Dictionary learning has played an important role in the success of sparse representation. Although discriminative synthesis dictionary learning for sparse representation with a high-computational-complexity l 0 or l 1 norm constraint has been well studied for image classification, jointly and discriminatively learning an analysis dictionary and a synthesis dictionary is still in its infant stage. As a dual of synthesis dictionary, the recently developed analysis dictionary can provide a complementary view of data representation, which can have a much lower time complexity than sparse synthesis representation. Although several class-specific analysis-synthesis dictionary, which may have a big correlation between different classes' dictionaries, have been developed, how to learn a more compact and discriminative universal analysis-synthesis dictionary is still open. In this paper, to provide a more complete view of discriminative data representation, we propose a novel model of discriminative analysis-synthesis dictionary learning (DASDL), in which a linear classifier based on the coding coefficient is jointly learned with the dictionary pair, thus the performance of the classifier and the representational power of the dictionary pair being considered at the same time by the same optimization procedure. The size of the learned dictionaries can be very small since the analysis-synthesis dictionary is shared by all class data. An iterative algorithm to efficiently solve the proposed DASDL is presented in this paper. The experiments on face recognition, gender classification, action recognition and

Sparse coding can learn good robust representation to noise and model more higher-order representation for image classification. However, the inference algorithm is computationally expensive even though the supervised signals are used to learn compact and discriminative dictionaries in sparse coding techniques. Luckily, a simplified neural network module (SNNM) has been proposed to directly learn the discriminative dictionaries for avoiding the expensive inference. But the SNNM module ignores the sparse representations. Therefore, we propose a sparse SNNM module by adding the mixed-norm regularization (l1/l2 norm). The sparse SNNM modules are further stacked to build a sparse deep stacking network (S-DSN). In the experiments, we evaluate S-DSN with four databases, including Extended YaleB, AR, 15 scene and Caltech101. Experimental results show that our model outperforms related classification methods with only a linear classifier. It is worth noting that we reach 98.8% recognition accuracy on 15 scene.

Dictionary learning (DL), playing a key role in the success of sparse representation, has led to state-of-the-art results in image classification tasks. Among the existing supervised dictionary learning methods, the label of each dictionary atom is predefined and fixed, i.e., each dictionary atom is either associated to all classes or assigned to a single class. In this paper, we propose a structure adaptive dictionary learning (SADL) method to learn the relationship between dictionary atoms and classes, which is indicated by a binary association matrix and jointly optimized with the dictionary. The binary association matrix can not only represent class-specific dictionary atoms, but also hyper-class dictionary atoms shared by multiple classes. Furthermore, discrimination is explored by introducing Fisher criterion on coding coefficient and reducing between-class dictionary coherence. The extensive experimental results have shown the proposed SADL can achieve better performance than previous supervised dictionary learning methods on various classification databases.

No abstract