Abstract
Real-time object detection is one of the core problems in computer vision. The cascade boosting framework proposed by Viola and Jones has become the standard for this problem. In this framework, the learning goal for each node is asymmetric, which is required to achieve a high detection rate and a moderate false positive rate. We develop new boosting algorithms to address this asymmetric learning problem. We show that our methods explicitly optimize asymmetric loss objectives in a totally corrective fashion. The methods are totally corrective in the sense that the coefficients of all selected weak classifiers are updated at each iteration. In contract, conventional boosting like AdaBoost is stage-wise in that only the current weak classifier’s coefficient is updated. At the heart of the totally corrective boosting is the column generation technique. Experiments on face detection show that our methods outperform the state-of-the-art asymmetric boosting methods.
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.J.: Robust real-time face detection. Int. J. Comp. Vis. 57, 137–154 (2004)
Viola, P., Jones, M.: Fast and robust classification using asymmetric AdaBoost and a detector cascade. In: Proc. Adv. Neural Inf. Process. Syst., pp. 1311–1318. MIT Press, Cambridge (2002)
Fan, W., Stolfo, S., Zhang, J., Chan, P.: Adacost: Misclassification cost-sensitive boosting. In: Proc. Int. Conf. Mach. Learn., pp. 97–105 (1999)
Li, S.Z., Zhang, Z.: Float Boost learning and statistical face detection. IEEE Trans. Pattern Anal. Mach. Intell. 26, 1112–1123 (2004)
Xiao, R., Zhu, L., Zhang, H.: Boosting chain learning for object detection. In: Proc. IEEE Int. Conf. Comp. Vis., pp. 709–715 (2003)
Hou, X., Liu, C., Tan, T.: Learning boosted asymmetric classifiers for object detection. In: Proc. IEEE Conf. Comp. Vis. Patt. Recogn. (2006)
Pham, M.T., Hoang, V.D.D., Cham, T.J.: Detection with multi-exit asymmetric boosting. In: Proc. IEEE Conf. Comp. Vis. Patt. Recogn. (2008)
Bourdev, L., Brandt, J.: Robust object detection via soft cascade. In: Proc. IEEE Conf. Comp. Vis. Patt. Recogn., San Diego, CA, US, pp. 236–243 (2005)
Xiao, R., Zhu, H., Sun, H., Tang, X.: Dynamic cascades for face detection. In: Proc. IEEE Int. Conf. Comp. Vis., Rio de Janeiro, Brazil (2007)
Wu, J., Brubaker, S.C., Mullin, M.D., Rehg, J.M.: Fast asymmetric learning for cascade face detection. IEEE Trans. Pattern Anal. Mach. Intell. 30, 369–382 (2008)
Liu, C., Shum, H.Y.: Kullback-Leibler boosting. In: Proc. IEEE Conf. Comp. Vis. Patt. Recogn., Madison, Wisconsin, vol. 1, pp. 587–594 (2003)
Zhu, C., Byrd, R.H., Nocedal, J.: L-BFGS-B: Algorithm 778: L-BFGS-B, FORTRAN routines for large scale bound constrained optimization. ACM Trans. Mathematical Software 23, 550–560 (1997)
Masnadi-Shirazi, H., Vasconcelos, N.: Cost-sensitive boosting. IEEE Trans. Pattern Anal. Mach. Intell. (2010)
Friedman, J., Hastie, T., Tibshirani, R.: Additive logistic regression: a statistical view of boosting. Ann. Statist. 28, 337–407 (2000)
Rätsch, G., Mika, S., Schölkopf, B., Müller, K.R.: Constructing boosting algorithms from SVMs: An application to one-class classification. IEEE Trans. Pattern Anal. Mach. Intell. 24, 1184–1199 (2002)
Demiriz, A., Bennett, K., Shawe-Taylor, J.: Linear programming boosting via column generation. Mach. Learn. 46, 225–254 (2002)
Shen, C., Li, H.: On the dual formulation of boosting algorithms. IEEE Trans. Pattern Anal. Mach. Intell. (2010)
Boyd, S., Vandenberghe, L.: Convex Optimization. Cambridge University Press, Cambridge (2004)
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
Wang, P., Shen, C., Barnes, N., Zheng, H., Ren, Z. (2011). Asymmetric Totally-Corrective Boosting for Real-Time Object Detection. In: Kimmel, R., Klette, R., Sugimoto, A. (eds) Computer Vision – ACCV 2010. ACCV 2010. Lecture Notes in Computer Science, vol 6492. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-19315-6_14
Download citation
DOI: https://doi.org/10.1007/978-3-642-19315-6_14
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-19314-9
Online ISBN: 978-3-642-19315-6
eBook Packages: Computer ScienceComputer Science (R0)