Skip to main content
Book cover

International Conference on Image Analysis and Processing

ICIAP 2019: Image Analysis and Processing – ICIAP 2019 pp 390–401Cite as

Discovering Latent Domains for Unsupervised Domain Adaptation Through Consistency

Part of the Lecture Notes in Computer Science book series (LNIP,volume 11752)

Abstract

In recent years, great advances in Domain Adaptation (DA) have been possible through deep neural networks. While this is true even for multi-source scenarios, most of the methods are based on the assumption that the domain to which each sample belongs is known a priori. However, in practice, we might have a source domain composed by a mixture of multiple sub-domains, without any prior about the sub-domain to which each source sample belongs. In this case, while multi-source DA methods are not applicable, restoring to single-source ones may lead to sub-optimal results. In this work, we explore a recent direction in deep domain adaptation: automatically discovering latent domains in visual datasets. Previous works address this problem by using a domain prediction branch, trained with an entropy loss. Here we present a novel formulation for training the domain prediction branch which exploits (i) domain prediction output for various perturbations of the input features and (ii) the min-entropy consensus loss, which forces the predictions of the perturbation to be both consistent and with low entropy. We compare our approach to the previous state-of-the-art on publicly-available datasets, showing the effectiveness of our method both quantitatively and qualitatively.

Keywords

  • Domain Adaptation
  • Visual recognition
  • Deep learning

This is a preview of subscription content, access via your institution.

Chapter
USD   29.95
Price excludes VAT (USA)
  • DOI: 10.1007/978-3-030-30645-8_36
  • Chapter length: 12 pages
  • Instant PDF download
  • Readable on all devices
  • Own it forever
  • Exclusive offer for individuals only
  • Tax calculation will be finalised during checkout
eBook
USD   89.00
Price excludes VAT (USA)
  • ISBN: 978-3-030-30645-8
  • Instant PDF download
  • Readable on all devices
  • Own it forever
  • Exclusive offer for individuals only
  • Tax calculation will be finalised during checkout
Softcover Book
USD   119.99
Price excludes VAT (USA)
Learn about institutional subscriptions
Fig. 1.
Fig. 2.
Fig. 3.

Notes

  1. 1.

    https://github.com/HolmesShuan/ResNet-18-Caffemodel-on-ImageNet.

References

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

    MathSciNet  CrossRef  Google Scholar 

  2. Bousmalis, K., Silberman, N., Dohan, D., Erhan, D., Krishnan, D.: Unsupervised pixel-level domain adaptation with generative adversarial networks. In: CVPR (2017)

    Google Scholar 

  3. Carlucci, F.M., D’Innocente, A., Bucci, S., Caputo, B., Tommasi, T.: Domain generalization by solving jigsaw puzzles. In: CVPR (2019)

    Google Scholar 

  4. Carlucci, F.M., Porzi, L., Caputo, B., Ricci, E., Rota Bulò, S.: Autodial: automatic domain alignment layers. In: ICCV (2017)

    Google Scholar 

  5. Carlucci, F.M., Porzi, L., Caputo, B., Ricci, E., Bulò, S.R.: Just DIAL: domain alignment layers for unsupervised domain adaptation. In: Battiato, S., Gallo, G., Schettini, R., Stanco, F. (eds.) ICIAP 2017. LNCS, vol. 10484, pp. 357–369. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-68560-1_32

    CrossRef  Google Scholar 

  6. D’Innocente, A., Caputo, B.: Domain generalization with domain-specific aggregation modules. In: Brox, T., Bruhn, A., Fritz, M. (eds.) GCPR 2018. LNCS, vol. 11269, pp. 187–198. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-12939-2_14

    CrossRef  Google Scholar 

  7. Donahue, J., et al.: Decaf: a deep convolutional activation feature for generic visual recognition. In: ICML (2014)

    Google Scholar 

  8. Duan, L., Tsang, I.W., Xu, D., Chua, T.S.: Domain adaptation from multiple sources via auxiliary classifiers. In: ICML (2009)

    Google Scholar 

  9. French, G., Mackiewicz, M., Fisher, M.: Self-ensembling for visual domain adaptation. In: ICLR (2018)

    Google Scholar 

  10. Ganin, Y., Lempitsky, V.: Unsupervised domain adaptation by backpropagation. In: ICML (2015)

    Google Scholar 

  11. Gong, B., Grauman, K., Sha, F.: Reshaping visual datasets for domain adaptation. In: NIPS (2013)

    Google Scholar 

  12. He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770–778 (2016)

    Google Scholar 

  13. Hoffman, J., Kulis, B., Darrell, T., Saenko, K.: Discovering latent domains for multisource domain adaptation. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, pp. 702–715. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-33709-3_50

    CrossRef  Google Scholar 

  14. Huang, J., Gretton, A., Borgwardt, K.M., Schölkopf, B., Smola, A.J.: Correcting sample selection bias by unlabeled data. In: NIPS (2006)

    Google Scholar 

  15. Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. arXiv preprint arXiv:1502.03167 (2015)

  16. Jia, Y., et al.: Caffe: convolutional architecture for fast feature embedding. In: ACM-Multimedia, pp. 675–678. ACM (2014)

    Google Scholar 

  17. Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: NIPS, pp. 1097–1105 (2012)

    Google Scholar 

  18. Li, D., Yang, Y., Song, Y.Z., Hospedales, T.M.: Deeper, broader and artier domain generalization. In: ICCV (2017)

    Google Scholar 

  19. Li, W., Xu, Z., Xu, D., Dai, D., Van Gool, L.: Domain generalization and adaptation using low rank exemplar SVMs. IEEE T-PAMI 40(5), 1114–1127 (2018)

    CrossRef  Google Scholar 

  20. Li, Y., Wang, N., Shi, J., Liu, J., Hou, X.: Revisiting batch normalization for practical domain adaptation. arXiv preprint arXiv:1603.04779 (2016)

  21. Long, M., Wang, J.: Learning transferable features with deep adaptation networks. In: ICML (2015)

    Google Scholar 

  22. Long, M., Wang, J., Jordan, M.I.: Unsupervised domain adaptation with residual transfer networks. In: NIPS (2016)

    Google Scholar 

  23. Mancini, M., Bulò, S.R., Caputo, B., Ricci, E.: Best sources forward: domain generalization through source-specific nets. In: ICIP (2018)

    Google Scholar 

  24. Mancini, M., Bulò, S.R., Caputo, B., Ricci, E.: Robust place categorization with deep domain generalization. IEEE RAL 3(3), 2093–2100 (2018)

    Google Scholar 

  25. Mancini, M., Bulò, S.R., Caputo, B., Ricci, E.: Adagraph: Unifying predictive and continuous domain adaptation through graphs. In: CVPR (2019)

    Google Scholar 

  26. Mancini, M., Karaoguz, H., Ricci, E., Jensfelt, P., Caputo, B.: Kitting in the wild through online domain adaptation. In: IROS (2018)

    Google Scholar 

  27. Mancini, M., Porzi, L., Bulò, S.R., Caputo, B., Ricci, E.: Boosting domain adaptation by discovering latent domains. In: CVPR (2018)

    Google Scholar 

  28. Mansour, Y., Mohri, M., Rostamizadeh, A.: Domain adaptation: Learning bounds and algorithms. arXiv preprint arXiv:0902.3430 (2009)

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

    CrossRef  Google Scholar 

  30. Roy, S., Siarohin, A., Sangineto, E., Bulo, S.R., Sebe, N., Ricci, E.: Unsupervised domain adaptation using feature-whitening and consensus loss. In: CVPR (2019)

    Google Scholar 

  31. Russo, P., Carlucci, F.M., Tommasi, T., Caputo, B.: From source to target and back: symmetric bi-directional adaptive GAN. In: CVPR (2018)

    Google Scholar 

  32. Saenko, K., Kulis, B., Fritz, M., Darrell, T.: Adapting visual category models to new domains. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010. LNCS, vol. 6314, pp. 213–226. Springer, Heidelberg (2010). https://doi.org/10.1007/978-3-642-15561-1_16

    CrossRef  Google Scholar 

  33. Saito, K., Ushiku, Y., Harada, T.: Asymmetric tri-training for unsupervised domain adaptation. arXiv preprint arXiv:1702.08400 (2017)

  34. Srivastava, N., Hinton, G.E., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929–1958 (2014)

    MathSciNet  MATH  Google Scholar 

  35. Sun, Q., Chattopadhyay, R., Panchanathan, S., Ye, J.: A two-stage weighting framework for multi-source domain adaptation. In: NIPS (2011)

    Google Scholar 

  36. Xiong, C., McCloskey, S., Hsieh, S.H., Corso, J.J.: Latent domains modeling for visual domain adaptation. In: AAAI (2014)

    Google Scholar 

  37. Xu, R., Chen, Z., Zuo, W., Yan, J., Lin, L.: Deep cocktail network: multi-source unsupervised domain adaptation with category shift. In: CVPR (2018)

    Google Scholar 

  38. Xu, Z., Li, W., Niu, L., Xu, D.: Exploiting low-rank structure from latent domains for domain generalization. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8691, pp. 628–643. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10578-9_41

    CrossRef  Google Scholar 

  39. Zeng, X., Ouyang, W., Wang, M., Wang, X.: Deep learning of scene-specific classifier for pedestrian detection. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8691, pp. 472–487. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10578-9_31

    CrossRef  Google Scholar 

Download references

Acknowledgements

This work was partially supported by the ERC grant 637076 - RoboExNovo.

Author information

Authors and Affiliations

  1. Sapienza University of Rome, Rome, Italy

    Massimiliano Mancini

  2. Fondazione Bruno Kessler, Trento, Italy

    Massimiliano Mancini

  3. Mapillary Research, Graz, Austria

    Lorenzo Porzi

  4. Politecnico di Torino, Turin, Italy

    Fabio Cermelli & Barbara Caputo

  5. Italian Institute of Technology, Turin, Italy

    Massimiliano Mancini, Fabio Cermelli & Barbara Caputo

Authors
  1. Massimiliano Mancini
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Lorenzo Porzi
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Fabio Cermelli
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Barbara Caputo
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Massimiliano Mancini .

Editor information

Editors and Affiliations

  1. University of Trento, Povo, Italy

    Elisa Ricci

  2. Mapillary Research, Graz, Austria

    Samuel Rota Bulò

  3. University of Amsterdam, Amsterdam, The Netherlands

    Cees Snoek

  4. Fondazione Bruno Kessler, Povo, Italy

    Oswald Lanz

  5. Fondazione Bruno Kessler, Povo, Italy

    Stefano Messelodi

  6. University of Trento, Povo, Italy

    Nicu Sebe

Rights and permissions

Reprints and Permissions

Copyright information

© 2019 Springer Nature Switzerland AG

About this paper

Verify currency and authenticity via CrossMark

Cite this paper

Mancini, M., Porzi, L., Cermelli, F., Caputo, B. (2019). Discovering Latent Domains for Unsupervised Domain Adaptation Through Consistency. In: Ricci, E., Rota Bulò, S., Snoek, C., Lanz, O., Messelodi, S., Sebe, N. (eds) Image Analysis and Processing – ICIAP 2019. ICIAP 2019. Lecture Notes in Computer Science(), vol 11752. Springer, Cham. https://doi.org/10.1007/978-3-030-30645-8_36

Download citation

  • DOI: https://doi.org/10.1007/978-3-030-30645-8_36

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-30644-1

  • Online ISBN: 978-3-030-30645-8

  • eBook Packages: Computer ScienceComputer Science (R0)