Advertisement

Dynamic Adaptation on Non-stationary Visual Domains

  • Sindi ShkodraniEmail author
  • Michael HofmannEmail author
  • Efstratios GavvesEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11130)

Abstract

Domain adaptation aims to learn models on a supervised source domain that perform well on an unsupervised target. Prior work has examined domain adaptation in the context of stationary domain shifts, i.e. static data sets. However, with large-scale or dynamic data sources, data from a defined domain is not usually available all at once. For instance, in a streaming data scenario, dataset statistics effectively become a function of time. We introduce a framework for adaptation over non-stationary distribution shifts applicable to large-scale and streaming data scenarios. The model is adapted sequentially over incoming unsupervised streaming data batches. This enables improvements over several batches without the need for any additionally annotated data. To demonstrate the effectiveness of our proposed framework, we modify associative domain adaptation to work well on source and target data batches with unequal class distributions. We apply our method to several adaptation benchmark datasets for classification and show improved classifier accuracy not only for the currently adapted batch, but also when applied on future stream batches. Furthermore, we show the applicability of our associative learning modifications to semantic segmentation, where we achieve competitive results.

References

  1. 1.
    Aggarwal, C.C.: A survey of stream classification algorithms (2014)Google Scholar
  2. 2.
    Annapoorna, P.S., Mirnalinee, T.: Streaming data classification. In: 2016 International Conference on Recent Trends in Information Technology (ICRTIT), pp. 1–7. IEEE (2016)Google Scholar
  3. 3.
    Bousmalis, K., Silberman, N., Dohan, D., Erhan, D., Krishnan, D.: Unsupervised pixel-level domain adaptation with generative adversarial networks. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), vol. 1, p. 7 (2017)Google Scholar
  4. 4.
    Chen, L.C., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.L.: DeepLab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. IEEE Trans. Pattern Anal. Mach. Intell. 40(4), 834–848 (2018)CrossRefGoogle Scholar
  5. 5.
    Chen, M., Xu, Z., Weinberger, K., Sha, F.: Marginalized denoising autoencoders for domain adaptation. arXiv preprint arXiv:1206.4683 (2012)
  6. 6.
    Chen, Y., Li, W., Gool, L.V.: ROAD: reality oriented adaptation for semantic segmentation of urban scenes. In: CVPR (2018)Google Scholar
  7. 7.
    Coates, A., Ng, A., Lee, H.: An analysis of single-layer networks in unsupervised feature learning. In: Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics, pp. 215–223 (2011)Google Scholar
  8. 8.
    Csurka, G.: Domain adaptation for visual applications: a comprehensive survey. arXiv preprint arXiv:1702.05374 (2017)
  9. 9.
    Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009, pp. 248–255. IEEE (2009)Google Scholar
  10. 10.
    Ganin, Y., et al.: Domain-adversarial training of neural networks. J. Mach. Learn. Res. 17(1), 2096–2130 (2016)MathSciNetzbMATHGoogle Scholar
  11. 11.
    Gavves, E., Mensink, T., Tommasi, T., Snoek, C., Tuytelaars, T.: Active transfer learning with zero-shot priors: reusing past datasets for future tasks. In: Proceedings ICCV 2015, pp. 2731–2739 (2015)Google Scholar
  12. 12.
    Ghifary, M., Kleijn, W.B., Zhang, M., Balduzzi, D., Li, W.: Deep reconstruction-classification networks for unsupervised domain adaptation. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 597–613. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-46493-0_36CrossRefGoogle Scholar
  13. 13.
    Glorot, X., Bordes, A., Bengio, Y.: Domain adaptation for large-scale sentiment classification: a deep learning approach. In: Proceedings of the 28th International Conference on Machine Learning (ICML-11), pp. 513–520 (2011)Google Scholar
  14. 14.
    Goodfellow, I., et al.: Generative adversarial nets. In: Advances in Neural Information Processing Systems, pp. 2672–2680 (2014)Google Scholar
  15. 15.
    Haeusser, P., Frerix, T., Mordvintsev, A., Cremers, D.: Associative domain adaptation. In: International Conference on Computer Vision (ICCV), vol. 2, p. 6 (2017)Google Scholar
  16. 16.
    Haeusser, P., Mordvintsev, A., Cremers, D.: Learning by association-a versatile semi-supervised training method for neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)Google Scholar
  17. 17.
    He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)Google Scholar
  18. 18.
    Hoffman, J., et al.: CyCADA: cycle-consistent adversarial domain adaptation. arXiv preprint arXiv:1711.03213 (2017)
  19. 19.
    Hoffman, J., Wang, D., Yu, F., Darrell, T.: FCNs in the wild: pixel-level adversarial and constraint-based adaptation. arXiv:1612.02649 (2016)
  20. 20.
    Krizhevsky, A., Hinton, G.: Learning multiple layers of features from tiny images (2009)Google Scholar
  21. 21.
    LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998)CrossRefGoogle Scholar
  22. 22.
    Long, M., Cao, Y., Wang, J., Jordan, M.I.: Learning transferable features with deep adaptation networks. arXiv preprint arXiv:1502.02791 (2015)
  23. 23.
    Long, M., Zhu, H., Wang, J., Jordan, M.I.: Deep transfer learning with joint adaptation networks. arXiv preprint arXiv:1605.06636 (2016)
  24. 24.
    Long, M., Zhu, H., Wang, J., Jordan, M.I.: Unsupervised domain adaptation with residual transfer networks. In: Advances in Neural Information Processing Systems, pp. 136–144 (2016)Google Scholar
  25. 25.
    Moiseev, B., Konev, A., Chigorin, A., Konushin, A.: Evaluation of traffic sign recognition methods trained on synthetically generated data. In: Blanc-Talon, J., Kasinski, A., Philips, W., Popescu, D., Scheunders, P. (eds.) ACIVS 2013. LNCS, vol. 8192, pp. 576–583. Springer, Cham (2013).  https://doi.org/10.1007/978-3-319-02895-8_52CrossRefGoogle Scholar
  26. 26.
    Netzer, Y., Wang, T., Coates, A., Bissacco, A., Wu, B., Ng, A.Y.: Reading digits in natural images with unsupervised feature learning. In: NIPS Workshop on Deep Learning and Unsupervised Feature Learning, vol. 2011, p. 5 (2011)Google Scholar
  27. 27.
    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
  28. 28.
    Sankaranarayanan, S., Balaji, Y., Jain, A., Lim, S.N., Chellappa, R.: Unsupervised domain adaptation for semantic segmentation with GANs. arXiv preprint arXiv:1711.06969 (2017)
  29. 29.
    Stallkamp, J., Schlipsing, M., Salmen, J., Igel, C.: The German traffic sign recognition benchmark: a multi-class classification competition. In: The 2011 International Joint Conference on Neural Networks (IJCNN), pp. 1453–1460. IEEE (2011)Google Scholar
  30. 30.
    Street, W.N., Kim, Y.: A streaming ensemble algorithm (SEA) for large-scale classification. In: Proceedings of the seventh ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 377–382. ACM (2001)Google Scholar
  31. 31.
    Sun, B., Saenko, K.: Deep CORAL: correlation alignment for deep domain adaptation. In: Hua, G., Jégou, H. (eds.) ECCV 2016. LNCS, vol. 9915, pp. 443–450. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-49409-8_35CrossRefGoogle Scholar
  32. 32.
    Tan, C., Ji, G.: Semi-supervised incremental feature extraction algorithm for large-scale data stream. Concurr. Comput.: Pract. Exp. 29(6), e3914 (2017)CrossRefGoogle Scholar
  33. 33.
    Tennant, M., Stahl, F., Rana, O., Gomes, J.B.: Scalable real-time classification of data streams with concept drift. Future Gener. Comput. Syst. 75, 187–199 (2017)CrossRefGoogle Scholar
  34. 34.
    Tommasi, T., Patricia, N., Caputo, B., Tuytelaars, T.: A deeper look at dataset bias. In: Csurka, G. (ed.) Domain Adaptation in Computer Vision Applications. ACVPR, pp. 37–55. Springer, Cham (2017).  https://doi.org/10.1007/978-3-319-58347-1_2CrossRefGoogle Scholar
  35. 35.
    Tzeng, E., Hoffman, J., Saenko, K., Darrell, T.: Adversarial discriminative domain adaptation. In: Computer Vision and Pattern Recognition (CVPR), vol. 1, p. 4 (2017)Google Scholar
  36. 36.
    Wang, M., Deng, W.: Deep visual domain adaptation: a survey. arXiv preprint arXiv:1802.03601 (2018)
  37. 37.
    Wang, Y., Li, H., Wang, H., Zhou, B., Zhang, Y.: Multi-window based ensemble learning for classification of imbalanced streaming data. In: Wang, J., et al. (eds.) WISE 2015. LNCS, vol. 9419, pp. 78–92. Springer, Cham (2015).  https://doi.org/10.1007/978-3-319-26187-4_6CrossRefGoogle Scholar
  38. 38.
    Zhang, J., Liang, C., Kuo, C.C.J.: A fully convolutional tri-branch network (FCTN) for domain adaptation. arXiv preprint arXiv:1711.03694 (2017)
  39. 39.
    Zhang, Y., David, P., Gong, B.: Curriculum domain adaptation for semantic segmentation of urban scenes. In: The IEEE International Conference on Computer Vision (ICCV), vol. 2, p. 6 (2017)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.University of AmsterdamAmsterdamThe Netherlands
  2. 2.TomTomAmsterdamThe Netherlands

Personalised recommendations