nips nips2007 nips2007-137 nips2007-137-reference knowledge-graph by maker-knowledge-mining
Source: pdf
Author: Cha Zhang, Paul A. Viola
Abstract: Cascade detectors have been shown to operate extremely rapidly, with high accuracy, and have important applications such as face detection. Driven by this success, cascade learning has been an area of active research in recent years. Nevertheless, there are still challenging technical problems during the training process of cascade detectors. In particular, determining the optimal target detection rate for each stage of the cascade remains an unsolved issue. In this paper, we propose the multiple instance pruning (MIP) algorithm for soft cascades. This algorithm computes a set of thresholds which aggressively terminate computation with no reduction in detection rate or increase in false positive rate on the training dataset. The algorithm is based on two key insights: i) examples that are destined to be rejected by the complete classifier can be safely pruned early; ii) face detection is a multiple instance learning problem. The MIP process is fully automatic and requires no assumptions of probability distributions, statistical independence, or ad hoc intermediate rejection targets. Experimental results on the MIT+CMU dataset demonstrate significant performance advantages. 1
[1] L. Bourdev and J. Brandt. Robust object detection via soft cascade. In Proc. of CVPR, 2005.
[2] S. C. Brubaker, M. D. Mullin, and J. M. Rehg. Towards optimal training of cascaded detectors. In Proc. of ECCV, 2006.
[3] J. Friedman, T. Hastie, and R. Tibshirani. Additive logistic regression: a statistical view of boosting. Technical report, Dept. of Statistics, Stanford University, 1998.
[4] S. Li, L. Zhu, Z. Zhang, A. Blake, H. Zhang, and H. Shum. Statistical learning of multi-view face detection. In Proc. of ECCV, 2002.
[5] H. Luo. Optimization design of cascaded classifiers. In Proc. of CVPR, 2005.
[6] S. J. Nowlan and J. C. Platt. A convolutional neural network hand tracker. In Proc. of NIPS, volume 7, 1995.
[7] H. Rowley, S. Baluja, and T. Kanade. Neural network-based face detection. IEEE Trans. on PAMI, 20:23–38, 1998.
[8] R. E. Schapire and Y. Singer. Improved boosting algorithms using confidence-rated predictions. Machine Learning, 37:297–336, 1999.
[9] J. Sochman and J. Matas. Waldboost - learning for time constrained sequential detection. In Proc. of CVPR, 2005.
[10] K. Sung and T. Poggio. Example-based learning for view-based face detection. IEEE Trans. on PAMI, 20:39–51, 1998.
[11] P. Viola and M. Jones. Rapid object detection using a boosted cascade of simple features. In Proc. of CVPR, 2001.
[12] P. Viola, J. C. Platt, and C. Zhang. Multiple instance boosting for object detection. In Proc. of NIPS, volume 18, 2006.
[13] B. Wu, H. Ai, C. Huang, and S. Lao. Fast rotation invariant multi-view face detection based on real adaboost. In Proc. of IEEE Automatic Face and Gesture Recognition, 2004.
[14] J. Wu, J. M. Rehg, and M. D. Mullin. Learning a rare event detection cascade by direct feature selection. In Proc. of NIPS, volume 16, 2004.
[15] R. Xiao, L. Zhu, and H. Zhang. Boosting chain learning for object detection. In Proc. of ICCV, 2003. 8