一种基于低秩表示的子空间聚类改进算法

张涛; 唐振民; 吕建勇

doi:10.11999/JEIT160009

一种基于低秩表示的子空间聚类改进算法

doi: 10.11999/JEIT160009

基金项目:

国家自然科学基金(61473154)

计量
- 文章访问数: 1403
- HTML全文浏览量: 110
- PDF下载量: 689
- 被引次数: 0
出版历程
- 收稿日期: 2016-01-04
- 修回日期: 2016-05-12
- 刊出日期: 2016-11-19

Improved Algorithm Based on Low Rank Representation for Subspace Clustering

Funds:

The National Natural Science Foundation of China (61473154)

摘要

摘要: 该文针对现有的基于低秩表示的子空间聚类算法使用核范数来代替秩函数，不能有效地估计矩阵的秩和对高斯噪声敏感的缺陷，提出一种改进的算法，旨在提高算法准确率的同时，保持其在高斯噪声下的稳定性。在构建目标函数时，使用系数矩阵的核范数和Forbenius范数作为正则项，对系数矩阵的奇异值进行强凸的正则化后，采用非精确的增广拉格朗日乘子方法求解，最后对求得的系数矩阵进行后处理得到亲和矩阵，并采用经典的谱聚类方法进行聚类。在人工数据集、Extended Yale B数据库和PIE数据库上同流行的子空间聚类算法的实验对比证明了所提改进算法的有效性和对高斯噪声的鲁棒性。
- 子空间聚类 /
- 低秩表示 /
- 秩函数 /
- Forbenius范数 /
- 增广拉格朗日乘子法
Abstract: The nuclear norm is used to replace the rank function in the subspace clustering algorithm based on low rank representation, it can not estimate the rank of the matrix effectively and it is sensitive to Gauss noise. In this paper, a novel algorithm is proposed to improve the accuracy and maintain its stability under the Gauss noise. When building the objective function, the nuclear norm and Forbenius norm of coefficient matrix are used as the regularization terms, after a strong convex regularizer over singular values of coefficient matrix, an inexact augmented Lagrange multiplier method is utilized to solve the problem. Finally, the affinity matrix is acquired by post-processing of coefficient matrix and the classical spectral clustering method is employed to clustering. The experimental comparison results between the state-of-the-art algorithms on synthetic data, Extended Yale B and PIE datasets demonstrate the effectiveness of the proposed improved method and the robustness to Gauss noise.
- Subspace clustering /
- Low rank representation /
- Rank function /
- Forbenius norm /
- Augmented Lagrange multiplier method

HTML全文

参考文献(23)

王卫卫, 李小平, 冯象初, 等. 稀疏子空间聚类综述[J]. 自动化学报, 2015, 41(8): 1373-1384. doi: 10.16383/j.aas.2015. c140891.

WANG Weiwei, LI Xiaoping, FENG Xiangchu, et al. A survey on sparse subspace clustering[J]. Acta Automatica Sinica, 2015, 41(8): 1373-1384. doi: 10.16383/j.aas.2015.c140891.

VIDAL R. Subspace clustering[J]. IEEE Signal Processing, 2011, 28(2): 52-68. doi: 10.1109/MSP.2010.939739.

ELHAMIFAR E and VIDAL R. Sparse subspace clustering: Algorithm, theory, and applications[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 34(11): 2765-2781. doi: 10.1109/TPAMI.2013.57.

VIDAL R and FAVARO P. Low rank subspace clustering (LRSC)[J]. Pattern Recognition Letters, 2014, 43: 47-61. doi: 10.1016/j.patrec.2013.08.006.

LIU G C, LIN Z C, and YU Y. Robust subspace segmentation by low-rank representation[C]. Proceedings of the International Conference on Machine Learning, Haifa, Israel, 2010: 663-670.

LIU G C, LIN Z C, YAN S C, et al. Robust recovery of subspace structures by low-rank representation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 35(1): 171-184. doi: 10.1109/TPAMI.2012.88.

FENG J S, LIN Z C, XU H, et al. Robust subspace segmentation with block-diagonal prior[C]. Proceedings of the IEEE International Conference on Computer Vision and Pattern Recognition, Columbus, USA, 2014: 3818-3825. doi: 10.1109/CVPR.2014.482.

ZHANG X, SUN F, LIU G C, et al. Fast low-rank subspace segmentation[J]. IEEE Transactions on Knowledge and Data Engineering, 2014, 26(5): 1293-1297. doi: 10.1109/TKDE. 2013.114.

PATEL V M, NGUYEN H V, and VIDAL R. Latent space sparse and low-rank subspace clustering[J]. IEEE Journal of Selected Topics in Signal Processing, 2015, 9(4): 691-701. doi: 10.1109/JSTSP.2015.2402643.

LIU J M, CHEN Y J, ZHANG J S, et al. Enhancing low-rank subspace clustering by manifold regularization[J]. IEEE Transactions on Image Processing, 2014, 23(9): 4022-4030. doi: 10.1109/TIP.2014.2343458.

YIN M, GAO J B, LIN Z C, et al. Dual graph regularized latent low-rank representation for subspace clustering[J]. IEEE Transactions on Image Processing, 2015, 24(12): 4918-4933. doi: 10.1109/TIP.2015.2472277.

MOL C D, VITO E D, and ROSASCO L. Elastic-net regularization in learning theory[J]. Journal of Complexity, 2009, 25(2): 201-230. doi: 10.1016/j.jco.2009. 01.002.

LIN Z C, CHEN M M, and MA Y. The augmented Lagrange multiplier method for exact recovery of corrupted low-rank matrices[R]. UIUC Technical Report UILU-ENG-09-2215, 2009.

NG A Y, JORDAN M, and WEISS Y. On spectral clustering: Analysis and an algorithm[C]. Proceedings of the Advances in Neural Information Processing Systems, Vancouver, Canada, 2001: 849-856.

LI H, CHEN N, and LI L Q. Error analysis for matrix elastic-net regularization algorithms[J]. IEEE Transactions on Neural Networks and Learning Systems, 2012, 23(5): 737-748. doi: 10.1109/TNNLS.2012.2188906.

CAI J F, CANDES E J, and SHEN Z W. A singular value thresholding algorithm for matrix completion[J]. SIAM Journal on Control and Optimization, 2010, 20(4): 1956-1982. doi: 10.1137/080738970.

SHI J B and MALIK J. Normalized cuts and image segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000, 22(8): 888-905. doi: 10.1109/ 34.868688.

BERTSEKAS D. Constrained Optimization and Lagrange Multiplier Methods[M]. Belmont, MA, USA: Athena Scientific, 1996: 326-340.

CANDES E J, LI X D, MA Y, et al. Robust principal component analysis[J]. Journal of the ACM, 2010, 58(1): 1-37. doi: 10.1145/1970392.1970395.

YAN J Y and POLLEFEYS M. A general framework for motion segmentation: Independent, articulated, rigid, non-rigid, degenerate and non-degenerate[C]. Proceedings of the European Conference on Computer Vision, Graz, Austria, 2006: 94-106. doi: 10.1007/11744085_8.

CHEN J L and LERMAN G. Spectral curvature clustering (SCC)[J]. International Journal of Computer Vision, 2009, 81(3): 317-330. doi: 10.1007/s11263-008-0178-9.

LU C Y, MIN H, ZHAO Z Q, et al. Robust and efficient subspace segmentation via least squares regression[C]. Proceedings of the European Conference on Computer Vision, Florence, Italy, 2012: 347-360. doi: 10.1007/978-3-642- 33786-4_26.

施引文献

资源附件(0)

访问统计