Abstract
Popular visual representations like SIFT have shown broad applicability across many task. This great generality comes naturally with a lack of specificity when focusing on a particular task or a set of classes. Metric learning approaches have been proposed to tailor general purpose representations to the needs of more specific tasks and have shown strong improvements on visual matching and recognition benchmarks. However, the performance of metric learning depends strongly on the labels that are used for learning. Therefore, we propose to combine metric learning with an active sample selection strategy in order to find labels that are representative for each class as well as improve the class separation of the learnt metric. We analyze several active sample selection strategies in terms of exploration and exploitation trade-offs. Our novel scheme achieves on three different datasets up to 10% improvement of the learned metric. We compare a batch version of our scheme to an interleaved execution of sample selection and metric learning which leads to an overall improvement of up to 23% on challenging datasets for object class recognition.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Baram, Y., El-Yaniv, R., Luz, K.: Online Choice of Active Learning Algorithms. JMLR 5, 255–291 (2004)
Basu, S., Banerjee, A., Mooney, R.: Active Semi-Supervision for Pairwise Constrained Clustering. SIAM (2004)
Cebron, N., Berthold, M.R.: Active learning for object classification: from exploration to exploitation. DMKD 18(2), 283–299 (2009)
Chang, C.C., Lin, C.J.: LIBSVM: A library for support vector machines. ACM Transactions on Intelligent Systems and Technology 2(3), 1–27 (2011)
Dasgupta, S., Hsu, D.: Hierarchical sampling for active learning. In: ICML (2008)
Davis, J., Kulis, B., Jain, P., Sra, S., Dhillon, I.: Information-theoretic metric learning. In: ICML (2007)
Ebert, S., Fritz, M., Schiele, B.: Pick Your Neighborhood – Improving Labels and Neighborhood Structure for Label Propagation. In: Mester, R., Felsberg, M. (eds.) DAGM 2011. LNCS, vol. 6835, pp. 152–162. Springer, Heidelberg (2011)
Ebert, S., Fritz, M., Schiele, B.: RALF: A Reinforced Active Learning Formulation for Object Class Recognition. In: CVPR (2012)
Goldberger, J., Roweis, S., Hinton, G., Salakhutdinov, R.: Neighbourhood Components Analysis. In: NIPS (2005)
Guillaumin, M., Verbeek, J., Schmid, C.: Multiple Instance Metric Learning from Automatically Labeled Bags of Faces. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part I. LNCS, vol. 6311, pp. 634–647. Springer, Heidelberg (2010)
Kulis, B., Jain, P., Grauman, K.: Fast Similarity Search for Learned Metrics. PAMI 31(12), 2143–2157 (2009)
Malisiewicz, T., Gupta, A., Efros, A.: Ensemble of Exemplar-SVMs for Object Detection and Beyond. In: ICCV (2011)
Nguyen, H.T., Smeulders, A.: Active learning using pre-clustering. In: ICML (2004)
Settles, B., Craven, M.: An analysis of active learning strategies for sequence labeling tasks. In: Emp. Meth. in NLP (2008)
Straka, M., Hauswiesner, S., Ruether, M., Bischof, H.: Skeletal Graph Based Human Pose Estimation in Real-Time. In: BMVC (2011)
Tong, S., Koller, D.: Support Vector Machine Active Learning with Applications to Text Classification. JMLR 2, 45–66 (2001)
Vedaldi, A., Fulkerson, B.: VLFEAT: An Open and Portable Library of Computer Vision Algorithms (2008), http://www.vlfeat.org/
Yang, L., Jin, R., et al.: Bayesian active distance metric learning. In: UAI (2007)
Zhou, D., Bousquet, O., Lal, T.N., Weston, J., Schölkopf, B.: Learning with Local and Global Consistency. In: NIPS (2004)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Ebert, S., Fritz, M., Schiele, B. (2012). Active Metric Learning for Object Recognition. In: Pinz, A., Pock, T., Bischof, H., Leberl, F. (eds) Pattern Recognition. DAGM/OAGM 2012. Lecture Notes in Computer Science, vol 7476. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-32717-9_33
Download citation
DOI: https://doi.org/10.1007/978-3-642-32717-9_33
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-32716-2
Online ISBN: 978-3-642-32717-9
eBook Packages: Computer ScienceComputer Science (R0)