Towards Learning Free Naive Bayes Nearest Neighbor-Based Domain Adaptation

  • Faraz Saeedan
  • Barbara CaputoEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9280)


As of today, object categorization algorithms are not able to achieve the level of robustness and generality necessary to work reliably in the real world. Even the most powerful convolutional neural network we can train fails to perform satisfactorily when trained and tested on data from different databases. This issue, known as domain adaptation and/or dataset bias in the literature, is due to a distribution mismatch between data collections. Methods addressing it go from max-margin classifiers to learning how to modify the features and obtain a more robust representation. Recent work showed that by casting the problem into the image-to-class recognition framework, the domain adaptation problem is significantly alleviated [23]. Here we follow this approach, and show how a very simple, learning free Naive Bayes Nearest Neighbor (NBNN)-based domain adaptation algorithm can significantly alleviate the distribution mismatch among source and target data, especially when the number of classes and the number of sources grow. Experiments on standard benchmarks used in the literature show that our approach (a) is competitive with the current state of the art on small scale problems, and (b) achieves the current state of the art as the number of classes and sources grows, with minimal computational requirements.


Naive Bayes Nearest Neighbor Domain adaptation Transfer learning 


  1. 1.
    Bay, H., Ess, A., Tuytelaars, T., Gool, V.: SURF: Speeded up robust features. CVIU 110, 346–359 (2008)Google Scholar
  2. 2.
    Ben-David, S., Blitzer, J., Crammer, K., Pereira, F.: Anaylsis of representations for domain adaptation. In: NIPS (2007)Google Scholar
  3. 3.
    Bergamo, A., Torresani, L.: Exploiting weakly-labeled web images to improve object classification: a domain adaptation approach. In: NIPS (2010)Google Scholar
  4. 4.
    Blitzer, J., McDonald, R., Pereira, F.: Domain adaptation with structural correspondence learning. In: EMNLP (2006)Google Scholar
  5. 5.
    Boiman, O., Shechtman, E., Irani, M.: In defense of nearest-neighbor based image classification. In: CVPR (2008)Google Scholar
  6. 6.
    Bruzzone, L., Marconcini, M.: Domain adaptation problems: A DASVM classification technique and a circular validation strategy. IEEE PAMI 32(5), 770–787 (2010)CrossRefGoogle Scholar
  7. 7.
    Caputo, B., Müller, H., Martinez-Gomez, J., Villegas, M., Acar, B., Patricia, N., Marvasti, N., Üsküdarlı, S., Paredes, R., Cazorla, M., Garcia-Varea, I., Morell, V.: ImageCLEF 2014: overview and analysis of the results. In: Kanoulas, E., Lupu, M., Clough, P., Sanderson, M., Hall, M., Hanbury, A., Toms, E. (eds.) CLEF 2014. LNCS, vol. 8685, pp. 192–211. Springer, Heidelberg (2014) Google Scholar
  8. 8.
    Chatfield, K., Simonyan, K., Vedaldi, A., Zisserman A.: Return of the Devil in the Details: Delving Deep into Convolutional NetsGoogle Scholar
  9. 9.
    Daume III., H.: Frustratingly easy domain adaptation. In: ACL (2007)Google Scholar
  10. 10.
    Duan, L., Tsang, I.W.-H., Xu, D., Maybank, S.J.: Domain transfer svm for video concept detection. In: CVPR (2009)Google Scholar
  11. 11.
    Fornoni, M., Caputo, B.: Scene recognition with naive bayes non-linear learning. In: Proc. ICPR (2014)Google Scholar
  12. 12.
    Gong, B., Grauman, K., Sha, F.: Connecting the dots with landmarks: discriminatively learning domain-invariant features for unsupervised domain adaptation. In: JMLR (2013)Google Scholar
  13. 13.
    Gong, B., Shi, Y., Sha, F., Grauman, K.: Geodesic flow kernel for unsupervised domain adaptation. In: CVPR (2012)Google Scholar
  14. 14.
    Gopalan, R., Li, R., Chellappa, R.: Domain adaptation for object recognition: an unsupervised approach. In: ICCV (2011)Google Scholar
  15. 15.
    Griffin, G., Holub, A., Perona, P.: Caltech 256 object category dataset. Technical Report UCB/USD-04-1366, California Institute of Technology (2007)Google Scholar
  16. 16.
    Khosla, A., Zhou, T., Malisiewicz, T., Efros, A.A., Torralba, A.: Undoing the damage of dataset bias. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part I. LNCS, vol. 7572, pp. 158–171. Springer, Heidelberg (2012) CrossRefGoogle Scholar
  17. 17.
    Ni, J., Qiu, Q., Chellappa, R.: Subspace interpolation via dictionary learning for unsupervised domain adaptation. In: CVPR (2013)Google Scholar
  18. 18.
    Patricia, N., Caputo, B.: Learning to learn, from transfer learning to domain adaptation: a unifying persspective. In: CVPR (2014)Google Scholar
  19. 19.
    Qiu, Q., Patel, V.M., Turaga, P., Chellappa, R.: Domain adaptive dictionary learning. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part IV. LNCS, vol. 7575, pp. 631–645. Springer, Heidelberg (2012) CrossRefGoogle Scholar
  20. 20.
    Quionero-Candela, J., Sugiyama, M., Schwaighofer, A., Lawrence, N.: Dataset Shift in Machine Learning. The MIT Press (2009)Google Scholar
  21. 21.
    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, Part IV. LNCS, vol. 6314, pp. 213–226. Springer, Heidelberg (2010) CrossRefGoogle Scholar
  22. 22.
    Tommasi, T., Caputo, B.: The more you know, the less you learn: from knowledge transfer to one-shot learning of object categories. In: Proc. BMVC (2009)Google Scholar
  23. 23.
    Tommasi, T., Caputo, B.: Frustratingly easy NBNN domain adaptation. In: ICCV (2013)Google Scholar
  24. 24.
    Tommasi, T., Orabona, F., Caputo, B.: Learning categories from few examples with multi model knowledge transfer. IEEE Transaction on PAMI 36(5), 928–941 (2014)CrossRefGoogle Scholar
  25. 25.
    Tommasi, T., Orabona, F., Castellini, C., Caputo, B.: Improving control of dexterous hand prostheses using adaptive learning. IEEE Transaction on Robotics, pp. 1–13 (2013)Google Scholar
  26. 26.
    Tommasi, T., Quadrianto, N., Caputo, B., Lampert, C.H.: Beyond dataset bias: multi-task unaligned shared knowledge transfer. In: Lee, K.M., Matsushita, Y., Rehg, J.M., Hu, Z. (eds.) ACCV 2012, Part I. LNCS, vol. 7724, pp. 1–15. Springer, Heidelberg (2013) CrossRefGoogle Scholar
  27. 27.
    Torralba, A., Efros, A.A.: Unbiased look at dataset bias. In: CVPR (2011)Google Scholar
  28. 28.
    Yang, J., Yan, R., Hauptmann, A.G.: Cross-domain video concept detection using adaptive svms. In: ACM Multimedia (2007)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  1. 1.Sapienza UniversityRomeItaly
  2. 2.Idiap Research InstituteMartignySwitzerland

Personalised recommendations