cvpr cvpr2013 cvpr2013-125 cvpr2013-125-reference knowledge-graph by maker-knowledge-mining
Source: pdf
Author: Yi-Chen Chen, Vishal M. Patel, Jaishanker K. Pillai, Rama Chellappa, P. Jonathon Phillips
Abstract: We propose a novel dictionary-based learning method for ambiguously labeled multiclass classification, where each training sample has multiple labels and only one of them is the correct label. The dictionary learning problem is solved using an iterative alternating algorithm. At each iteration of the algorithm, two alternating steps are performed: a confidence update and a dictionary update. The confidence of each sample is defined as the probability distribution on its ambiguous labels. The dictionaries are updated using either soft (EM-based) or hard decision rules. Extensive evaluations on existing datasets demonstrate that the proposed method performs significantly better than state-of-the-art ambiguously labeled learning approaches.
[1] M. Aharon, M. Elad, and A. M. Bruckstein. The K− SVD: an algo− rithm for designing of overcomplete dictionaries for sparse represen− tation. IEEE Transactions on Signal Processing, 54(1 1):431 1–4322, 2006. 2, 3, 5
[2] J. A. Bilmes. A gentle tutorial of the em algorithm and its applica− tion to parameter estimation for gaussian mixture and hidden markov models. ICSI and U.C. Berkeley, TR-97-021, April, 1998. 4
[3] C. M. Bishop. Pattern Recognition and Machine Learning. Springer, October, 2007. 4
[4] Y.− C. Chen, C. S. Sastry, V. M. Patel, P. J. Phillips, and R. Chellappa. Rotation invarient simultaneous clustering and dictionary learning. IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2012. 1
[5] T. Cour, B. Sapp, C. Jordan, and B. Taskar. Learning from ambigu− ously labeled images. IEEE Computer Vision and Pattern Recognition (CVPR), pages 919–926, June 2009. 1, 5, 6, 7
[6] T. Cour, B. Sapp, and B. Taskar. Learning from partial labels. Journal of Machine Learning Research (JMLR), 12: 1225–1261, 2011. 1, 5, 6, 7
[7] F. Dellaert. The expectation maximization algorithm. Georgia Institute of Technology, GIT-GVU-02-20, February, 2002. 4
[8] A. P. Dempster, N. M. Laird, and D. B. Rubin. Maximum likelihood from incomplete data via the em algorithm. Journal of the Royal Statistical Society: Series B, 39(1): 1–38, 1977. 1
[9] E. Elhamifar and R. Vidal. Sparse subspace clustering. IEEE Computer Vision and Pattern Recognition (CVPR), pages 2790–2797, June 2009. 1
[10] G. Huang, V. Jian, and E. Learned− Miller. Unsupervised joint align− ment of complex images. International Conference on Computer Vision (ICCV), 2007. 6
[11] K. Huang and S. Aviyente. Sparse representation for signal clas− sification. Proceedings of Neural Information Processing Systems (NIPS), 19:609–616, 2007. 1
[12] E. H ¨ullermeier and J. Beringer. Learning from ambiguously labeled examples. Intell. Data Anal., 10(5):419–439, Sept. 2006. 1
[13] R. Jin and Z. Ghahramani. Learning with multiple labels. Proceedings of Neural Information Processing Systems (NIPS), pages 897– 904, 2002. 1, 6
[14] J. Mairal, F. Bach, J. Pnce, G. Sapiro, and A. Zisserman. Discrimi− native learned dictionaries for local image analysis. IEEE Computer Vision and Pattern Recognition (CVPR), Anchorage, AL, June 2008. 1
[15] J. Mairal, F. Bach, and J. Ponce. Task− driven dictionary learning. IEEE Transactions on Pattern Analysis and Machine Intelligence, 34(4):791 –804, April 2012. 1
[16] J. Mairal, F. Bach, J. Ponce, G. Sapiro, and A. Zisserman. Supervised dictionary learning. Advances in Neural Information Processing Systems, Vancouver, B.C., Canada, Dec. 2008. 1
[17] M. Ranzato, F. Haung, Y. Boureau, and Y. LeCun. Unsupervised learning of invariant feature hierarchies with applications to ob− ject recognition. IEEE Computer Vision and Pattern Recognition (CVPR), pages 1–8, 2007. 1
[18] A. Shrivastava, J. K. Pillai, V. M. Patel, and R. Chellappa. Learning discriminative dictionaries with partially labeled data. International Conference on Image Processing (ICIP), 2012. 1, 5
[19] T. Sim, S. Baker, and M. Bsat. The cmu pose, illumination, and ex− pression database. IEEE Transactions on Pattern Analysis and Machine Intelligence, 25(12): 1615–1618, Dec. 2003. 6
[20] P. Sprechmann and G. Sapiro. Dictionary learning and sparse cod− ing for unsupervised clustering. IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pages 2042– 2045, March 2010. 1, 5 333565880