Abstract
We propose a novel unsupervised transfer learning framework that utilises unlabelled auxiliary data to quantify and select the most relevant transferrable knowledge for recognising a target object class from the background given very limited training target samples. Unlike existing transfer learning techniques, our method does not assume that auxiliary data are labelled, nor the relationships between target and auxiliary classes are known a priori. Our unsupervised transfer learning is formulated by a novel kernel adaptation transfer (KAT) learning framework, which aims to (a) extract general knowledge about how more structured objects are visually distinctive from cluttered background regardless object class, and (b) more importantly, perform selective transfer of knowledge extracted from the auxiliary data to minimise negative knowledge transfer suffered by existing methods. The effectiveness and efficiency of the proposed approach is demonstrated by performing one-class object recognition (object vs. background) task using the Caltech256 dataset.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Viola, P., Jones, M.: Rapid object detection using a boosted cascade of simple features. In: CVPR (2001)
Pinker, S.: How the minds works. W. W. Norton, New York (1999)
Bart, E., Ullman, S.: Cross-generalization: Learning novel classes from a single example by feature replacement. In: CVPR (2005)
Farhadi, A., Endres, I., Hoiem, D., Forsyth, D.: Describing objects by their attributes. In: CVPR (2009)
Lampert, C.H., Nickisch, H., Harmeling, S.: Learning to detect unseen object classes by between-class attribute transfer. In: CVPR (2009)
Stark, M., Goesele, M., Schiele, B.: A shape-based object class model for knowledge transfer. In: ICCV (2009)
Fei-Fei, L., Fergus, R., Perona, P.: One-shot learning of object categories. PAMI 28, 594–611 (2006)
Pan, S.J., Yang, Q.: A survey on transfer learning. IEEE Transactions on Knowledge and Data Engineering 22, 1345–1359 (2010)
Zweig, A., Weinshall, D.: Exploiting object hierarchy: Combining models from different category levels. In: ICCV (2007)
Pan, S.J., Kwok, J.T., Yang, Q.: Transfer learning via dimensionality reduction. In: AAAI, pp. 677–682 (2008)
Pan, S.J., Tsang, I.W., Kwok, J.T., Yang, Q.: Domain adaptation via transfer component analysis. In: IJCAI (2009)
Yang, J., Yan, R., Hauptmann, A.G.: Cross-domain video concept detection using adaptive svms. In: ACM Multimedia, pp. 188–197 (2008)
Duan, L., Tsang, I.W., Xu, D., Maybank, S.J.: Domain transfer svm for video concept detection. In: CVPR (2009)
Rosenstein, M.T., Marx, Z., Kaelbling, L.P., Dietterich, T.G.: To transfer or not to transfer. In: NIPS 2005 Workshop on Transfer Learning (2005)
Griffin, G., Holub, A., Perona, P.: Caltech-256 object category dataset, Technical Report UCB/CSD-04-1366, California Institute of Technology (2007)
Fergus, R., Perona, P., Zisserman, A.: Object class recognition by unsupervised scale-invariant learnings. In: CVPR (2003)
Raina, R., Battle, A., Lee, H., Packer, B., Ng, A.Y.: Self-taught learning: transfer learning from unlabeled data. In: ICML, pp. 759–766 (2007)
Dai, W., Jin, O., Xue, G.R., Yang, Q., Yu, Y.: Eigentransfer: a unified framework for transfer learning. In: ICML, p. 25 (2009)
Lanckriet, G., Cristianini, N., Bartlett, P., Ghaoui, L., Jordan, M.: Learning the kernel matrix with semidefinite programming. JMLR 5, 27–72 (2004)
Gehler, P., Nowozin, S.: On feature combination for multiclass object classfication. In: ICCV (2009)
Daumé, H.: Frustratingly easy domain adaptation. In: ACL (2007)
Nocedal, J., Wright, S.: Numerical optimization, 2nd edn. Springer, Heidelberg (2006)
Cristianini, N., Kandola, J., Elisseeff, A., Shawe-Taylor, J.: On kernel-target alignment. In: NIPS (2002)
Hillel, A.B., Hertz, T., Weinshall, D.: Efficient learning of relational object class models. In: ICCV (2005)
Kadir, T., Brady, M.: Saliency and image description. IJCV 45, 83–105 (2001)
Lowe, D.: Distinctive image features from scale-invariant keypoints. IJCV 2, 91–110 (2004)
Crandall, D.J., Huttenlocher, D.P.: Weakly supervised learning of part-based spatial models for visual object recognition. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3951, pp. 16–29. Springer, Heidelberg (2006)
Schnitzspan, P., Fritz, M., Schiele, B.: Hierarchical support vector random fields: Joint training to combine local and global features. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part II. LNCS, vol. 5303, pp. 527–540. Springer, Heidelberg (2008)
Rakotomamonjy, A., Bach, F., Canu, S., Grandvalet, Y.: More efficiency in multiple kernel learning. In: ICML (2007)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Zheng, WS., Gong, S., Xiang, T. (2011). Unsupervised Selective Transfer Learning for Object Recognition. In: Kimmel, R., Klette, R., Sugimoto, A. (eds) Computer Vision – ACCV 2010. ACCV 2010. Lecture Notes in Computer Science, vol 6493. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-19309-5_41
Download citation
DOI: https://doi.org/10.1007/978-3-642-19309-5_41
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-19308-8
Online ISBN: 978-3-642-19309-5
eBook Packages: Computer ScienceComputer Science (R0)