Projects authored by ran he.


About: This letter proposes a new multiple linear regression model using regularized correntropy for robust pattern recognition. First, we motivate the use of correntropy to improve the robustness of the classicalmean square error (MSE) criterion that is sensitive to outliers. Then an l1 regularization scheme is imposed on the correntropy to learn robust and sparse representations. Based on the half-quadratic optimization technique, we propose a novel algorithm to solve the nonlinear optimization problem. Second, we develop a new correntropy-based classifier based on the learned regularization scheme for robust object recognition. Extensive experiments over several applications confirm that the correntropy-based l1 regularization can improve recognition accuracy and receiver operator characteristic curves under noise corruption and occlusion.

Changes:

Initial Announcement on mloss.org.


About: Robust sparse representation has shown significant potential in solving challenging problems in computer vision such as biometrics and visual surveillance. Although several robust sparse models have been proposed and promising results have been obtained, they are either for error correction or for error detection, and learning a general framework that systematically unifies these two aspects and explore their relation is still an open problem. In this paper, we develop a half-quadratic (HQ) framework to solve the robust sparse representation problem. By defining different kinds of half-quadratic functions, the proposed HQ framework is applicable to performing both error correction and error detection. More specifically, by using the additive form of HQ, we propose an L1-regularized error correction method by iteratively recovering corrupted data from errors incurred by noises and outliers; by using the multiplicative form of HQ, we propose an L1-regularized error detection method by learning from uncorrupted data iteratively. We also show that the L1-regularization solved by soft-thresholding function has a dual relationship to Huber M-estimator, which theoretically guarantees the performance of robust sparse representation in terms of M-estimation. Experiments on robust face recognition under severe occlusion and corruption validate our framework and findings.

Changes:

Initial Announcement on mloss.org.


About: We study the problem of robust feature extraction based on L21 regularized correntropy in both theoretical and algorithmic manner. In theoretical part, we point out that an L21-norm minimization can be justified from the viewpoint of half-quadratic (HQ) optimization, which facilitates convergence study and algorithmic development. In particular, a general formulation is accordingly proposed to unify L1-norm and L21-norm minimization within a common framework. In algorithmic part, we propose an L21 regularized correntropy algorithm to extract informative features meanwhile to remove outliers from training data. A new alternate minimization algorithm is also developed to optimize the non-convex correntropy objective. In terms of face recognition, we apply the proposed method to obtain an appearance-based model, called Sparse-Fisherfaces. Extensive experiments show that our method can select robust and sparse features, and outperforms several state-of-the-art subspace methods on largescale and open face recognition datasets.

Changes:

Initial Announcement on mloss.org.


About: Ran He, Wei-Shi Zheng,Tieniu Tan, and Zhenan Sun. Half-quadratic based Iterative Minimization for Robust Sparse Representation. Submitted to IEEE Trans. on Pattern Analysis and Machine Intelligence.

Changes:

Initial Announcement on mloss.org.


Logo Efficient Nonnegative Sparse Coding Algorithm 1.0

by openpr_nlpr - January 4, 2012, 09:44:18 CET [ Project Homepage BibTeX BibTeX for corresponding Paper Download ] 2089 views, 439 downloads, 1 subscription

About: Nonnegative Sparse Coding, Discriminative Semi-supervised Learning, sparse probability graph

Changes:

Initial Announcement on mloss.org.


About: In this paper, we propose an improved principal component analysis based on maximum entropy (MaxEnt) preservation, called MaxEnt-PCA, which is derived from a Parzen window estimation of Renyi’s quadratic entropy. Instead of minimizing the reconstruction error either based on L2-norm or L1-norm, the MaxEnt-PCA attempts to preserve as much as possible the uncertainty information of the data measured by entropy. The optimal solution of MaxEnt-PCA consists of the eigenvectors of a Laplacian probability matrix corresponding to the MaxEnt distribution. MaxEnt-PCA (1) is rotation invariant, (2) is free from any distribution assumption, and (3) is robust to outliers. Extensive experiments on real-world datasets demonstrate the effectiveness of the proposed linear method as compared to other related robust PCA methods.

Changes:

Initial Announcement on mloss.org.


About: This code is developed based on Uriel Roque's active set algorithm for the linear least squares problem with nonnegative variables in: Portugal, L.; Judice, J.; and Vicente, L. 1994. A comparison of block pivoting and interior-point algorithms for linear least squares problems with nonnegative variables. Mathematics of Computation 63(208):625-643.Ran He, Wei-Shi Zheng and Baogang Hu, "Maximum Correntropy Criterion for Robust Face Recognition," IEEE TPAMI, in press, 2011.

Changes:

Initial Announcement on mloss.org.


Logo Two stage Sparse Representation 1.0.0

by openpr_nlpr - December 2, 2011, 05:32:31 CET [ Project Homepage BibTeX Download ] 1228 views, 414 downloads, 1 subscription

About: This program implements a novel robust sparse representation method, called the two-stage sparse representation (TSR), for robust recognition on a large-scale database. Based on the divide and conquer strategy, TSR divides the procedure of robust recognition into outlier detection stage and recognition stage. The extensive numerical experiments on several public databases demonstrate that the proposed TSR approach generally obtains better classification accuracy than the state-of-the-art Sparse Representation Classification (SRC). At the same time, by using the TSR, a significant reduction of computational cost is reached by over fifty times in comparison with the SRC, which enables the TSR to be deployed more suitably for large-scale dataset.

Changes:

Initial Announcement on mloss.org.