Abstract
In this paper we develop an algorithm for structured prediction that optimizes against complex performance measures, those which are a function of false positive and false negative counts. The approach can be directly applied to performance measures such as F β score (natural language processing), intersection over union (image segmentation), Precision/Recall at k (search engines) and ROC area (binary classifiers). We attack this optimization problem by approximating the loss function with a piecewise linear function and relaxing the obtained QP problem to a LP which we solve with an off-the-shelf LP solver. We present experiments on object class-specific segmentation and show significant improvement over baseline approaches that either use simple loss functions or simple compatibility functions on VOC 2009.
Chapter PDF
References
Hoiem, D., Efros, A.A., Hebert, M.: Closing the loop in scene interpretation. In: Proc. IEEE Comput. Soc. Conf. Comput. Vision and Pattern Recogn. (2008)
Blaschko, M.B., Lampert, C.H.: Learning to localize objects with structured output regression. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part I. LNCS, vol. 5302, pp. 2–15. Springer, Heidelberg (2008)
Desai, C., Ramanan, D., Fowlkes, C.: Discriminative models for multi-class object layout. In: ICCV (2009)
Malik, J., Belongie, S., Leung, T., Shi, J.: Contour and texture analysis for image segmentation. Int. Journal of Computer Vision 43, 7–27 (2001)
Boykov, Y., Veksler, O., Zabih, R.: Fast approximate energy minimization via graph cuts. IEEE Trans. PAMI 23, 1222–1239 (2001)
Szummer, M., Kohli, P., Hoiem, D.: Learning crfs using graph cuts. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part II. LNCS, vol. 5303, pp. 582–595. Springer, Heidelberg (2008)
Everingham, M., Van Gool, L., Williams, C.K.I., Winn, J., Zisserman, A.: The PASCAL Visual Object Classes Challenge (VOC2009) Results (2009), http://www.pascal-network.org/challenges/VOC/voc2009/workshop/index.html
Taskar, B., Chatalbashev, V., Koller, D., Guestrin, C.: Learning structured prediction models: a large margin approach. In: ICML 2005, pp. 896–903 (2005)
Tsochantaridis, I., Hofmann, T., Joachims, T., Altun, Y.: Support vector machine learning for interdependent and structured output spaces. In: ICML (2004)
Joachims, T.: A support vector method for multivariate performance measures. In: ICML 2005, pp. 377–384. ACM, New York (2005)
Werner, T.: A linear programming approach to max-sum problem: A review. IEEE Trans. PAMI 29, 1165–1179 (2007)
Kohli, P., Torr, P.H.S.: Measuring uncertainty in graph cut solutions. Comput. Vis. Image Underst. 112, 30–38 (2008)
Komodakis, N., Tziritas, G.: Approximate labeling via graph-cuts based on linear programming. IEEE Trans. PAMI 29 (2007)
Felzenszwalb, P.F., Huttenlocher, D.P.: Efficient graph-based image segmentation. Int. Journal of Computer Vision 59 (2004)
van de Sande, K.E.A., Gevers, T., Snoek, C.G.M.: Evaluating color descriptors for object and scene recognition. IEEE Trans. PAMI (2010)
Leibe, B., Leonardis, A., Schiele, B.: Combined object categorization and segmentation with an implicit shape model. In: ECCV Workshop on Statistical Learning in Computer Vision, pp. 17–32 (2004)
Felzenszwalb, P., Girshick, R., McAllester, D., Ramanan, D.: Object detection with discriminatively trained part based models. IEEE Trans. PAMI (2009)
Mosek: The mosek optimization software (2010), http://www.mosek.com
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2010 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Ranjbar, M., Mori, G., Wang, Y. (2010). Optimizing Complex Loss Functions in Structured Prediction. In: Daniilidis, K., Maragos, P., Paragios, N. (eds) Computer Vision – ECCV 2010. ECCV 2010. Lecture Notes in Computer Science, vol 6312. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-15552-9_42
Download citation
DOI: https://doi.org/10.1007/978-3-642-15552-9_42
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-15551-2
Online ISBN: 978-3-642-15552-9
eBook Packages: Computer ScienceComputer Science (R0)