iccv iccv2013 iccv2013-44 iccv2013-44-reference knowledge-graph by maker-knowledge-mining
Source: pdf
Author: Vidit Jain, Sachin Sudhakar Farfade
Abstract: Classification cascades have been very effective for object detection. Such a cascade fails to perform well in data domains with variations in appearances that may not be captured in the training examples. This limited generalization severely restricts the domains for which they can be used effectively. A common approach to address this limitation is to train a new cascade of classifiers from scratch for each of the new domains. Building separate detectors for each of the different domains requires huge annotation and computational effort, making it not scalable to a large number of data domains. Here we present an algorithm for quickly adapting a pre-trained cascade of classifiers using a small number oflabeledpositive instancesfrom a different yet similar data domain. In our experiments with images of human babies and human-like characters from movies, we demonstrate that the adapted cascade significantly outperforms both of the original cascade and the one trained from scratch using the given training examples. –
[1] A. Arnold et al. A comparative study of methods for transductive transfer learning. In ICDMW, 2007.
[2] B. Babenko, P. Doll a´r, and S. Belongie. Task specific local region matching. In ICCV, 2007.
[3] L. Bourdev and J. Brandt. Robust object detection via soft cascade. In CVPR, 2005.
[4] D. Wu et al. Domain adaptive bootstrapping for named entity recognition. In EMNLP, 2009.
[5] W. Dai, Q. Yang, G.-R. Xue, and Y. Yu. Self-taught clustering. In ICML, 2008.
[6] H. Daum e´ III and D. Marcu. Domain adaptation for statistical classifiers. JAIR, 2006.
[7] P. O. Hoyer. Non-negative matrix factorization with sparseness constraints. JMLR, 2004.
[8] W. Hu, W. Hu, and S. J. Maybank. Adaboost-based algorithm for network intrusion detection. IEEE Transactions on Systems, Man, and Cybernetics, 2008.
[9] G. B. Huang, V. Jain, and E. Learned-Miller. Unsupervised joint alignment of complex images. In ICCV, 2007.
[10] J. Blitzer et al. Learning bounds for domain adaptation. In NIPS, 2008.
[11] V. Jain and E. Learned-Miller. FDDB: A benchmark for face detection in unconstrained settings. Technical report, University of Massachusetts Amherst, 2010.
[12] V. Jain and E. Learned-Miller. Online domain adaptation of a pre-trained cascade of classifiers. In CVPR, 2011.
[13] D. D. Lee and H. S. Seung. Algorithms for non-negative matrix factorization. In NIPS, 2000.
[14] W. Liu, N. Zheng, and X. Lu. Non-negative matrix factorization for visual coding. In ICASSP, 2003.
[15] L.S. Mark et al. Wrinkling and head shape as coordinated sources of age level information. J. Per. and Psy., 1980.
[16] R. Raina et al. Self-taught learning: Transfer learning from unlabeled data. In ICML, 2007.
[17] M. Saberian and N. Vasconcelos. Boosting classifier cascades. In NIPS, 2010.
[18] P. A. Viola and M. J. Jones. Robust real-time face detection. IJCV, 2004.
[19] X. Ren. Finding people in archive films through tracking. In CVPR, 2008.
[20] C. Zhang and Z. Zhang. A survey of recent advances in face detection. Technical report, Microsoft Research, 2010.
[21] X. Zhu. Semi-Supervised Learning with Graphs. PhD thesis, CMU, 2005. 112