Abstract
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.
Chapter PDF
Similar content being viewed by others
References
Bay, H., Ess, A., Tuytelaars, T., Gool, V.: SURF: Speeded up robust features. CVIU 110, 346–359 (2008)
Ben-David, S., Blitzer, J., Crammer, K., Pereira, F.: Anaylsis of representations for domain adaptation. In: NIPS (2007)
Bergamo, A., Torresani, L.: Exploiting weakly-labeled web images to improve object classification: a domain adaptation approach. In: NIPS (2010)
Blitzer, J., McDonald, R., Pereira, F.: Domain adaptation with structural correspondence learning. In: EMNLP (2006)
Boiman, O., Shechtman, E., Irani, M.: In defense of nearest-neighbor based image classification. In: CVPR (2008)
Bruzzone, L., Marconcini, M.: Domain adaptation problems: A DASVM classification technique and a circular validation strategy. IEEE PAMI 32(5), 770–787 (2010)
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)
Chatfield, K., Simonyan, K., Vedaldi, A., Zisserman A.: Return of the Devil in the Details: Delving Deep into Convolutional Nets
Daume III., H.: Frustratingly easy domain adaptation. In: ACL (2007)
Duan, L., Tsang, I.W.-H., Xu, D., Maybank, S.J.: Domain transfer svm for video concept detection. In: CVPR (2009)
Fornoni, M., Caputo, B.: Scene recognition with naive bayes non-linear learning. In: Proc. ICPR (2014)
Gong, B., Grauman, K., Sha, F.: Connecting the dots with landmarks: discriminatively learning domain-invariant features for unsupervised domain adaptation. In: JMLR (2013)
Gong, B., Shi, Y., Sha, F., Grauman, K.: Geodesic flow kernel for unsupervised domain adaptation. In: CVPR (2012)
Gopalan, R., Li, R., Chellappa, R.: Domain adaptation for object recognition: an unsupervised approach. In: ICCV (2011)
Griffin, G., Holub, A., Perona, P.: Caltech 256 object category dataset. Technical Report UCB/USD-04-1366, California Institute of Technology (2007)
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)
Ni, J., Qiu, Q., Chellappa, R.: Subspace interpolation via dictionary learning for unsupervised domain adaptation. In: CVPR (2013)
Patricia, N., Caputo, B.: Learning to learn, from transfer learning to domain adaptation: a unifying persspective. In: CVPR (2014)
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)
Quionero-Candela, J., Sugiyama, M., Schwaighofer, A., Lawrence, N.: Dataset Shift in Machine Learning. The MIT Press (2009)
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)
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)
Tommasi, T., Caputo, B.: Frustratingly easy NBNN domain adaptation. In: ICCV (2013)
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)
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)
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)
Torralba, A., Efros, A.A.: Unbiased look at dataset bias. In: CVPR (2011)
Yang, J., Yan, R., Hauptmann, A.G.: Cross-domain video concept detection using adaptive svms. In: ACM Multimedia (2007)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Saeedan, F., Caputo, B. (2015). Towards Learning Free Naive Bayes Nearest Neighbor-Based Domain Adaptation. In: Murino, V., Puppo, E. (eds) Image Analysis and Processing — ICIAP 2015. ICIAP 2015. Lecture Notes in Computer Science(), vol 9280. Springer, Cham. https://doi.org/10.1007/978-3-319-23234-8_30
Download citation
DOI: https://doi.org/10.1007/978-3-319-23234-8_30
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-23233-1
Online ISBN: 978-3-319-23234-8
eBook Packages: Computer ScienceComputer Science (R0)