Skip to main content
SpringerLink
Log in

Decomposed-distance weighted optimal transport for unsupervised domain adaptation

  • Published:
Applied Intelligence Aims and scope Submit manuscript

Abstract

Unsupervised Domain Adaptation (UDA) aims to transfer knowledge from a label-rich source domain to an unlabeled target domain with a different but related distribution. Optimal Transport (OT) based Wasserstein distance has recently been used to measure and reduce the domain discrepancy in virtue of its robustness in distance measurement. However, the inaccurate estimation of the transport cost between samples is harmful to the fine-grained domain alignment. This paper proposes Decomposed-Distance Weighted Optimal Transport (DDW-OT) method for better adaptation. Technically, according to the clustering-based prototype generation (CPG), DDW-OT constructs a decomposed-distance reweighing matrix to revise the original inaccurate transport distance on sample-level, which conjoins the category uncertainty of the target samples and the correlation degree of category between domains. Besides, the dual-OT solver takes neural netw11 orks to parameterize the dual variables and alleviate the computation cost. DDW-OT also allocated an explicit class-conditional alignment strategy to enhance transfer performance. Extensive experiments on benchmarks demonstrate the effectiveness of the proposed 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

Similar content being viewed by others

References

  1. Ajakan H, Germain P, Larochelle H, Laviolette F, Marchand M (2014) Domain-adversarial neural networks. arXiv:1412.4446

  2. Arjovsky M, Chintala S, Bottou L (2017) Wasserstein gan

  3. Asad M, Jiang H, Yang J, Tu E, Malik AA (2021) Multi-stream 3d latent feature clustering for abnormality detection in videos. Appl Intell pp 1–18

  4. Aude G, Cuturi M, Peyré G, Bach F (2016) Stochastic optimization for large-scale optimal transport. arXiv:1605.08527

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

    Article  MathSciNet  Google Scholar 

  6. Ben-David S, Blitzer J, Crammer K, Pereira F, et al. (2007) Analysis of representations for domain adaptation. Advances in Neural Information Processing Systems 19:137

    Google Scholar 

  7. Blondel M, Seguy V, Rolet A (2018) Smooth and sparse optimal transport. In: International conference on artificial intelligence and statistics. PMLR, pp 880–889

  8. Chen C, Chen Z, Jiang B, Jin X (2019) Joint domain alignment and discriminative feature learning for unsupervised deep domain adaptation. In: Proceedings of the AAAI conference on artificial intelligence, vol 33, pp 3296–3303

  9. Chen C, Xie W, Huang W, Rong Y, Ding X, Huang Y, Xu T, Huang J (2019) Progressive feature alignment for unsupervised domain adaptation. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 627–636

  10. Courty N, Flamary R, Tuia D, Rakotomamonjy A (2017) Optimal transport for domain adaptation. IEEE Transactions on Pattern Analysis and Machine Intelligence 39(9):1853–1865. https://doi.org/10.1109/TPAMI.2016.2615921

    Article  Google Scholar 

  11. Cuturi M (2013) Sinkhorn distances: lightspeed computation of optimal transport. In: NIPS, vol 2, p 4

  12. Damodaran BB, Kellenberger B, Flamary R, Tuia D, Courty N (2018) Deepjdot: Deep joint distribution optimal transport for unsupervised domain adaptation. In: Proceedings of the european conference on computer vision (ECCV), pp 447–463

  13. Deng Z, Luo Y, Zhu J (2019) Cluster alignment with a teacher for unsupervised domain adaptation. In: Proceedings of the IEEE/CVF international conference on computer vision, pp 9944–9953

  14. Gao B, Yang Y, Gouk H, Hospedales TM (2020) Deep clustering for domain adaptation. In: ICASSP 2020-2020 IEEE International conference on acoustics, speech and signal processing (ICASSP). IEEE, pp 4247–4251

  15. Ghifary M, Kleijn WB, Zhang M, Balduzzi D, Li W (2016) Deep reconstruction-classification networks for unsupervised domain adaptation. In: European conference on computer vision. Springer, pp 597–613

  16. Gholenji E, Tahmoresnezhad J (2020) Joint discriminative subspace and distribution adaptation for unsupervised domain adaptation. Appl Intell 50(7):2050–2066

    Article  Google Scholar 

  17. Hartigan JA, Wong MA (1979) A k-means clustering algorithm. Appl Stat 28(1)

  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. Hinton G, Vinyals O, Dean J (2015) Distilling the knowledge in a neural network. Comput Sci 14(7):38–39

    Google Scholar 

  20. 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 

  21. 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 209:106214

    Article  Google Scholar 

  22. Jiang X, Lao Q, Matwin S, Havaei M (2020) Implicit class-conditioned domain alignment for unsupervised domain adaptation. In: International conference on machine learning. PMLR, pp 4816–4827

  23. Kang G, Jiang L, Yang Y, Hauptmann AG (2019) Contrastive adaptation network for unsupervised domain adaptation. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 4893–4902

  24. Kantorovich L (1942) On the transfer of masses (in russian). In: Doklady akademii nauk, vol 37, pp 227–229

  25. Kerdoncuff T, Emonet R, Sebban M (2020) Metric learning in optimal transport for domain adaptation

  26. Li M, Zhai YM, Luo YW, Ge PF, Ren CX (2020) Enhanced transport distance for unsupervised domain adaptation. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 13936–13944

  27. Liakos KG, Busato P, Moshou D, Pearson S, Bochtis D (2018) Machine learning in agriculture: a review. Sensors 18(8):2674

    Article  Google Scholar 

  28. Long M, Cao Y, Wang J, Jordan M (2015) Learning transferable features with deep adaptation networks. In: International conference on machine learning. PMLR, pp 97–105

  29. Long M, Cao Z, Wang J, Jordan MI (2017) Conditional adversarial domain adaptation. arXiv:1705.10667

  30. 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

  31. Long M, Zhu H, Wang J, Jordan MI (2017) Deep transfer learning with joint adaptation networks. In: International conference on machine learning. PMLR, pp 2208–2217

  32. Van der Maaten L, Hinton G (2008) Visualizing data using t-sne. J Mach Learn Rese 9(11)

  33. Maxwell AE, Warner TA, Fang F (2018) Implementation of machine-learning classification in remote sensing: an applied review. Int J Remote Sens 39(9):2784–2817

    Article  Google Scholar 

  34. Munkres J (1962) Algorithms for the assignment and transportation problems. SIAM J, 10

  35. Pan Y, Yao T, Li Y, Wang Y, Ngo CW, Mei T (2019) Transferrable prototypical networks for unsupervised domain adaptation. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 2239–2247

  36. Perrot M, Courty N, Flamary R, Habrard A (2016) Mapping estimation for discrete optimal transport. In: Proceedings of the 30th international conference on neural information processing systems, pp 4204–4212

  37. Peyré G., Cuturi M, et al. (2019) Computational optimal transport: With applications to data science. Foundations and Trends® in Machine Learning 11(5-6):355–607

  38. Redko I, Habrard A, Sebban M (2017) Theoretical analysis of domain adaptation with optimal transport. In: Joint european conference on machine learning and knowledge discovery in databases. Springer, pp 737–753

  39. Russakovsky O, Deng J, Su H, Krause J, Satheesh S, Ma S, Huang Z, Karpathy A, Khosla A, Bernstein M (2015) Imagenet large scale visual recognition challenge. Int J Comput Vis 115 (3):211–252

    Article  MathSciNet  Google Scholar 

  40. 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

  41. Saito K, Watanabe K, Ushiku Y, Harada T (2018) Maximum classifier discrepancy for unsupervised domain adaptation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3723–3732

  42. Sankaranarayanan S, Balaji Y, Castillo CD, Chellappa R (2018) Generate to adapt: Aligning domains using generative adversarial networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 8503–8512

  43. Seguy V, Damodaran BB, Flamary R, Courty N, Rolet A, Blondel M (2018) Large-scale optimal transport and mapping estimation. In: ICLR 2018-International conference on learning representations, pp 1–15

  44. Shen J, Qu Y, Zhang W, Yu Y (2018) Wasserstein distance guided representation learning for domain adaptation. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32

  45. Song L, Wang C, Zhang L, Du B, Zhang Q, Huang C, Wang X (2020) Unsupervised domain adaptive re-identification: theory and practice. Pattern Recogn 102:107173

    Article  Google Scholar 

  46. Sun B, Saenko K (2016) Deep coral: Correlation alignment for deep domain adaptation. In: European conference on computer vision. Springer, pp 443–450

  47. Tzeng E, Hoffman J, Saenko K, Darrell T (2017) Adversarial discriminative domain adaptation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 7167–7176

  48. Tzeng E, Hoffman J, Zhang N, Saenko K, Darrell T (2014) Deep domain confusion: Maximizing for domain invariance. arXiv:1412.3474

  49. Venkateswara H, Eusebio J, Chakraborty S, Panchanathan S (2017) Deep hashing network for unsupervised domain adaptation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 5018–5027

  50. Wang Y, Ye H, Cao F (2021) A novel multi-discriminator deep network for image segmentation. Appl Intell (12)

  51. Xiao N, Zhang L (2021) Dynamic weighted learning for unsupervised domain adaptation. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 15242–15251

  52. Xu R, Liu P, Wang L, Chen C, Wang J (2020) Reliable weighted optimal transport for unsupervised domain adaptation. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 4394–4403

  53. Zhang B, Qian J (2020) Autoencoder-based unsupervised clustering and hashing. Appl Intell (8)

  54. Zhang T, Wang H, Du W, Li M (2021) Deep cnn-based local dimming technology. Appl Intell (1)

  55. Zhang Y, Deng B, Tang H, Zhang L, Jia K (2020) Unsupervised multi-class domain adaptation: theory, algorithms, and practice. IEEE Trans Pattern Anal Mach Intell

  56. Zhang Y, Liu T, Long M, Jordan M (2019) Bridging theory and algorithm for domain adaptation. In: International conference on machine learning. PMLR, pp 7404–7413

Download references

Author information

Authors and Affiliations

  1. College of Computer Science and Technology, Jilin University, Changchun, 130012, China

    Bilin Wang, Shengsheng Wang, Zhe Zhang, Xin Zhao & Zihao Fu

  2. Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University, Changchun, 130012, China

    Bilin Wang, Shengsheng Wang, Zhe Zhang, Xin Zhao & Zihao Fu

Authors
  1. Bilin Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Shengsheng Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Zhe Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Xin Zhao
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Zihao Fu
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Shengsheng Wang.

Ethics declarations

Ethics Statement

This article does not contain any studies with human participants or animal performed by any of the authors.

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.

This work is supported by the Innovation Capacity Construction Project of Jilin Province Development and Reform Commission (2021FGWCXNLJSSZ10), the National Key Research and Development Program of China (No. 2020YFA0714103) and the Science & Technology Development Project of Jilin Province, China (20190302117GX) and the Graduate Innovation Fund of Jilin University under Grant 101832020CX179.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Wang, B., Wang, S., Zhang, Z. et al. Decomposed-distance weighted optimal transport for unsupervised domain adaptation. Appl Intell 52, 14070–14084 (2022). https://doi.org/10.1007/s10489-021-03112-9

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10489-021-03112-9

Keywords

Search

Navigation