Advertisement

Partially-Shared Variational Auto-encoders for Unsupervised Domain Adaptation with Target Shift

Conference paper
  • 794 Downloads
Part of the Lecture Notes in Computer Science book series (LNCS, volume 12361)

Abstract

Target shift, the different label distributions of source and target domains, is an important problem for practical use of unsupervised domain adaptation (UDA); as we do not know labels in target domain datasets, we cannot ensure an identical label distribution between the two domains. Despite this inaccessibility, modern UDA methods commonly try to match the shape of the feature distributions over the domains while projecting the features to labels by a common classifier. This implicitly assumes the identical label distribution. To overcome this problem, we propose a method that generates a pseudo pair by domain conversion where the label is preserved identically even trained with target-shifted datasets. A pair-wise metric learning enables to align feature over the domains without matching the shape of distributions. We conducted two experiments: one is a regression of pose-estimation, where label distribution is continuous and the target shift problem can seriously degrade the quality of UDA. The other is digit classification task where we can systematically control the distribution difference. The code and dataset are available at https://github.com/iiyama-lab/PS-VAEs.

Supplementary material

504471_1_En_1_MOESM1_ESM.pdf (383 kb)
Supplementary material 1 (pdf 382 KB)

References

  1. 1.
    Cao, Z., Long, M., Wang, J., Jordan, M.I.: Partial transfer learning with selective adversarial networks. In: The IEEE Conference on Computer Vision and Pattern Recognition (2018)Google Scholar
  2. 2.
    Cao, Z., Ma, L., Long, M., Wang, J.: Partial adversarial domain adaptation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11212, pp. 139–155. Springer, Cham (2018).  https://doi.org/10.1007/978-3-030-01237-3_9CrossRefGoogle Scholar
  3. 3.
    Cao, Z., You, K., Long, M., Wang, J., Yang, Q.: Learning to transfer examples for partial domain adaptation. In: The IEEE Conference on Computer Vision and Pattern Recognition (2019)Google Scholar
  4. 4.
    CMU Graphics Lab.: CMU graphics lab motion capture database. http://mocap.cs.cmu.edu/. Accessed 11 Nov 2019
  5. 5.
    Cordts, M., et al.: The cityscapes dataset for semantic urban scene understanding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3213–3223 (2016)Google Scholar
  6. 6.
    Deng, Z., Luo, Y., Zhu, J.: Cluster alignment with a teacher for unsupervised domain adaptation. In: The IEEE International Conference on Computer Vision (2019)Google Scholar
  7. 7.
    Doersch, C.: Tutorial on variational autoencoders. In: CoRR (2016)Google Scholar
  8. 8.
    Ghifary, M., Kleijn, W.B., Zhang, M.: Domain adaptive neural networks for object recognition. In: Pham, D.-N., Park, S.-B. (eds.) PRICAI 2014. LNCS (LNAI), vol. 8862, pp. 898–904. Springer, Cham (2014).  https://doi.org/10.1007/978-3-319-13560-1_76CrossRefGoogle Scholar
  9. 9.
    Girshick, R.: Fast R-CNN. In: The IEEE International Conference on Computer Vision (2015)Google Scholar
  10. 10.
    Gong, M., Zhang, K., Liu, T., Tao, D., Glymour, C., Schölkopf, B.: Domain adaptation with conditional transferable components. In: International Conference on Machine Learning, pp. 2839–2848 (2016)Google Scholar
  11. 11.
    Hoffman, J., et al.: CyCADA: cycle-consistent adversarial domain adaptation. In: Proceedings of the 35th International Conference on Machine Learning (2018)Google Scholar
  12. 12.
    Huang, X., Liu, M.-Y., Belongie, S., Kautz, J.: Multimodal unsupervised image-to-image translation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11207, pp. 179–196. Springer, Cham (2018).  https://doi.org/10.1007/978-3-030-01219-9_11CrossRefGoogle Scholar
  13. 13.
    Hull, J.J.: A database for handwritten text recognition research. IEEE Trans. Pattern Anal. Mach. Intell. 16(5), 550–554 (1994)CrossRefGoogle Scholar
  14. 14.
    Joo, H., et al.: Panoptic studio: a massively multiview system for social motion capture. In: The IEEE International Conference on Computer Vision (2015)Google Scholar
  15. 15.
    Kuhnke, F., Ostermann, J.: Deep head pose estimation using synthetic images and partial adversarial domain adaption for continuous label spaces. In: The IEEE International Conference on Computer Vision (2019)Google Scholar
  16. 16.
    Laradji, I., Babanezhad, R.: M-ADDA: unsupervised domain adaptation with deep metric learning. In: Proceedings of the 36th International Conference on Machine Learning Workshop (2018)Google Scholar
  17. 17.
    LeCun, Y., Cortes, C.: MNIST handwritten digit database. http://yann.lecun.com/exdb/mnist/ (2010)
  18. 18.
    Lee, H.-Y., Tseng, H.-Y., Huang, J.-B., Singh, M., Yang, M.-H.: Diverse image-to-image translation via disentangled representations. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11205, pp. 36–52. Springer, Cham (2018).  https://doi.org/10.1007/978-3-030-01246-5_3CrossRefGoogle Scholar
  19. 19.
    Liu, A.H., Liu, Y.C., Yeh, Y.Y., Wang, Y.C.F.: A unified feature disentangler for multi-domain image translation and manipulation. In: Advances in Neural Information Processing Systems, vol. 31, pp. 2590–2599 (2018)Google Scholar
  20. 20.
    Liu, M.Y., Breuel, T., Kautz, J.: Unsupervised image-to-image translation networks. In: Guyon, I., et al. (eds.) Advances in Neural Information Processing Systems, vol. 30, pp. 700–708 (2017)Google Scholar
  21. 21.
    Liu, Y., Wang, Z., Jin, H., Wassell, I.: Multi-task adversarial network for disentangled feature learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3743–3751 (2018)Google Scholar
  22. 22.
    Long, M., Cao, Y., Wang, J., Jordan, M.I.: Learning transferable features with deep adaptation networks. In: Proceedings of the 32nd International Conference on International Conference on Machine Learning, pp. 97–105 (2015)Google Scholar
  23. 23.
    Long, M., Cao, Z., Wang, J., Jordan, M.I.: Conditional adversarial domain adaptation. In: Advances in Neural Information Processing Systems, pp. 1645–1655 (2018)Google Scholar
  24. 24.
    Luo, Y., Zheng, L., Guan, T., Yu, J., Yang, Y.: Taking a closer look at domain shift: category-level adversaries for semantics consistent domain adaptation. In: The IEEE Conference on Computer Vision and Pattern Recognition (2019)Google Scholar
  25. 25.
    Maaten, L.V.D., Hinton, G.: Visualizing data using t-SNE. J. Mach. Learn. Res. 9(Nov), 2579–2605 (2008)zbMATHGoogle Scholar
  26. 26.
    Mao, X., Li, Q., Xie, H., Lau, R.Y., Wang, Z., Paul Smolley, S.: Least squares generative adversarial networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2794–2802 (2017)Google Scholar
  27. 27.
    Miyato, T., Kataoka, T., Koyama, M., Yoshida, Y.: Spectral normalization for generative adversarial networks. In: International Conference on Learning Representations (2018)Google Scholar
  28. 28.
    Moreno-Torres, J.G., Raeder, T., Alaiz-RodríGuez, R., Chawla, N.V., Herrera, F.: A unifying view on dataset shift in classification. Pattern Recogn. 45(1), 521–530 (2012)CrossRefGoogle Scholar
  29. 29.
    Netzer, Y., Wang, T., Coates, A., Bissacco, A., Wu, B., Ng, A.Y.: Reading digits in natural images with unsupervised feature learning. In: Advances in Neural Information Processing Systems Workshop (2011)Google Scholar
  30. 30.
    Richter, S.R., Vineet, V., Roth, S., Koltun, V.: Playing for data: ground truth from computer games. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9906, pp. 102–118. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-46475-6_7CrossRefGoogle Scholar
  31. 31.
    Roy, S., Siarohin, A., Sangineto, E., Bulo, S.R., Sebe, N., Ricci, E.: Unsupervised domain adaptation using feature-whitening and consensus loss. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 9471–9480 (2019)Google Scholar
  32. 32.
    Russo, P., Carlucci, F.M., Tommasi, T., Caputo, B.: From source to target and back: symmetric bi-directional adaptive GAN. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8099–8108 (2018)Google Scholar
  33. 33.
    Saito, K., Ushiku, Y., Harada, T., Saenko, K.: Adversarial dropout regularization. In: The International Conference on Learning Representations (2018)Google Scholar
  34. 34.
    Saito, K., Watanabe, K., Ushiku, Y., Harada, T.: Maximum classifier discrepancy for unsupervised domain adaptation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3723–3732 (2018)Google Scholar
  35. 35.
    Shrivastava, A., Pfister, T., Tuzel, O., Susskind, J., Wang, W., Webb, R.: Learning from simulated and unsupervised images through adversarial training. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2107–2116 (2017)Google Scholar
  36. 36.
    Shu, R., Bui, H., Narui, H., Ermon, S.: A DIRT-T approach to unsupervised domain adaptation. In: International Conference on Learning Representations (2018)Google Scholar
  37. 37.
    Software, P.: Poser pro 2014. https://www.renderosity.com/mod/bcs/poser-pro-2014/102000. Accessed 10 Nov 2019
  38. 38.
    Tzeng, E., Hoffman, J., Saenko, K., Darrell, T.: Adversarial discriminative domain adaptation. In: The IEEE Conference on Computer Vision and Pattern Recognition (2017)Google Scholar
  39. 39.
    Yan, H., Ding, Y., Li, P., Wang, Q., Xu, Y., Zuo, W.: Mind the class weight bias: weighted maximum mean discrepancy for unsupervised domain adaptation. In: The IEEE Conference on Computer Vision and Pattern Recognition (2017)Google Scholar
  40. 40.
    You, K., Long, M., Cao, Z., Wang, J., Jordan, M.I.: Universal domain adaptation. In: The IEEE Conference on Computer Vision and Pattern Recognition (2019)Google Scholar
  41. 41.
    Zhang, J., Ding, Z., Li, W., Ogunbona, P.: Importance weighted adversarial nets for partial domain adaptation. In: The IEEE Conference on Computer Vision and Pattern Recognition (2018)Google Scholar
  42. 42.
    Zhang, K., Schölkopf, B., Muandet, K., Wang, Z.: Domain adaptation under target and conditional shift. In: International Conference on Machine Learning, pp. 819–827 (2013)Google Scholar
  43. 43.
    Zhang, X., Wong, Y., Kankanhalli, M.S., Geng, W.: Unsupervised domain adaptation for 3D human pose estimation. In: Proceedings of the 27th ACM International Conference on Multimedia (2019)Google Scholar
  44. 44.
    Zhu, J.Y., Park, T., Isola, P., Efros, A.A.: Unpaired image-to-image translation using cycle-consistent adversarial networks. In: The IEEE International Conference on Computer Vision (2017)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.Kyoto UniversityKyotoJapan
  2. 2.OMRON SINIC X Corp.TokyoJapan

Personalised recommendations