar 

  34. Motiian S, Jones Q, Iranmanesh S, Doretto G (2017) Few-shot adversarial domain adaptation. In: Advances in neural information processing systems, pp 6670–6680

  35. Motiian S, Piccirilli M, Adjeroh DA, Doretto G (2017) Unified deep supervised domain adaptation and generalization. In: Proceedings of the IEEE international conference on computer vision, pp 5715–5725

  36. Pan SJ, Tsang IW, Kwok JT, Yang Q (2010) Domain adaptation via transfer component analysis. IEEE Trans Neural Netw 22(2):199–210

    Article  Google Scholar 

  37. Pan SJ, Yang Q (2009) A survey on transfer learning. IEEE Trans Knowl Data Eng 22 (10):1345–1359

    Article  Google Scholar 

  38. Rahman MM, Fookes C, Baktashmotlagh M, Sridharan S (2020) Correlation-aware adversarial domain adaptation and generalization. Pattern Recogn 100(107):124

    Google Scholar 

  39. Saenko K, Kulis B, Fritz M, Darrell T (2010) Adapting visual category models to new domains. In: European conference on computer vision. Springer, pp 213–226

  40. Saito K, Kim D, Sclaroff S, Saenko K (2020) Universal domain adaptation through self supervision. Conf Neural Inf Process Syst

  41. Shoeleh F, Asadpour M (2020) Skill based transfer learning with domain adaptation for continuous reinforcement learning domains. Appl Intell 50(2):502–518

    Article  Google Scholar 

  42. Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556

  43. Székely GJ, Rizzo ML (2013) Energy statistics: A class of statistics based on distances. J Stat Plan Infer 143(8):1249– 1272

    Article  MathSciNet  Google Scholar 

  44. Therrien CW (1989) Decision estimation and classification: an introduction to pattern recognition and related topics, John Wiley & Sons Inc, New York

  45. Tommasi T, Tuytelaars T (2014) A testbed for cross-dataset analysis. In: European conference on computer vision. Springer, pp 18–31

  46. Torralba A, Efros AA (2011) Unbiased look at dataset bias. In: CVPR 2011. IEEE, pp 1521–1528

  47. Wang J, Chen Y, Yu H, Huang M, Yang Q (2019) Easy transfer learning by exploiting intra-domain structures. In: 2019 IEEE international conference on multimedia and expo (ICME). IEEE, pp 1210–1215

  48. Wang J, Feng W, Chen Y, Yu H, Huang M, Yu PS (2018) Visual domain adaptation with manifold embedded distribution alignment. In: Proceedings of the 26th ACM international conference on multimedia, pp 402–410

  49. Wang Q, Breckon T (2020) Unsupervised domain adaptation via structured prediction based selective pseudo-labeling. In: Proceedings of the AAAI conference on artificial intelligence, vol 34, pp 6243–6250

  50. Wang Q, Li W, Gool LV (2019) Semi-supervised learning by augmented distribution alignment. In: Proceedings of the IEEE international conference on computer vision, pp 1466–1475

  51. Wang T, Zhang X, Yuan L, Feng J (2019) Few-shot adaptive faster r-cnn. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 7173–7182

  52. Wen J, Liu R, Zheng N, Zheng Q, Gong Z, Yuan J (2019) Exploiting local feature patterns for unsupervised domain adaptation. In: Proceedings of the AAAI conference on artificial intelligence, vol 33, pp 5401–5408

  53. Wu Y, Inkpen D, El-Roby A (2020) Dual mixup regularized learning for adversarial domain adaptation. In: European conference on computer vision. Springer, pp 540–555

  54. Xu M, Zhang J, Ni B, Li T, Wang C, Tian Q, Zhang W (2020) Adversarial domain adaptation with domain mixup. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 6502–6509

  55. Xu X, Zhou X, Venkatesan R, Swaminathan G (2019) Majumder, O.: d-sne: Domain adaptation using stochastic neighborhood embedding. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 2497–2506

  56. Yao Y, Zhang Y, Li X, Ye Y (2019) Heterogeneous domain adaptation via soft transfer network. In: Proceedings of the 27th ACM international conference on multimedia, pp 1578–1586

  57. Zhang H, Cisse M, Dauphin YN, Lopez-Paz D (2017) mixup: Beyond empirical risk minimization. arXiv:1710.09412

  58. Zhang J, Ding Z, Li W, Ogunbona P (2018) Importance weighted adversarial nets for partial domain adaptation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 8156–8164

  59. Zhang Y, Tang H, Jia K, Tan M (2019) Domain-symmetric networks for adversarial domain adaptation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 5031–5040

Download references

Acknowledgements

The work is supported by National Key R&D Program of China (2018YFC 0309400), National Natural Science Foundation of China (61801133, 61871188, 61901160), Guang zhou city science and technology research projects (201902020008).

Author information

Authors and Affiliations

  1. School of Electronic and Information Engineering, South China University of Technology, Guangzhou, Guangdong, China

    Junyuan Shang, Chang Niu, Junchu Huang, Zhiheng Zhou, Junmei Yang & Shiting Xu

  2. Key Laboratory of Big Data and Intelligent Robot, Ministry of Education, South China University of Technology, Guangzhou, China

    Junyuan Shang, Chang Niu, Junchu Huang, Zhiheng Zhou, Junmei Yang & Shiting Xu

  3. School of Computer Science and Cyber Engineering, Guangzhou University, Guangzhou, China

    Liu Yang

Authors
  1. Junyuan Shang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Chang Niu
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Junchu Huang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Zhiheng Zhou
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Junmei Yang
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Shiting Xu
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Liu Yang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Zhiheng Zhou.

Ethics declarations

Conflict of Interests

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

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Shang, J., Niu, C., Huang, J. et al. Few-shot domain adaptation through compensation-guided progressive alignment and bias reduction. Appl Intell 52, 10917–10933 (2022). https://doi.org/10.1007/s10489-021-02987-y

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10489-021-02987-y

Keywords

Search

Navigation