Skip to main content
Springer Nature Link
Log in

Unsupervised domain adaptation with target reconstruction and label confusion in the common subspace

  • Original Article
  • Published:
Neural Computing and Applications Aims and scope Submit manuscript

Abstract

Deep neural networks can learn powerful and discriminative representations from a large number of labeled samples. However, it is typically costly to collect and annotate large-scale datasets, which limits the applications of deep learning in many real-world scenarios. Domain adaptation, as an option to compensate for the lack of labeled data, has attracted much attention in the community of machine learning. Although a mass of methods for domain adaptation has been presented, many of them simply focus on matching the distribution of the source and target feature representations, which may fail to encode useful information about the target domain. In order to learn invariant and discriminative representations for both domains, we propose a Cross-Domain Minimization with Deep Autoencoder method for unsupervised domain adaptation, which simultaneously learns label prediction on the source domain and input reconstruction on the target domain using shared feature representations aligned with correlation alignment in a unified framework. Furthermore, inspired by adversarial training and cluster assumption, a task-specific class label discriminator is incorporated to confuse the predicted target class labels with samples draw from categorical distribution, which can be regarded as entropy minimization regularization. Extensive empirical results demonstrate the superiority of our approach over the state-of-the-art unsupervised adaptation methods on both visual and non-visual cross-domain adaptation tasks.

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

Similar content being viewed by others

Explore related subjects

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

Notes

  1. https://github.com/BoyuanJiang/CDMDA.

References

  1. Abadi M, Agarwal A, Barham P, Brevdo E, Chen Z, Citro C, Corrado GS, Davis A, Dean J, Devin M et al (2016) Tensorflow: large-scale machine learning on heterogeneous distributed systems. ArXiv: Distributed, Parallel, and Cluster Computing

  2. Amini M, 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. Badrinarayanan V, Kendall A, Cipolla R (2017) Segnet: a deep convolutional encoder-decoder architecture for image segmentation. IEEE Trans Pattern Anal Mach Intell 39(12):2481–2495

    Article  Google Scholar 

  4. Baktashmotlagh M, Harandi M, Salzmann M (2016) Distribution-matching embedding for visual domain adaptation. J Mach Learn Res 17(1):3760–3789

    MathSciNet  MATH  Google Scholar 

  5. Bay H, Tuytelaars T, Van Gool L (2006) Surf: speeded up robust features. In: European conference on computer vision. Springer, pp 404–417

  6. 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 

  7. Bousmalis K, Trigeorgis G, Silberman N, Krishnan D, Erhan D (2016) Domain separation networks. In: Neural information processing systems, pp 343–351

  8. Bromley J, Guyon I, LeCun Y, Säckinger E, Shah R (1994) Signature verification using a “siamese” time delay neural network. In: Advances in neural information processing systems, pp 737–744

  9. Carlucci FM, Porzi L, Caputo B, Ricci E, Bulò SR (2017) Autodial: automatic domain alignment layers. In: International conference on computer vision

  10. Caruana R (1998) Multitask learning. In: Learning to learn. Springer, pp 95–133

  11. Chapelle O, Zien A, Ghahramani RCZ (2005) Semi-supervised classification by low density separation, pp 57–64

  12. Chen M, Xu Z, Sha F, Weinberger KQ (2012) Marginalized denoising autoencoders for domain adaptation. In: International conference on machine learning, pp 1627–1634

  13. Dai W, Yang Q, Xue GR, Yu Y (2007) Boosting for transfer learning. In: Proceedings of the 24th international conference on machine learning. ACM, pp 193–200

  14. Fernando B, Habrard A, Sebban M, Tuytelaars T (2013) Unsupervised visual domain adaptation using subspace alignment. In: 2013 IEEE international conference on computer vision, pp 2960–2967. https://doi.org/10.1109/ICCV.2013.368

  15. Ganin Y, Lempitsky V (2015) Unsupervised domain adaptation by backpropagation. In: International conference on machine learning, pp 1180–1189

  16. 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 17(1):2030–2096

    MathSciNet  MATH  Google Scholar 

  17. Gatys LA, Ecker AS, Bethge M (2016) Image style transfer using convolutional neural networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2414–2423

  18. 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, pp 597–613

  19. Girshick R, Donahue J, Darrell T, Malik J (2014) Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 580–587

  20. Goodfellow I, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair S, Courville A, Bengio Y (2014) Generative adversarial nets. In: Advances in neural information processing systems, pp 2672–2680

  21. Grandvalet Y, Bengio Y (2005) Semi-supervised learning by entropy minimization. In: Advances in neural information processing systems, pp 529–536

  22. Gretton A, Borgwardt KM, 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

  23. Gretton A, Smola A, Huang J, Schmittfull M, Borgwardt K, Schölkopf B (2009) Covariate shift and local learning by distribution matching. MIT Press, Cambridge, pp 131–160

    Google Scholar 

  24. 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

  25. 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

  26. Hull JJ (1994) A database for handwritten text recognition research. IEEE Trans Pattern Anal Mach Intell 16(5):550–554

    Article  Google Scholar 

  27. Joachims T (1999) Transductive inference for text classification using support vector machines. ICML 99:200–209

    Google Scholar 

  28. Kamnitsas K, Baumgartner C, Ledig C, Newcombe V, Simpson J, Kane A, Menon D, Nori A, Criminisi A, Rueckert D et al (2017) Unsupervised domain adaptation in brain lesion segmentation with adversarial networks. In: International conference on information processing in medical imaging. Springer, pp 597–609

  29. Kan M, Shan S, Chen X (2015) Bi-shifting auto-encoder for unsupervised domain adaptation. In: Proceedings of the IEEE international conference on computer vision, pp 3846–3854

  30. Kingma DP, Ba JL (2015) Adam: a method for stochastic optimization. In: International conference on learning representations

  31. Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. In: Advances in neural information processing systems, pp 1097–1105

  32. La L, Guo Q, Cao Q, Wang Y (2014) Transfer learning with reasonable boosting strategy. Neural Comput Appl 24(3–4):807–816

    Article  Google Scholar 

  33. Lecun Y, Bottou L, Bengio Y, Haffner P (1998) Gradient-based learning applied to document recognition. Proc IEEE 86(11):2278–2324

    Article  Google Scholar 

  34. LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521(7553):436

    Article  Google Scholar 

  35. Lee DH (2013) Pseudo-label: the simple and efficient semi-supervised learning method for deep neural networks. In: Workshop on challenges in representation learning, vol 3. ICML, p 2

  36. Liu W, Anguelov D, Erhan D, Szegedy C, Reed S, Fu CY, Berg AC (2016) Ssd: single shot multibox detector. In: European conference on computer vision. Springer, pp 21–37

  37. Long J, Shelhamer E, Darrell T (2015) Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3431–3440

  38. Long M, Wang J, Ding G, Sun J, Philip SY (2013) Transfer feature learning with joint distribution adaptation. In: 2013 IEEE international conference on computer vision (ICCV). IEEE, pp 2200–2207

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

  40. Long M, Zhu H, Wang J, Jordan MI (2016) Unsupervised domain adaptation with residual transfer networks. In: Advances in neural information processing systems, pp 136–144

  41. Lvd M, Hinton G (2008) Visualizing data using t-SNE. J Mach Learn Res 9(Nov):2579–2605

    MATH  Google Scholar 

  42. Makhzani A, Shlens J, Jaitly N, Goodfellow I, Frey B (2015) Adversarial autoencoders. ArXiv preprint arXiv:151105644

  43. Nair V, Hinton GE (2010) Rectified linear units improve restricted Boltzmann machines. In: Proceedings of the 27th international conference on machine learning (ICML-10), pp 807–814

  44. Netzer Y, Wang T, Coates A, Bissacco A, Wu B, Ng AY (2011) Reading digits in natural images with unsupervised feature learning. In: NIPS workshop on deep learning and unsupervised feature learning, vol 2011, p 5

  45. Pan SJ, Yang Q (2010) A survey on transfer learning. IEEE Trans Knowl Data Eng 22(10):1345–1359

    Article  Google Scholar 

  46. Pietro Morerio VM Jacopo Cavazza (2018) Minimal-entropy correlation alignment for unsupervised deep domain adaptation. In: International conference on learning representations

  47. Purushotham S, Carvalho W, Nilanon T, Liu Y (2017) Variational recurrent adversarial deep domain adaptation

  48. Rumelhart DE, Hinton GE, Williams RJ (1985) Learning internal representations by error propagation. Tech. rep., California Univ San Diego La Jolla Inst for Cognitive Science

  49. 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

  50. Si S, Tao D, Geng B (2010) Bregman divergence-based regularization for transfer subspace learning. IEEE Trans Knowl Data Eng 22(7):929–942

    Article  Google Scholar 

  51. Sun B, Saenko K (2016) Deep coral: correlation alignment for deep domain adaptation. In: ECCV 2016 workshops

  52. Sun B, Feng J, Saenko K (2016) Return of frustratingly easy domain adaptation. In: AAAI

  53. Tzeng E, Hoffman J, Zhang N, Saenko K, Darrell T (2014) Deep domain confusion: maximizing for domain invariance. ArXiv preprint arXiv:14123474

  54. Tzeng E, Hoffman J, Saenko K, Darrell T (2017) Adversarial discriminative domain adaptation. In: 2017 IEEE conference on computer vision and pattern recognition (CVPR), pp 2962–2971. https://doi.org/10.1109/CVPR.2017.316

  55. Ueffing N, Simard M, Larkin S, Johnson H (2007) NRCs portage system for WMT 2007. ACL 2007:185–188

    Google Scholar 

  56. Vincent P, Larochelle H, Bengio Y, Manzagol PA (2008) Extracting and composing robust features with denoising autoencoders. In: Proceedings of the 25th international conference on machine learning. ACM, pp 1096–1103

  57. Wang H, Xu A, Wang S, Chughtai S (2018) Cross domain adaptation by learning partially shared classifiers and weighting source data points in the shared subspaces. Neural Comput Appl 29(6):237–248

    Article  Google Scholar 

  58. Wei P, Ke Y, Goh CK (2016) Deep nonlinear feature coding for unsupervised domain adaptation. In: IJCAI, pp 2189–2195

  59. Yang S, Lin M, Hou C, Zhang C, Wu Y (2012) A general framework for transfer sparse subspace learning. Neural Comput Appl 21(7):1801–1817

    Article  Google Scholar 

  60. Yang Z, Yu W, Liang P, Guo H, Xia L, Zhang F, Ma Y, Ma J (2018) Deep transfer learning for military object recognition under small training set condition. Neural Comput Appl 1–10

  61. Zeiler MD, Krishnan D, Taylor GW, Fergus R (2010) Deconvolutional networks. In: 2010 IEEE conference on computer vision and pattern recognition (CVPR). IEEE, pp 2528–2535

  62. Zhang H, Cao X, Ho JK, Chow TW (2017) Object-level video advertising: an optimization framework. IEEE Trans Ind Inform 13(2):520–531

    Article  Google Scholar 

  63. Zhang H, Ji Y, Huang W, Liu L (2018) Sitcom-star-based clothing retrieval for video advertising: a deep learning framework. Neural Comput Appl. https://doi.org/10.1007/s00521-018-3579-x

  64. Zhu X (2006) Semi-supervised learning literature survey. Computer Science, University of Wisconsin-Madison, vol 2, no. 3

  65. Zhuang F, Cheng X, Luo P, Pan SJ, He Q (2015) Supervised representation learning: transfer learning with deep autoencoders. In: IJCAI, pp 4119–4125

Download references

Acknowledgements

This research is supported by the National Science and Technology Major Projects (NO. 2013ZX03005013) and the Opening Foundation of the State Key Laboratory for Diagnosis and Treatment of Infectious Diseases (NO. 2014KF06).

Author information

Authors and Affiliations

  1. Institution of Information Science and Electrical Engineering, Zhejiang University, Hangzhou, 310037, Zhejiang, China

    Boyuan Jiang, Chao Chen & Xinyu Jin

Authors
  1. Boyuan Jiang
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Chao Chen
    View author publications

    You can also search for this author inPubMed Google Scholar

  3. Xinyu Jin
    View author publications

    You can also search for this author inPubMed Google Scholar

Corresponding author

Correspondence to Xinyu Jin.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Jiang, B., Chen, C. & Jin, X. Unsupervised domain adaptation with target reconstruction and label confusion in the common subspace. Neural Comput & Applic 32, 4743–4756 (2020). https://doi.org/10.1007/s00521-018-3846-x

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-018-3846-x

Keywords