Dual graph-regularized Constrained Nonnegative Matrix Factorization for Image Clustering = Dual graph-regularized Constrained Nonnegative Matrix Factorization for Image Clustering

다국어 초록 (Multilingual Abstract)

Nonnegative matrix factorization (NMF) has received considerable attention due to its effectiveness of reducing high dimensional data and importance of producing a parts-based image representation. Most of existing NMF variants attempt to address the assertion that the observed data distribute on a nonlinear low-dimensional manifold. However, recent research results showed that not only the observed data but also the features lie on the low-dimensional manifolds. In addition, a few hard priori label information is available and thus helps to uncover the intrinsic geometrical and discriminative structures of the data space. Motivated by the two aspects above mentioned, we propose a novel algorithm to enhance the effectiveness of image representation, called Dual graph-regularized Constrained Nonnegative Matrix Factorization (DCNMF). The underlying philosophy of the proposed method is that it not only considers the geometric structures of the data manifold and the feature manifold simultaneously, but also mines valuable information from a few known labeled examples. These schemes will improve the performance of image representation and thus enhance the effectiveness of image classification. Extensive experiments on common benchmarks demonstrated that DCNMF has its superiority in image classification compared with state-of-the-art methods.

참고문헌 (Reference)

1 I. Dhillon, "Weighted graph cuts without eigenvectors: a multilevel approch" 29 (29): 1944-1957, 2007

2 A. Narita, "Tensor factorization using auxiliary information" 25 (25): 501-516, 2012

3 H. Zha, "Spectral relaxation for k-means clustering" 1057-1064, 2001

4 F. Shang, "Robust positive semidefinite L-Isomap ensemble" 32 (32): 640-649, 2011

5 J. Wright, "Robust face recognition via sparse representation" 1-2, 2008

6 V. Sindhwani, "Regularized co-clustering with dual supervision" 1505-1512, 2008

7 P. Paatero, "Positive matrix factorization: a non-negative factor model with optimal utilization of error estimates of data values" 5 (5): 111-126, 1994

8 C. H. Q. Ding, "On the equivalence of non-negative matrix factorization and spectral clustering" 606-610, 2005

9 S. T. Roweis, "Nonlinear dimensionality reduction by locally linear embedding" 290 (290): 2323-2326, 2000

10 F. Sun, "Multi-label image categorization with sparse factor representation" 23 (23): 1028-1037, 2014

11 M. Belkin, "Manifold regularization: a geometric framework for learning from labeled and unlabeled examples" 7 (7): 2399-2434, 2006

12 T. M. Mitchell, "Machine learning" McGraw-Hill 1986

13 D. D. Lee, "Learning the parts of objects by non-negative matrix factorization" 6755 (6755): 788-791, 1999

14 M. Belkin, "Laplacian eigenmaps and spectral techniques for embedding and clustering" 14 (14): 585-591, 2002

15 X. Jia, "Image multi-label annotation based on supervised nonnegative matrix factorization with new matching measurement" 2016

16 X. B. Shu, "Image classification with tailored fine-grained dictionaries" 1-1, 2016

17 Z. Q. Shu, "Graph-regularized constrained non-negative matrix factorization algorithm and its application to image representation" 26 (26): 300-306, 2013

18 C. Deng, "Graph regularized non-negative matrix factorization for data representation" 33 (33): 1548-1560, 2010

19 F. Sun, "Graph regularized and sparse nonnegative matrix factorization with hard constraints for data representation" 173 (173): 233-244, 2016

20 F. H. Shang, "Graph dual regularization non-negative matrix factorization for co-clustering" 45 (45): 2237-2250, 2012

21 A. K. Jain, "Data clustering: a review" 31 (31): 264-323, 1999

22 H. Liu, "Constrained non-negative matrix factorization for image representation" 34 (34): 1299-1311, 2012

23 W. Michael, "Computing sparse reduced-rank approximations to sparse matrices" 31 (31): 252-269, 2005

24 Q. Gu, "Co-clustering on manifolds" 359-368, 2009

25 Z. Li, "Clustering-guided sparse structural learning for unsupervised feature selection" 26 (26): 2138-2150, 2014

26 D. D. Lee, "Algorithms for nonnegative matrix factorization" 556-562, 2000

27 J. B. Tenenbaum, "A global geometric framework for nonlinear dimensionality reduction" 290 (290): 2319-2323, 2000