Robust Subspace Segmentation by Low-Rank Representation

By Guangcan Liu, Zhouchen Lin, Yong Yu. International Conference on Machine Learning, 2010

1,748 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/047175fb23f6f152d86e81100ba7140dd2847636

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Dacheng Tao
2. Changqing Zhang
3. René Vidal
4. Zhouchen Lin
5. Shuicheng Yan
6. Lei Zhang
7. Yi Yang
8. Luc Van Gool

Citations in the corpus

• See all by looking at a few: Sparse modeling for finding representative objects (2012, background): “In this section, we formulate the problem of finding representative objects from the collection of data points.”
• Low rank subspace clustering (LRSC) (2014, methodology): “…is given by A ¼ US1 a ðRÞV>, where S!ðxÞ is the shrinkage-thresholding operator S!ðxÞ ¼ x+ ! x > ! xþ ! x < +! 0 else: 8 >< >: ð7Þ Notice that the latter solution does not coincide with the one given by PCA, which performs hard-thresholding of the singular values of D without shrinking them by 1=a.”
• Multi-view Domain Generalization for Visual Recognition (2015, methodology): “, which cluster each weight vector w i belongs to) by using low-rank representation (LRR) [28], which has shown promising results in various real-world applications [37, 36].”
• Dual Principal Component Pursuit (2015, methodology): “Recently, two attractive methods have appeared (Xu et al., 2012; Soltanolkotabi and Candès, 2012) that are directly based on convex optimization and are inspired by low-rank representation (Liu et al., 2010) and compressed sensing (Candès and Wakin, 2008).”
• Infrared and Visible Image Fusion with ResNet and zero-phase component analysis (2018, methodology): “t sections. 4.2. The eect of dierent networks and norms In this section, we choose dierent networks(VGG19[18], ResNet50[19] and ResNet101[19]) and dierent norms(l 1-norm, l 2-norm and nuclear-norm[31]) to evaluate our fusion framework. When the nuclear-norm is utilized in our framework, Eq.5 is rewr”
• Sparse Subspace Clustering: Algorithm, Theory, and Applications (2013, methodology): “Using advances in sparse [29], [30], [31] and low-rank [32], [33], [34] recovery algorithms, the Sparse Subspace Clustering (SSC) [35], [36], [37], Low-Rank Recovery (LRR) [38], [39], [40], and Low-Rank Subspace Clustering (LRSC) [41] algorithms pose the clustering problem as one of finding a sparse”
• Multiview Spectral Clustering via Structured Low-Rank Matrix Factorization (2017, unknown): “To this end, Low-Rank Representation (LRR) [ Xia et al. , 2014; Liu et al. , 2010; Wang et al. , 2015c; Liu and Yan, 2011; Liu et al. , 2013 ] is proposed.”
• A closed form solution to robust subspace estimation and clustering (2011, methodology): “The LRR algorithm proceeds by solving the optimization problem in (18) using an ALM method.”
• Weighted Nuclear Norm Minimization and Its Applications to Low Level Vision (2016, methodology): “…facial images can be modeled as reflections of a Lambertian object and approximated by a low dimensional linear subspace; this low rank nature leads to a proper reconstruction of a face model from occluded/corrupted face images (De La Torre and Black, 2003; Liu et al, 2010; Zheng et al, 2012).”
• Low-Rank Representation for Multi-center Autism Spectrum Disorder Identification (2018, unknown): “We first compared our MCLRR method with 3 baseline methods, including KNN, support vector machine (SVM), and classical low-rank representation (LRR) method [6].”
• Graph-Regularized Low-Rank Representation for Destriping of Hyperspectral Images (2013, background): “By following [27], (7) is first converted into the equivalent problem”
• Nonconvex Nonsmooth Low Rank Minimization via Iteratively Reweighted Nuclear Norm (2015, methodology): “.56 67.19 UMINST 54.26 54.09 56.00 58.09 TableIIshows the face clustering accuracies of NTLRR, compared with LRR, LatLRR and TLRR. The performances of LRR and LatLRR are consistent with previous work [46], [36]. Also, it can be seen that TLRR achieve better performance than LRR and LatLRR, since it ”
• A Geometric Analysis of Subspace Clustering with Outliers (2011, methodology): “We believe that a major advantage of SSC vis a vis more recent approaches [13, 28] is that the eigen-gap heuristic is applicable under broader circumstances.”
• Robust and Efficient Subspace Segmentation via Least Squares Regression (2012, methodology): “ingthe subspaces, existing works can be roughlydividedinto four categories: algebraicmethods [5] [6], iterative methods [7] [8], statistical methods [9] [10] and spectral clustering-basedmethods [11] [12] [13] [14]. A review of these methods can be found in [15]. In this work, we review four most re”