[go: up one dir, main page]
Skip to main content
Springer Nature Link
Log in

When to transfer: a dynamic domain adaptation method for effective knowledge transfer

  • Original Article
  • Published:
International Journal of Machine Learning and Cybernetics Aims and scope Submit manuscript

Abstract

Transfer learning has achieved a lot of success recently in saving training samples. However, most of the existing methods only focus on what and how to transfer, but ignore when is the proper transfer time. In the study, we find that transfer useful knowledge at proper time is also significant for the performance. To address this issue, we propose a dynamic domain adaptation approach based on the particle swarm optimization evolutionary algorithm, which searches transfer opportunity automatically for different data domains and training stages. We evaluate the proposed method on various deep learning network structures, and find that the transfer coefficient has large variance in the first several training epochs, and becomes smaller later. This indicates that the features learned in the first several epochs are not stable and is not suitable for static transfer. In addition, the proposed method is not sensitive to the hyper-parameters generated, and it searches suitable transfer coefficients dynamically and automatically instead of conventional manual way. Extensive experiments conducted on various datasets and network structures demonstrate the superiority 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

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

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
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15
Fig. 16
Fig. 17
Fig. 18
Fig. 19

Similar content being viewed by others

Explore related subjects

Discover the latest articles, news and stories from top researchers in related subjects.

Data availability statement

Not applicable.

Code availability

Not applicable.

Notes

  1. http://www.imageclef.org/2014/adaptation.

References

  1. Russakovsky O, Deng J, Hao S, Krause J, Satheesh S, Ma S, Huang Zhiheng, 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 

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

  3. Sinno JP, Yang Q (2010) A survey on transfer learning. IEEE Trans Knowl Data Eng 22(10):1345–1359

    Article  Google Scholar 

  4. Sun G, Ayepah-Mensah D, Xu R, Agbesi VK, Liu G, Jiang W (2021) Transfer learning for autonomous cell activation based on relational reinforcement learning with adaptive reward. IEEE Syst J 16:1044–1055

    Article  Google Scholar 

  5. Hu X, Pan J, Li P, Li H, Wei H, Zhang Y (2016) Multi-bridge transfer learning. Knowl-Based Syst 97(C):60–74

    Article  Google Scholar 

  6. Yi Z, Xuegang H, Zhang Y, Li P (2018) Transfer learning with stacked reconstruction independent component analysis. Knowl-Based Syst 152:100–106

    Article  Google Scholar 

  7. Zhang L, Gao X (2019) Transfer adaptation learning: a decade survey. arXiv preprint arXiv:1903.04687

  8. Huang J, Smola A, Gretton A, Borgwardt KM, Schölkopf B (2007) Correcting sample selection bias by unlabeled data. In: Twentieth Annual Conference on neural information processing systems (NIPS 2006), pp 601–608. MIT Press

  9. Dai W, Yang Q, Xue G-R , Yu Y (2007) Boosting for transfer learning. In: Proceedings of the 24th International Conference on machine learning, ICML ’07, page 193-200, New York, NY, USA. Association for Computing Machinery

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

  11. 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, pp 2066–2073. IEEE

  12. Fernando B, Habrard A, Sebban M, Tuytelaars T (2014) Unsupervised visual domain adaptation using subspace alignment. In: IEEE International Conference on computer vision, pp 2960–2967

  13. Chen Q, Liu Y, Wang Z, Wassell I, Chetty K (2018) Re-weighted adversarial adaptation network for unsupervised domain adaptation. In: Proceedings of the IEEE Conference on computer vision and pattern recognition, pp 7976–7985

  14. Long M, Cao Z, Wang J, Jordan MI (2018)Conditional adversarial domain adaptation. In: Proceedings of the 32nd International Conference on neural information processing systems, pp 1647–1657

  15. Gretton A, Borgwardt KM, Rasch MJ, Schölkopf B, Smola A (2012) A kernel two-sample test. J Mach Learn Res 13:723–773

    MathSciNet  MATH  Google Scholar 

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

  17. Sun B, Saenko K (2016) Deep Coral: correlation alignment for deep domain adaptation. In: European Conference on computer vision, pp 443–450. Springer

  18. Long M, Yue C, Wang J, Jordan MI (2015) Learning transferable features with deep adaptation networks. In: International Conference on machine learning, PMLR, pp 97–105

  19. Pan SJ, Tsang IW, Kwok JT, Yang Q (2011) Domain adaptation via transfer component analysis. IEEE Trans Neural Netw 22(2):199–210

    Article  Google Scholar 

  20. Li J, Lu K, Huang Z, Lei Z, Tao SH (2018) Transfer independently together: a generalized framework for domain adaptation. IEEE Trans Cybern 99:1–12

    Google Scholar 

  21. Yang Z, Liu G, Xie X, Cai Q (2020) Efficient dynamic domain adaptation on deep cnn. Multimed Tools Appl 79(45):33853–33873

    Article  Google Scholar 

  22. 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

  23. Xie X, Liu G, Cai Q, Wei P, Hong Q (2019) Multi-source sequential knowledge regression by using transfer rnn units. Neural Netw 119:151–161

    Article  Google Scholar 

  24. Chen C, Chen Z, Jiang B, Jin X (2019) Joint domain alignment and discriminative feature learning for unsupervised deep domain adaptation. Proceedings of the AAAI Conference on Artificial Intelligence 33(01):3296–3303

    Article  Google Scholar 

  25. Long M, Zhu H, Wang J, Jordan MI (2017) Deep transfer learning with joint adaptation networks. In: Proceedings of the 34th International Conference on machine learning, pp 2208-2217

  26. Tzeng E, Hoffman J, Darrell T, Saenko K (2015) Simultaneous deep transfer across domains and tasks. In: Proceedings of the IEEE International Conference on computer vision, pp 4068–4076

  27. Wang J, Chen Y, Feng W, Han Yu, Huang M, Yang Q (2020) Transfer learning with dynamic distribution adaptation. ACM Trans Intell Syst Technol 11(1):1–25

    Google Scholar 

  28. Jang Y, Lee H, Hwang SJ, Shin J (2019) Learning what and where to transfer. In: International conference on machine learning, pp 3030–3039. PMLR

  29. Kim Y, Soh JW, Park GY, and Cho NI (2020) Transfer learning from synthetic to real-noise denoising with adaptive instance normalization. In: The IEEE Conference on computer vision and pattern recognition (CVPR), pp 3482–3492

  30. Soh JW, Cho S, Cho NI (2020) Meta-transfer learning for zero-shot super-resolution. In: The IEEE Conference on Computer vision and pattern recognition (CVPR), pp 3516–3525

  31. Qiu S, Deng W (2018) Deep local descriptors with domain adaptation. In: Pattern Recognition and Computer Vision, pp 344–355

  32. Li S, Song SJ, Wu C (2018) Layer-wise domain correction for unsupervised domain adaptation. Front Inf Technol Electron Eng 19(1):91–103

    Article  Google Scholar 

  33. Kennedy J, Eberhart R (1995) Particle swarm optimization. In: Proceedings of ICNN’95-International Conference on neural networks, volume 4, pp 1942–1948. IEEE

  34. Tan B, Song Y, Zhong E, Yang Q (2015) Transitive transfer learning. In: Proceedings of the 21th ACM SIGKDD International Conference on knowledge discovery and data mining, pp 1155–1164

  35. Ben Tan Y, Zhang SP, Yang Q (2017) Distant domain transfer learning. In: Proceedings of the AAAI Conference on artificial intelligence 31:2604–2610

  36. 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

  37. Liu M-Y, Tuzel O (2016) Coupled generative adversarial networks. Adv Neural Inf Process Syst 29:469–477

    Google Scholar 

  38. Li J, Chen E, Ding Z, Zhu L, Lu K, Shen HT (2020) Maximum density divergence for domain adaptation. IEEE Trans Pattern Anal Mach Intell 43(11):3918–3930

    Article  Google Scholar 

  39. Du Z, Li J, Su H, Zhu L, Lu K (2021) Cross-domain gradient discrepancy minimization for unsupervised domain adaptation. In: Proceedings of the IEEE/CVF Conference on computer vision and pattern recognition, pp 3937–3946

  40. Li J, Jing M, Su H, Lu K, Zhu L, Shen HT (2021) Faster domain adaptation networks. IEEE Trans Knowl Data Eng. https://doi.org/10.1109/TKDE.2021.3060473

  41. Liu G, Zhiwu L (2020) Discriminativeness-preserved domain adaptation for few-shot learning. IEEE Access 8:168405–168413

    Article  Google Scholar 

  42. Li J, Jing M, Zhu L, Ding Z, Lu K, Yang Y (2020) Learning modality-invariant latent representations for generalized zero-shot learning. In: Proceedings of the 28th ACM International Conference on multimedia, pp 1348–1356

  43. Jing M, Li J, Ke L, Zhu L, Yang Y (2020) Learning explicitly transferable representations for domain adaptation. Neural Netw 130:39–48

    Article  Google Scholar 

  44. Zhan Q, Liu G, Xie X, Sun G, Tang H (2021) Effective transfer learning algorithm in spiking neural networks. IEEE TransCybern. https://doi.org/10.1109/TCYB.2021.3079097

  45. Zhang W, Deng L, Zhang L, Wu D (2020) A survey on negative transfer. arXiv preprint arXiv:2009.00909

  46. Ruan G, Minku LL, Menzel S, Sendhoff B, Yao X (2019) When and how to transfer knowledge in dynamic multi-objective optimization. In: IEEE Symposium Series on Computational Intelligence (SSCI), pp 2034–2041. IEEE

  47. Tolstikhin IO, Bharath K et al (2016) Sriperumbudur. Minimax estimation of maximum mean discrepancy with radial kernels. Adv Neural Inf Process Syst 29:1930–1938

    Google Scholar 

  48. Jing M, Zhao J, Li J, Zhu L, Yang Y, Shen HT (2020) Adaptive component embedding for domain adaptation. IEEE Trans Cybern 51(7):3390–3403

    Article  Google Scholar 

  49. Yan K, Kou L, David Z (2017) Learning domain-invariant subspace using domain features and independence maximization. IEEE Trans Cybern 48(1):288–299

    Article  Google Scholar 

  50. Caputo B, Patricia N (2014) Overview of the imageclef 2014 domain adaptation task. Technical report

  51. Yan H, Ding Y, Li P, Wang Q, Xu Y, Zuo W (2017) Mind the class weight bias: Weighted maximum mean discrepancy for unsupervised domain adaptation. In: Proceedings of the IEEE Conference on computer vision and pattern recognition, pp 2272–2281

  52. Ristani E, Solera F, Zou R, Cucchiara R, Tomasi C (2016) Performance measures and a data set for multi-target, multi-camera tracking. In: Computer Vision—-ECCV 2016 Workshops, pp 17–35. Springer

  53. Zheng L, Shen L, Tian L, Wang S, Wang J, Tian Q (2015) Scalable person re-identification: a benchmark. In: Computer Vision, IEEE International Conference on, pp 1116–1124

  54. Wei L, Zhang S, Gao W, Tian Q (2018) Person transfer gan to bridge domain gap for person re-identification. In: Proceedings of the IEEE Conference on computer vision and pattern recognition (CVPR), pp 79–88, June

  55. Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. In: Proceedings of the 25th International Conference on neural information processing systems-Volume 1, pp 1097–1105

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

  57. He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: The IEEE Conference on computer vision and pattern recognition (CVPR), pp 770–778

  58. Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A (2015) Going deeper with convolutions. In: Proceedings of the IEEE Conference on computer vision and pattern recognition (CVPR), pp 1–9

  59. Yan H, Ding Y, Li P, Wang Q, Xu Y, Wangmeng Z (2017) Mind the class weight bias: weighted maximum mean discrepancy for unsupervised domain adaptation. In: Proceedings of the IEEE Conference on computer vision and pattern recognition (CVPR), pp 2272–2281

  60. Zou Y, Yang X, Yu Z, Vijaya Kumar BVK, Kautz J (2020) Joint disentangling and adaptation for cross-domain person re-identification. In: Computer Vision—ECCV 2020, pp 87–104, 2

  61. Liang W, Wang G, Lai J, Zhu J (2018) M2m-gan: many-to-many generative adversarial transfer learning for person re-identification. arXiv preprint arXiv:1811.03768

Download references

Funding

This work was supported by the Natural Science Foundation of Guangdong Province under Grant No. 2021A1515011866 and Sichuan Province under Grant No. 2021YFG0018 and No. 2022YFG0314, and the Social Foundation of Zhongshan Sci-Tech Institute under Grant No. 420S36.

Author information

Authors and Affiliations

  1. School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, 610054, People’s Republic of China

    Xiurui Xie, Hongjie Zhang & Zeheng Yang

  2. School of Electrical and Computer Engineering, National University of Singapore, Singapore, 119077, Singapore

    Qing Cai & Malu Zhang

  3. School of Computing and Artificial Intelligence, Southwestern University of Finance and Economics, Chengdu, 611130, People’s Republic of China

    Qing Cai & Guisong Liu

  4. Zhongshan Institute, University of Electronic Science and Technology of China, Zhongshan, 528400, People’s Republic of China

    Guisong Liu

Authors
  1. Xiurui Xie
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Qing Cai
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Hongjie Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Malu Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Zeheng Yang
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Guisong Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Guisong Liu.

Ethics declarations

Conflict of interest

The authors have no conflicts of interest to declare that are relevant to the content of this article.

Ethical approval

Not applicable.

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

Xie, X., Cai, Q., Zhang, H. et al. When to transfer: a dynamic domain adaptation method for effective knowledge transfer. Int. J. Mach. Learn. & Cyber. 13, 3491–3508 (2022). https://doi.org/10.1007/s13042-022-01608-5

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s13042-022-01608-5

Keywords

Search

Navigation