Advertisement

Beyond Dataset Bias: Multi-task Unaligned Shared Knowledge Transfer

  • Tatiana Tommasi
  • Novi Quadrianto
  • Barbara Caputo
  • Christoph H. Lampert
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7724)

Abstract

Many visual datasets are traditionally used to analyze the performance of different learning techniques. The evaluation is usually done within each dataset, therefore it is questionable if such results are a reliable indicator of true generalization ability. We propose here an algorithm to exploit the existing data resources when learning on a new multiclass problem. Our main idea is to identify an image representation that decomposes orthogonally into two subspaces: a part specific to each dataset, and a part generic to, and therefore shared between, all the considered source sets. This allows us to use the generic representation as un-biased reference knowledge for a novel classification task. By casting the method in the multi-view setting, we also make it possible to use different features for different databases. We call the algorithm MUST, Multitask Unaligned Shared knowledge Transfer. Through extensive experiments on five public datasets, we show that MUST consistently improves the cross-datasets generalization performance.

Keywords

Projection Matrix Domain Adaptation Distribution Mismatch Transfer Learn Projection Matrice 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Fei-Fei, L., Fergus, R., Perona, P.: Learning generative visual models from few training examples: An incremental bayesian approach tested on 101 object categories. Comput. Vis. Image Underst. 106, 59–70 (2007)CrossRefGoogle Scholar
  2. 2.
    Everingham, M., Van Gool, L., Williams, C.K.I., Winn, J., Zisserman, A.: The PASCAL Visual Object Classes Challenge 2007 (VOC 2007) Results (2007), http://www.pascal-network.org/challenges/VOC/
  3. 3.
    Lampert, C.H., Nickisch, H., Harmeling, S.: Learning to detect unseen object classes by between class attribute transfer. In: CVPR (2009)Google Scholar
  4. 4.
    Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: A Large-Scale Hierarchical Image Database. In: CVPR (2009)Google Scholar
  5. 5.
    Torralba, A., Efros, A.A.: Unbiased look at dataset bias. In: CVPR (2011)Google Scholar
  6. 6.
    Perronnin, F., Sánchez, J., Liu, Y.: Large-scale image categorization with explicit data embedding. In: CVPR (2010)Google Scholar
  7. 7.
    Stark, M.M., Riesenfeld, R.F.: Wordnet: An electronic lexical database. In: Eurographics Workshop on Rendering. MIT Press (1998)Google Scholar
  8. 8.
    Salakhutdinov, R., Torralba, A., Tenenbaum, J.: Learning to Share Visual Appearance for Multiclass Object Detection. In: CVPR (2011)Google Scholar
  9. 9.
    Blitzer, J., Crammer, K., Kulesza, A., Pereira, O., Wortman, J.: Learning bounds for domain adaptation. In: NIPS (2008)Google Scholar
  10. 10.
    Ben-david, S., Blitzer, J., Crammer, K., Sokolova, P.M.: Analysis of representations for domain adaptation. In: NIPS (2007)Google Scholar
  11. 11.
    Blitzer, J., McDonald, R., Pereira, F.: Domain adaptation with structural correspondence learning. In: EMNLP (2006)Google Scholar
  12. 12.
    Daumé III, H.: Frustratingly easy domain adaptation. In: ACL (2007)Google Scholar
  13. 13.
    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
  14. 14.
    Gopalan, R., Li, R., Chellappa, R.: Domain adaptation for object recognition: An unsupervised approach. In: ICCV (2011)Google Scholar
  15. 15.
    Gong, B., Shi, Y., Sha, F., Grauman, K.: Geodesic flow kernel for unsupervised domain adaptation. In: CVPR (2012)Google Scholar
  16. 16.
    Pan, S.J., Yang, Q.: A survey on transfer learning. IEEE Transactions on Knowledge and Data Engineering 22, 1345–1359 (2010)CrossRefGoogle Scholar
  17. 17.
    Jie, L., Tommasi, T., Caputo, B.: Multiclass transfer learning from unconstrained priors. In: ICCV (2011)Google Scholar
  18. 18.
    Evgeniou, T., Pontil, M.: Regularized multi–task learning. In: KDD (2004)Google Scholar
  19. 19.
    Kang, Z., Grauman, K., Sha, F.: Learning with whom to share in multi-task feature learning. In: ICML (2011)Google Scholar
  20. 20.
    Wang, X., Zhang, C., Zhang, Z.: Boosted multi-task learning for face verification with applications to web image and video search. In: CVPR (2009)Google Scholar
  21. 21.
    Vezhnevets, A., Buhmann, J.M.: Towards weakly supervised semantic segmentation by means of multiple instance and multitask learning. In: CVPR (2010)Google Scholar
  22. 22.
    Quadrianto, N., Smola, A.J., Caetano, T.S., Vishwanathan, S.V.N., Petterson, J.: Multitask learning without label correspondences. In: NIPS (2010)Google Scholar
  23. 23.
    Parameswaran, S., Weinberger, K.: Large margin multi-task metric learning. In: NIPS (2010)Google Scholar
  24. 24.
    Leen, G.: Context assisted information extraction. PhD thesis, University of the West of Scotland (2008)Google Scholar
  25. 25.
    Jia, Y., Salzmann, M., Darrell, T.: Factorized latent spaces with structured sparsity. In: NIPS (2010)Google Scholar
  26. 26.
    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
  27. 27.
    Weinberger, K., Saul, L.: Distance metric learning for large margin nearest neighbor classification. Journal of Machine Learning Research 10, 207–244 (2009)zbMATHGoogle Scholar
  28. 28.
    Goldberger, J., Roweis, S.T., Hinton, G.E., Salakhutdinov, R.: Neighbourhood components analysis. In: NIPS (2004)Google Scholar
  29. 29.
    Quadrianto, N., Lampert, C.H.: Learning multi-view neighborhood preserving projections. In: ICML (2011)Google Scholar
  30. 30.
    Kleiner, A., Rahimi, A., Jordan, M.I.: Random conic pursuit for semidefinite programming. In: NIPS (2010)Google Scholar
  31. 31.
    Lewis, A.S., Overton, M.L.: Nonsmooth optimization via quasi-newton methods. Math. Programming (to appear)Google Scholar
  32. 32.
    Microsoft Research Cambridge Object Recognition Image Database (2005), http://research.microsoft.com/en-us/downloads/
  33. 33.
    Krizhevsky, A.: Learning multiple layers of features from tiny images. Technical Report MSc thesis, University of Toronto, USA (2007)Google Scholar
  34. 34.
    Oliva, A., Torralba, A.: Modeling the shape of the scene: A holistic representation of the spatial envelope. IJCV 42, 145–175 (2001)zbMATHCrossRefGoogle Scholar
  35. 35.
    Gibbons, J.: Nonparametric Statistical Inference. Marcel Dekker, New York (1985)zbMATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Tatiana Tommasi
    • 1
    • 2
  • Novi Quadrianto
    • 3
  • Barbara Caputo
    • 1
  • Christoph H. Lampert
    • 4
  1. 1.Idiap Research InstituteMartignySwitzerland
  2. 2.École Polytechnique Fédérale de LausanneSwitzerland
  3. 3.University of CambridgeUK
  4. 4.IST Austria (Institute of Science and Technology Austria)KlosterneuburgAustria

Personalised recommendations