Discovering Latent Domains for Unsupervised Domain Adaptation Through Consistency

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11752)


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.


Domain Adaptation Visual recognition Deep learning 



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


  1. 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)MathSciNetCrossRefGoogle Scholar
  2. 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. 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. 4.
    Carlucci, F.M., Porzi, L., Caputo, B., Ricci, E., Rota Bulò, S.: Autodial: automatic domain alignment layers. In: ICCV (2017)Google Scholar
  5. 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). Scholar
  6. 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). Scholar
  7. 7.
    Donahue, J., et al.: Decaf: a deep convolutional activation feature for generic visual recognition. In: ICML (2014)Google Scholar
  8. 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. 9.
    French, G., Mackiewicz, M., Fisher, M.: Self-ensembling for visual domain adaptation. In: ICLR (2018)Google Scholar
  10. 10.
    Ganin, Y., Lempitsky, V.: Unsupervised domain adaptation by backpropagation. In: ICML (2015)Google Scholar
  11. 11.
    Gong, B., Grauman, K., Sha, F.: Reshaping visual datasets for domain adaptation. In: NIPS (2013)Google Scholar
  12. 12.
    He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770–778 (2016)Google Scholar
  13. 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). Scholar
  14. 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. 15.
    Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. arXiv preprint arXiv:1502.03167 (2015)
  16. 16.
    Jia, Y., et al.: Caffe: convolutional architecture for fast feature embedding. In: ACM-Multimedia, pp. 675–678. ACM (2014)Google Scholar
  17. 17.
    Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: NIPS, pp. 1097–1105 (2012)Google Scholar
  18. 18.
    Li, D., Yang, Y., Song, Y.Z., Hospedales, T.M.: Deeper, broader and artier domain generalization. In: ICCV (2017)Google Scholar
  19. 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)CrossRefGoogle Scholar
  20. 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. 21.
    Long, M., Wang, J.: Learning transferable features with deep adaptation networks. In: ICML (2015)Google Scholar
  22. 22.
    Long, M., Wang, J., Jordan, M.I.: Unsupervised domain adaptation with residual transfer networks. In: NIPS (2016)Google Scholar
  23. 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. 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. 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. 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. 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. 28.
    Mansour, Y., Mohri, M., Rostamizadeh, A.: Domain adaptation: Learning bounds and algorithms. arXiv preprint arXiv:0902.3430 (2009)
  29. 29.
    Pan, S.J., Yang, Q.: A survey on transfer learning. IEEE Trans. Knowl. Data Eng. 22(10), 1345–1359 (2010)CrossRefGoogle Scholar
  30. 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. 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. 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). Scholar
  33. 33.
    Saito, K., Ushiku, Y., Harada, T.: Asymmetric tri-training for unsupervised domain adaptation. arXiv preprint arXiv:1702.08400 (2017)
  34. 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)MathSciNetzbMATHGoogle Scholar
  35. 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. 36.
    Xiong, C., McCloskey, S., Hsieh, S.H., Corso, J.J.: Latent domains modeling for visual domain adaptation. In: AAAI (2014)Google Scholar
  37. 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. 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). Scholar
  39. 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). Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.Sapienza University of RomeRomeItaly
  2. 2.Fondazione Bruno KesslerTrentoItaly
  3. 3.Mapillary ResearchGrazAustria
  4. 4.Politecnico di TorinoTurinItaly
  5. 5.Italian Institute of TechnologyTurinItaly

Personalised recommendations