Abstract
This chapter deals with object recognition in images involving a weakly supervised classification model. In weakly supervised learning, the label information of the training dataset is provided as a prior knowledge for each class. This prior knowledge is coming from a global proportion annotation of images. In this chapter, we compare three opposed classification models in a weakly supervised classification issue: a generative model, a discriminative model and a model based on random forests. Models are first introduced and discussed, and an application to fisheries acoustics is presented. Experiments show that random forests outperform discriminative and generative models in supervised learning but random forests are not robust to high complexity class proportions. Finally, a compromise is achieved by taking a combination of classifiers that keeps the accuracy of random forests and exploits the robustness of discriminative models.
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
Bhattacharyya, A.: On a measure of divergence between two statistical populations defined by probability distributions. Bull. Calcutta Maths. Soc. 35, 99–109 (1943)
Breiman, L.: Random forests. Machine Learning 45, 5–32 (2001)
Breiman, L., Friedman, J., Olshen, R., Stone, C.: Classification and regression trees. Chapman and Hall, Boca Raton (1984)
Chapelle, O., Schölkopf, B., Zien, A.: Semi-supervised learning. MIT Press, Cambridge (2006)
Chung, J., Kim, T., Nam Chae, Y., Yang, H.: Unsupervised constellation model learning algorithm based on voting weight control for accurate face localization. Pattern Recognition 42(3), 322–333 (2009)
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)
Dempster, A., Laird, N., Rubin, D.: Maximum likelihood from incomplete data via the em algorithm. Jour. of the RSS 39, Series B(1), 1–38 (1977)
Dietterich, T.: An experimental comparison of three methods for constructing ensembles of decision trees. Machine Learning 40(2), 139–158 (2000)
Fablet, R., Lefort, R., Scalabrin, C., Massé, J., Boucher, J.M.: Weakly supervised learning using proportion based information: an application to fisheries acoustic. In: International Conference on Pattern Recognition (2008)
Fergus, R., Perona, P., Zisserman, A.: Object class recognition by unsupervised scale invariant learning. In: Conference on Computer Vision and Pattern Recognition (2003)
Fishburn, P.: Utility theory for decision making. John Wiley and Sons, New York (1970)
Fisher, R.: The use of multiple measurements in taxonomic problems. In: Annals of Eugenics, pp. 179–188 (1936)
Freund, Y., Schapire, R.: A decision-theoretic generalization of on-line learning and an application to boosting. Journal of Computer and System Sciences 55, 119–139 (1997)
Gu, L., Xing, E., Kanade, T.: Learning gmrf structures for spatial priors. In: Conference on Computer Vision and Pattern Recognition, pp. 1–6 (2007)
Kass, G.: An exploratory technique for invesgating large quantities of categorical data. Journal of applied statistics 29(2), 119–127 (1980)
Lefort, R., Fablet, R., Boucher, J.M.: Combining image-level and object-level inference for weakly supervised object recognition. application to fisheries acoustics. In: International Conference on Image Processing (2009)
Lefort, R., Fablet, R., Boucher, J.M.: Weakly supervised learning with decision trees applied to fisheries acoustics. In: IEEE International Conference on Acoustics, Speech and Signal Processing (2010)
Loh, W.Y., Shih, Y.Y.: Split selection methods for classification trees. Statistica Sinica 7, 815–840 (1997)
Petitgas, P., Massé, J., Beillois, P., Lebarbier, E., Le Cann, A.: Sampling variance of species identification in fisheries acoustic surveys based on automated procedures associating acoustic images and trawl hauls. ICES Journal of Marine Science 60(3), 437–445 (2003)
Ponce, J., Hebert, M., Schmid, C., Ziserman, A.: Toward Category-Level Object Recognition. LNCS. Springer, Heidelberg (2006)
Quinlan, J.: C4.5: Programs for machine learning. Morgan Kaufmann, San Francisco (1993)
Scalabrin, C., Massé, J.: Acoustic detection of the spatial and temporal distribution of fish shoals in the bay of biscay. Aquatic Living Resources 6, 269–283 (1993)
Schölkopf, B., Smola, A.: Learning with Kernels. The MIT Press, Cambridge (2002)
Schmid, C.: Weakly supervised learning of visual models and its application to content-based retrieval. International Journal on Computer Vision 56, 7–16 (2004)
Shivani, A., Roth, D.: Learning a sparse representation for object detection. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2353, pp. 113–127. Springer, Heidelberg (2002)
Ulusoy, I., Bishop, C.: Generative versus discriminative methods for object recognition. In: Conference on Computer Vision and Pattern Recognition, vol. 2, pp. 258–265 (2005)
Vidal-Naquet, M., Ullmann, S.: Object recognition with informative features and linear classification. In: ICCV (2003)
Weber, M., Welling, M., Perona, P.: Unsupervised learning of models for recognition. In: Vernon, D. (ed.) ECCV 2000. LNCS, vol. 1842, pp. 18–32. Springer, Heidelberg (2000)
Xie, L., Perez, P.: Slightly supervised learning of part-based appearance models. In: Computer Vision and Pattern Recognition Workshop, vol. 6 (2004)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Lefort, R., Fablet, R., Boucher, JM. (2011). Weakly Supervised Learning: Application to Fish School Recognition. In: Ruano, A.E., Várkonyi-Kóczy, A.R. (eds) New Advances in Intelligent Signal Processing. Studies in Computational Intelligence, vol 372. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-11739-8_10
Download citation
DOI: https://doi.org/10.1007/978-3-642-11739-8_10
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-11738-1
Online ISBN: 978-3-642-11739-8
eBook Packages: EngineeringEngineering (R0)