Learning Discriminative Dictionary for Group Sparse Representation

Abstract

In recent years, sparse representation has been widely used in object recognition applications. How to learn the dictionary is a key issue to sparse representation. A popular method is to use l1 norm as the sparsity measurement of representation coefficients for dictionary learning. However, the l1 norm treats each atom in the dictionary independently, so the learned dictionary cannot well capture the multisubspaces structural information of the data. In addition, the learned subdictionary for each class usually shares some common atoms, which weakens the discriminative ability of the reconstruction error of each subdictionary. This paper presents a new dictionary learning model to improve sparse representation for image classification, which targets at learning a class-specific subdictionary for each class and a common subdictionary shared by all classes. The model is composed of a discriminative fidelity, a weighted group sparse constraint, and a subdictionary incoherence term. The discriminative fidelity encourages each class-specific subdictionary to sparsely represent the samples in the corresponding class. The weighted group sparse constraint term aims at capturing the structural information of the data. The subdictionary incoherence term is to make all subdictionaries independent as much as possible. Because the common subdictionary represents features shared by all classes, we only use the reconstruction error of each class-specific subdictionary for classification. Extensive experiments are conducted on several public image databases, and the experimental results demonstrate the power of the proposed method, compared with the state-of-the-arts.

Discriminative Nonlinear Analysis Operator Learning: When Cosparse Model Meets Image Classification

“…In the previous researches, the parametric feature model P(X|F, θ P )P(F) will be characterized by the above regularized linear synthesis model with θ P = D and a regularization term on F, e.g., sparsity inducing 1 norm [15]- [17], [26], square 2 norm [27], group sparsity inducing 1,2 norm [28], low rank inducing nuclear norm [29], their combinations [30], hierarchical prior [19], elastic net and Fisher term [3], [18]. Although these different regularizations can all compute the MAP solutions of a discriminative dictionary and features to promote the classification performance, this feature model will suffer from the following intrinsic problems.…”

Laplace Graph Embedding Class Specific Dictionary Learning for Face Recognition

“…The class specific dictionary learning method trained a dictionary for each class of samples. Sun et al [23] learned a class specific subdictionary for each class and a common subdictionary shared by all classes to improve the classification performance. Wang and Kong [24] proposed a method to explicitly learn a class specific dictionary for each category, which captures the most discriminative features of this category, and simultaneously learn a common pattern pool, whose atoms are shared by all the categories and only contribute to representation of the data rather than discrimination.…”

Tensor-Based Sparse Representation Classification for Urban Airborne LiDAR Points

“…Sparse coding is to find a certain small number of base atoms from the dictionary for reconstruction raw data. Sparse coding can be solved by Orthogonal Matching Pursuit (OMP) [14] , LASSO (least absolute shrinkage and selection operator) [13], or the gradient descent algorithm [15]. The dictionary can generally come from two sources: mathematical model-based methods and the dictionary learning from training data.…”