•Considering the features of the training sample patch itself, we propose a novel atomic learning formula based on contrast weights. In addition, an online discriminative dictionary learning ...algorithm based on contrast weight (CDL) is proposed to solve the formula.•We use l1-norm and l2,1-norm to measure the sparsity and reconstruction errors of sparse coefficients, and then combine these two measures to improve the expression of “outliers” in the coefficients. In addition, we propose a saliency map fusion method based on global gradient optimization to optimize the fusion effect of multiple saliency maps.•Experimental results on four datasets show that the proposed model is very competitive with the state-of-the-art methods under six evaluation metrics, especially on the VSRS dataset.
Display omitted
Object detection in very high resolution (VHR) optical remote sensing (RS) images is one of the most fundamental but challenging tasks in the field of RS image analysis. To reduce the computational complexity of redundant information and improve the efficiency of image processing, visual saliency models have been widely applied in this field. In this paper, a novel saliency detection model based on Contrast-weighted Dictionary Learning (CDL) is proposed for VHR optical RS images. Specifically, the proposed CDL learns salient and non-salient atoms from positive and negative samples to construct a discriminant dictionary, in which a contrast-weighted term is proposed to encourage the contrast-weighted patterns to be present in the learned salient dictionary while discouraging them from being present in the non-salient dictionary. Then, we measure the saliency by combining the coefficients of the sparse representation (SR) and reconstruction errors. Furthermore, by using the proposed joint saliency measure, a variety of saliency maps are generated based on the discriminant dictionary. Finally, a fusion method based on global gradient optimization is proposed to integrate multiple saliency maps. Experimental results on four datasets demonstrate that the proposed model outperforms other state-of-the-art methods.
Mining discriminative graph topological information plays an important role in promoting graph representation ability. However, it suffers from two main issues: (1) the difficulty/complexity of ...computing global inter-class/intra-class scatters, commonly related to mean and covariance of graph samples, for discriminant learning; (2) the huge complexity and variety of graph topological structure that is rather challenging to robustly characterize. In this paper, we propose the Wasserstein Discriminant Dictionary Learning (WDDL) framework to achieve discriminant learning on graphs with robust graph topology modeling, and hence facilitate graph-based pattern analysis tasks. Considering the difficulty of calculating global inter-class/intra-class scatters, a reference set of graphs (aka graph dictionary) is first constructed by generating representative graph samples (aka graph keys) with expressive topological structure. Then, a Wasserstein Graph Representation (WGR) process is proposed to project input graphs into a succinct dictionary space through the graph dictionary lookup. To further achieve discriminant graph learning, a Wasserstein discriminant loss (WD-loss) is defined on the graph dictionary, in which the graph keys are optimizable, to make the intra-class keys more compact and inter-class keys more dispersed. Hence, the calculation of global Wasserstein metric (W-metric) centers can be bypassed. For sophisticated topology mining in the WGR process, a joint-Wasserstein graph embedding module is constructed to model both between-node and between-edge relationships across inputs and graph keys by encapsulating both the Wasserstein metric (between cross-graph nodes) and proposed novel Kron-Gromov-Wasserstein (KGW) metric (between cross-graph adjacencies). Specifically, the KGW-metric comprehensively characterizes the cross-graph connection patterns with the Kronecker operation, then adaptively captures those salient patterns through connection pooling. To evaluate the proposed framework, we study two graph-based pattern analysis problems, i.e. graph classification and cross-modal retrieval, with the graph dictionary flexibly adjusted to cater to these two tasks. Extensive experiments are conducted to comprehensively compare with existing advanced methods, as well as dissect the critical component of our proposed architecture. The experimental results validate the effectiveness of the WDDL framework.
Single image deraining as a fundamental task in computer vision is important in improving the visual quality of images and videos. In this paper, we propose a feature-guided dictionary learning ...method for patch-and-group sparse representation in single image deraining. Specifically, we develop an external dictionary that learns the generic feature representation from a lot of natural images using Gaussian mixture models (GMMs), and a novel strategy is designed to learn an internal dictionary using the given rainy image guiding by the generic features. The external dictionary and the internal dictionary are adaptively tailored to produce a coherent dictionary, which can extend the representation abilities of the learned dictionary for the group-based sparse representation. Moreover, we present a novel patch-and-group sparse representation framework to reconstruct an image tending to be free of rain by simultaneously combining the local sparsity and the nonlocal self-similarity property. This framework can integrate their advantages of the two representative methods capable of capturing more effective features for the single image deraining. The results of experiments on both the synthetic and the real-world rainy images demonstrate that the proposed method delivers more favorable visual effects and superior quality results, and it outperforms several other state-of-the-art methods.
•A feature-guided dictionary learning method is proposed for single image deraining.•A coherent dictionary is learned using the rainy image guided by a lot of natural images.•A patch-and-group sparse representation framework is applied to reconstruct an image tended to be free of rain.•Experimental results demonstrate the effectiveness of the proposed method.
This paper aims at developing a dictionary-learning-based method for completing the visual tensor data with missing elements. Traditional dictionary learning approaches suffer from very high ...computational costs when processing high-dimensional tensor data. Some existing approaches for acceleration impose orthogonality constraints or rank-one decompositions on dictionary atoms; however, the expressibility of the resulting dictionary is rather limited. To address such issues, we propose a convolutional analysis model for tensor dictionary learning, where the update of sparse coefficients during dictionary learning is simple and fast. Furthermore, we propose an orthogonality-constrained convolutional factorization scheme for dictionary construction, in which each tensor dictionary atom is factorized by the convolution of two atoms selected from two orthogonal factor dictionaries respectively. This factorization scheme enables us to efficiently learn an expressive dictionary with over-completeness and non-rank-one atoms. Based on our convolutional analysis model and factorization scheme, an effective yet efficient dictionary learning method is proposed for visual tensor completion. Extensive experiments show that, our method not only outperforms existing dictionary-based approaches with relatively-low time cost, but also outperforms recent low-rank approaches.
Recently, label consistent k-svd (LC-KSVD) algorithm has been successfully applied in image classification. The objective function of LC-KSVD is consisted of reconstruction error, classification ...error and discriminative sparse codes error with ℓ0-norm sparse regularization term. The ℓ0-norm, however, leads to NP-hard problem. Despite some methods such as orthogonal matching pursuit can help solve this problem to some extent, it is quite difficult to find the optimum sparse solution. To overcome this limitation, we propose a method named label embedded dictionary learning (LEDL), which embeds the label information into ℓ1 regularized dictionary learning algorithm to improve the performance of image classification tasks. Specifically, (i) compared to LC-KSVD, we utilise the ℓ1-norm to transfer the sparse constraint problem to convex optimization problem; (ii) alternating direction method of multipliers (ADMM) is adopted to solve the sparse constraint problem to improve the optimization speed; (iii) extensive experimental results on six benchmark datasets illustrate that the classification rate of our proposed algorithm exceeds the LC-KSVD algorithm and our proposed algorithm has achieved state-of-the-art performance.
This book provides easy to read, concise, and clinically useful explanations of over 1800 terms and concepts from the field of psychoanalysis. A history of each term is included in its definition and ...so is the name of its originator. The attempt is made to demonstrate how the meanings of the term under consideration might have changed, with new connotations accruing with the passage of time and with growth of knowledge. Where indicated and possible, the glossary includes diverse perspectives on a given idea and highlights how different analysts have used the same term for different purposes and with different theoretical aims in mind.
•ℓ0TDL reconstruction algorithm was proposed for low-dose spectral CT.•ℓ0TDL method protect image edge information and recover finer image structure.•ℓ0TDL reduce reconstructed image artifacts.•An ...efficient split-Bregman method based the proposed ℓ0TDL model iterative algorithm is developed.•The parameter of proposed ℓ0TDL was optimized by experiments.
Spectral computed tomography (CT) has a great superiority in lesion detection, tissue characterization and material decomposition. To further extend its potential clinical applications, in this work, we propose an improved tensor dictionary learning method for low-dose spectral CT reconstruction with a constraint of image gradient ℓ0-norm, which is named as ℓ0TDL. The ℓ0TDL method inherits the advantages of tensor dictionary learning (TDL) by employing the similarity of spectral CT images. On the other hand, by introducing the ℓ0-norm constraint in gradient image domain, the proposed method emphasizes the spatial sparsity to overcome the weakness of TDL on preserving edge information. The split-bregman method is employed to solve the proposed method. Both numerical simulations and real mouse studies are perform to evaluate the proposed method. The results show that the proposed ℓ0TDL method outperforms other competing methods, such as total variation (TV) minimization, TV with low rank (TV+LR), and TDL methods.