Search

This work delves into unveiling the singularity issue latent in global attention-based Transformers. Empirical and theoretical analyses elucidate that interrelationships among token channels lead to singularities, impeding the training of attention weights. Concretely, the similar neighbor pixels within image patches can form intercorrelated channels after being flattened. Images that one color dominates can possess correlated channels. Furthermore, the fixed global connection architecture retains correlation relationships, contributing to the persistence of singularities. High singularity risks reducing Transformers' performance and robustness. Based on the singularity analysis, we propose the Token Singularity Removal (TSR) strategy. It incorporates the Dual-Tree Complex Wavelet Transform (DTCWT) stem and Feature Decorrelation (FD) loss, aiming to encourage Transformers to learn tokens with unrelated channels and eliminate singularities. Experimental validation across various image classification datasets and corruption image data sets demonstrate improved accuracy and robustness of Transformers utilizing the TSR strategy. Our code is publicly available at https://github.com/wdanc/TSR. [ABSTRACT FROM AUTHOR]

• A supervised classification based MRF model is proposed for depth map up-sampling. • Low-resolution depth segmentation is used to supervise color image classification. • Classification result is further introduced in the design of MRF energy function. • The designed MRF energy function is optimized with a gradient descent algorithm. • Comparisons with the state-of-the-art show the superiority of the proposed SC-MRF model. In this paper, a Supervised Classification assisted Markov Random Field (SC-MRF) model is proposed for generating high-quality up-sampled depth maps. The proposed model aims to reduce depth bleeding and depth confusion artifacts that can be produced at boundary regions of the up-sampled depth maps. In the proposed model, segmentation of low-resolution (LR) depth map is first used to supervise the classification of corresponding high-resolution (HR) color image. With this supervised classification, not only can the depth edges be retained, but redundant textures in the HR color image can be omitted. The classification result is then introduced into the design of a MRF energy function, and the final up-sampled depth map is obtained by optimizing this energy function with the gradient descent algorithm. For simplicity, classical K -means clustering is adopted to segment the LR depth map into several classes, and a feature-based K -nearest neighbour (K -NN) method is utilized for the supervised classification. With the proposed SC-MRF model, interaction between depths of different classes will be strongly suppressed, meaning depth edges are well preserved. Comparisons with the state-of-the-art demonstrate the strong performance of the proposed method both visually and by quantitative evaluation. [ABSTRACT FROM AUTHOR]

Recently, many deep learning methods are applied with the spatial information to learn features for polarimetric synthetic aperture radar (PolSAR) image classification. However, without considering the multi-scale information, the classification performance of these methods are limited. Hence, this paper proposes a multi-scale feature extraction method based on stacked sparse autoencoder (SSAE), named the multi-scale SSAE (MS-SSAE), to improve the classification performance. This method extracts the deep multi-scale features by a two-stage framework. In the first stage, the SSAE uses training data at different scales to extract the multi-scale features. Then, a 1-D average pooling strategy is proposed to reduce the feature dimensionality at the second stage. Therefore, the MS-SSAE can capture discriminative multi-scale features. The experimental results certify that the MS-SSAE can not only improve the classification accuracy, but also remain the details in the image. [ABSTRACT FROM AUTHOR]

Abstract In this paper, a fast unsupervised deep fusion framework for change detection of multitemporal synthetic aperture radar (SAR) images is presented. It mainly aim at generating a difference image (DI) in the feature learning procedure by stacked auto-encoders (SAEs). Stacked auto-encoders, as one kind of deep neural network, can learn feature maps that retain the structural information but suppress the noise in the SAR images, which will be beneficial for DI generation. Compared with shallow network, the proposed framework can extract more available features, and be favorable for getting better change results. Different with other common deep neural networks, our proposed method does not need labeled data to train the network. In addition, we find a subset of the entire samples that appropriately represent the whole dataset to speed up the training of the deep neural network without under-fitting. Moreover, we design a fusion network structure that can combine ratio operator based method to ensure that the representations of higher layers are better than that of the lower ones. To summarize, the main contribution of our work lies in using of deep fusion network for generation of DI in a fast and unsupervised way. Experiments on four real SAR images confirm that our network performs better than traditional ratio methods and convolutional neural network. [ABSTRACT FROM AUTHOR]

A novel deep learning method for face sketch synthesis is proposed in this work. It builds a lightweight neural network which contains two convolutional layers, a pooling layer and a multilayer perceptron convolutional layer to learn a mapping from face photos to sketches. Unlike conventional example-based methods which need to solve complex optimization problems, the proposed method only computes convolution and pooling operations, hence significantly improves the synthesis efficiency. Besides, due to the global feature extraction of the convolutional layer, it achieves more continuous and faithful facial contours. Experiments on three benchmark datasets demonstrate that compared with several state-of-the-arts, the proposed method achieves highly competitive numerical results and is more robust to illumination and expression variations. [ABSTRACT FROM AUTHOR]

In this paper, a new random subspace based ensemble sparse representation (RS_ESR) algorithm is proposed, where the random subspace is introduced into sparse representation model. For high-dimensional data, the random subspace method can not only reduce dimension of data but also make full use of effective information of data. It is not like traditional dimensionality reduction methods that may lose some information of original data. Additionally, a joint sparse representation model is emloyed to obtain the sparse representation of a sample set in the low dimensional random subspace. Then the sparse representations in multiple random subspaces are integrated as an ensemble sparse representation. Moreover, the obtained RS_ESR is applied in classical clustering and semi-supervised classification. The experimental results on different real-world data sets show the superiority of RS_ESR over traditional methods. [ABSTRACT FROM AUTHOR]

The multispectral (MS) and the panchromatic (PAN) images represent complementary and synergistic spatial spectral information, how to make optimal use of the advantages of them has become a hot research topic. This paper proposes a selectable Transformer and Gist CNN network (STGC-Net). It designs a subspace similar recombination module (SSR-Module) based on non-negative matrix factorization (NMF) and the self-attention mechanism for feature decomposition. This can alleviate the redundant information of multi-modal data and extract their own singular and common features. Considering that the MS and the PAN images exhibit different advantageous properties, a selectable self-attention spectral feature extraction module (S 3 FE-Module) and a multi-stream Gist spatial feature extraction module (MGSFE-Module) are proposed for the different singular features. The former can refine the Transformer's input and simultaneously characterize the sequence information between channels for the MS image. The latter introduces the positional relationship between local features while extracting spatial features for the PAN image, thereby improving the accuracy of scene classification. Experimental results indicate that the proposed method performs better than the other methods. The relevant code of this paper is provided at: https://github.com/ru-willow/ST-GC-Net. • A subspace similar recombination module is proposed. • The selectable self-attention spectral feature extraction module is designed. • The multi-stream Gist spatial feature extraction module is introduced. [ABSTRACT FROM AUTHOR]

Link prediction is a ubiquitous application in many fields which uses partially observed information to predict absence or presence of links between node pairs. The group evolving study provides reasonable explanations on the behaviors of nodes, relations between nodes and community formation in a network. Possible events in group evolution include continuing, growing, splitting, forming and so on. The changes discovered in networks are to some extent the result of these events. In this work, we present a group evolving-based characterization of node’s behavioral patterns, and via which we can estimate the probability they tend to interact. In general, the primary aim of this paper is to offer a minimal toy model to detect missing links based on evolution of groups and give a simpler explanation on the rationality of the model. We first introduce perturbations into networks to obtain stable cluster structures, and the stable clusters determine the stability of each node. Then fluctuations, another node behavior, are assumed by the participation of each node to its own belonging group. Finally, we demonstrate that such characteristics allow us to predict link existence and propose a model for link prediction which outperforms many classical methods with a decreasing computational time in large scales. Encouraging experimental results obtained on real networks show that our approach can effectively predict missing links in network, and even when nearly 40% of the edges are missing, it also retains stationary performance. [ABSTRACT FROM AUTHOR]

Complex network research has attracted lots of attention in both academic community and various application fields. Complex network clustering, as one of the key issues in complex network, explores the internal organization of the nodes in a complex network. The discrete particle swarm optimization strategy has been successfully proposed for network clustering, while the existing method works with weak robust. In this paper, we model the task of complex network clustering as a multi-objective optimization problem and solve the problem with the quantum mechanism based particle swarm optimization algorithm, which is a parallel algorithm. To our knowledge, this is the first attempt to apply the quantum mechanism based discrete particle swarm optimization algorithm into network clustering. In addition, the non-dominant sorting selection operation is employed for individual replacement. Consequently, a quantum-behaved discrete multi-objective particle swarm optimization algorithm is proposed for complex network clustering. The experimental results demonstrate that the proposed algorithm performs effectively and achieves competitive performance with the state-of-the-art approaches on the extension of Girvan and Newman benchmarks and real-world networks, especially on large-scale networks. [ABSTRACT FROM AUTHOR]

Recently sparse representation (SR) based clustering has attracted a growing interests in the field of image processing and pattern recognition. Since the SR technology has favorable category distinguishing ability, we introduce it into the fuzzy clustering in this paper, and propose a new clustering algorithm, called sparse learning based fuzzy c-means (SL_FCM). Firstly, to reduce the computation complexity of the SR based FCM method, most energy of discriminant feature obtained by solving a SR model is reserved and the remainder is discarded. By this way, some redundant information (i.e. the correlation among samples of different classes) in the discriminant feature can be also removed, which can improve the clustering quality. Furthermore, to further enhance the clustering performance, the position information of valid values in discriminant feature is also used to re-define the distance between sample and clustering center in SL_FCM. The weighted distance in SL_FCM can enhance the similarity of the samples from the same class and the difference of the samples of different classes, thus to improve the clustering result. In addition, as the dimension of stored discriminant feature of each sample is different, we use set operations to formulate the distance and cluster center in SL_FCM. The comparisons on several datasets and images demonstrate that SL_FCM performs better than other state-of-art methods with higher accuracy, while keeps low spatial and computational complexity, especially for the large scale dataset and image. [ABSTRACT FROM AUTHOR]

Discriminant analysis (DA) is a well-known dimensionality reduction tool in pattern classification. With enough efficient labeled samples, the optimal projections could be found by maximizing the between-class scatter variance meanwhile minimizing the within-class scatter variance. However, the acquisition of label information is difficult in practice. So, semi-supervised discriminant analysis has attracted much attention in recent years, where both few labeled samples and many unlabeled samples are utilized during learning process. Sparse graph learned by sparse representation contains local structure information about data and is widely employed in dimensionality reduction. In this paper, semi-supervised double sparse graphs (sDSG) based dimensionality reduction is proposed, which considers both the positive and negative structure relationship of data points by using double sparse graphs. Aiming to explore the discriminant information among unlabeled samples, joint k nearest neighbor selection strategy is proposed to select pseudo-labeled samples which contain some precise discriminant information. In the following procedures, the data subset consisting of labeled samples and pseudo-labeled samples are used instead of the original data. Based on two different criterions, two sDSG based discriminant analysis methods are designed and denoted by sDSG-dDA (distance-based DA) and sDSG-rDA (reconstruction-based DA), which also use different strategies to reduce the effect of pseudo-labels’ inaccuracy. Finally, the experimental results both on UCI datasets and hyperspectral images validate the effectiveness and advantage of the proposed methods compared with some classical dimensionality reduction methods. [ABSTRACT FROM AUTHOR]

Classification plays an important role in many fields of synthetic aperture radar (SAR) image understanding and interpretation. Many scholars have devoted to design features to characterize the content of SAR images. However, it is still a challenge to design discriminative and robust features for SAR image classification. Recently, the deep learning has attracted much attention and has been successfully applied in many fields of computer vision. In this paper, a novel feature learning approach that is called discriminant deep belief network (DisDBN) is proposed to learning high-level features for SAR image classification, in which the discriminant features are learned by combining ensemble learning with a deep belief network in an unsupervised manner. Firstly, some subsets of SAR image patches are selected and marked with pseudo-labels to train weak classifiers. Secondly, the specific SAR image patch is characterized by a set of projection vectors that are obtained by projecting the SAR image patch onto each weak decision space spanned by each weak classifier. Finally, the discriminant features are generated by feeding the projection vectors to a DBN for SAR image classification. Experimental results demonstrate that better classification performance can be achieved by the proposed approach than the other state-of-the-art approaches. [ABSTRACT FROM AUTHOR]

In this paper, a novel unsupervised saliency-guided synthetic aperture radar (SAR) image change detection method is proposed. Salient areas of an image always are discriminative and different from other areas, which make them easily noticed. The strong visual contrast of local areas makes saliency suitable to guide the change detection of SAR images, where exists a difference between the two images. By applying the saliency extraction on an initial difference map obtained via the log ratio operator, a saliency map can be obtained in which most of the changed areas are included and the false changed pixels raised by speckle noises are well neglected, simultaneously. Then, by thresholding the saliency map, most of the interest regions can be preserved and further used to extract regions from the initial SAR images to generate difference image. The principal component analysis (PCA) method is used to extract features from local patches to incorporate the spatial information and reduce the influence of isolated pixels. Finally, k -means clustering is employed to obtain the change map on the extracted features, which are clustered into two classes: changed areas and unchanged areas. Experimental results on five real and two simulated SAR image data sets have demonstrated the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

Inspired by the compressive sensing (CS) theory, a new classifier based on compressed dictionary and Least Squares Support Vector Machine (LS-SVM) is proposed to deal with large scale problems. The coefficients of support vectors can be recovered from a few measurements if LS-SVM is approximated to sparse structure. Using the known Cholesky decomposition, we approximate the given kernel matrix to represent the coefficients of support vectors sparsely by a low-rank matrix that we have used as a dictionary. The proposed measurement matrix being coupled with the dictionary forms a compressed dictionary that proves to satisfy the restricted isometry property (RIP). Our classifier has the quality of low storage and computational complexity, high degree of sparsity and information preservation. Experiments on benchmark data sets show that our classifier has positive performance. [ABSTRACT FROM AUTHOR]

Clustering learning and classification learning are two major tasks in pattern recognition. The traditional hybrid clustering and classification algorithms handle them in a sequential way rather than a simultaneous way. Fortunately, multiobjective optimization provides a way to solve this problem. In this paper, an algorithm that learns simultaneous clustering and classification adaptively via multiobjective evolutionary algorithm is proposed. The main idea of this paper is to optimize two objective functions which represent fuzzy cluster connectedness and classification error rate to achieve the goal of simultaneous learning. Firstly, we adopt a graph based representation scheme to encode so that it can generate a set of solutions with different number of clusters in a single run. Then the relationship between clustering and classification is built via the Bayesian theory during the optimization process. The quality of clustering and classification is measured by the objective functions and the feedback drawn from both aspects is used to guide the mutation. At last, a set of nondominated solutions are generated, from which the final Pareto optimal solution is selected by using Adjusted Rand Index. The results on synthetic datasets and real-life datasets demonstrate the rationality and effectiveness of the proposed algorithm. Furthermore, we apply the proposed algorithm to image segmentation including texture images and synthetic aperture radar images, the experimental results show the superiority of the proposed algorithm compared with other five algorithms. [ABSTRACT FROM AUTHOR]

It remains one of the most challenging tasks to distinguish different terrain materials from a single SAR image. With the increase of ground resolution, it allows us to model the SAR image directly by exploiting spatial structures and texture information that are extracted by several machine learning approaches. In this paper, a novel feature learning approach is proposed to capture discriminant features of high-resolution SAR images. In the first stage, a weighted discriminant filter bank is learned from some labeled SAR image patches to generate low-level features. Then, the locality constraint is introduced to produce the high-level features in both the encoding and the spatial pooling procedure. In this work, the superpixels are employed as the basic operational units instead of the pixels for terrain classification. With some learned domain patterns which are learned from all of the high-level features of each pixel, the superpixel is characterized by a hyper-feature. In the last stage, a linear-kernel support vector machine is utilized to classify all of these hyper-features which are generated for each superpixel. The experimental results show a better classification performance of the proposed approach than several available state-of-the-art approaches. [ABSTRACT FROM AUTHOR]

Deformable ConvNets achieve excellent performance due to learnable spatial sampling locations. However, the spatial support may deviate from the region of interest, according to observations of its behavior. More Deformable ConvNets reduce abnormal behavior mainly by relying on a modulation mechanism, but they do not identify the reason for the behavior. In this work, we find that the unusual behavior is caused by the interaction between offsets, and we present a novel method named Entire Deformable ConvNets for reducing its influence. This updated version helps the spatial support better focus on pertinent image content. In the new method, deformable convolution is replaced with a new module, namely, entire deformable convolution. The new module avoids mutual interference by changing the manner of offset allocation. Using this simple pattern, entire deformable convolution inherits all the advantages of deformable convolution and achieves better performance. Furthermore, this strategy is also applicable to More Deformable ConvNets. Similarly, Entire More Deformable ConvNets contain a new module called entire modulated deformable convolution. Extensive experiments on PASCAL VOC and MS COCO benchmarks show that our methods realize excellent improvement over the original versions. [ABSTRACT FROM AUTHOR]

Many works have been recently presented to extract efficient features for automatic target recognition of synthetic aperture radar (SAR) images. However, they are limited in the discriminative ability of similar targets and robustness to the remarkable speckle noises and background clutters existed in images. In this paper, we propose a Complementary Spatial Pyramid Coding (CSPC) approach in the framework of Spatial Pyramid Matching (SPM). Both the coding coefficients and coding residuals are explored to develop more discriminative and robust features for representing SAR images. Multiple codebooks are first built from some training example images, where each codebook is formulated by local features of a certain class of samples. Then multiple sparse coding models are developed to derive features of a target under these codebooks. Additionally, these coding residuals are further sparsely encoded in the same way to that of local features. Finally, the encoded local features and the residual features are pooled according to spatial pyramid respectively, then concatenated to form the complementary features for the subsequent classification. The experiments on Moving and Stationary Target Acquisition and Recognition (MSTAR) public database verify the superior performance of the proposed method to some related approaches. [ABSTRACT FROM AUTHOR]

The application of quantum-behaved particle swarm optimization to multiobjective problems has attracted more and more attention recently. However, in order to extend quantum-behaved particle swarm optimization to multiobjective context, two major problems, namely the selection of personal and global best positions and the maintenance of population diversity, need to be taken into consideration. In this paper, a novel Cultural MOQPSO algorithm is proposed, in which cultural evolution mechanism is introduced into quantum-behaved particle swarm optimization to deal with multiobjective problems. In Cultural MOQPSO, the exemplar positions of each particle are obtained according to “belief space,” which contains different types of knowledge. Moreover, to increase population diversity and obtain continuous and even-distributed Pareto fronts, a combination-based update operator is proposed to update the external population in this paper. A comprehensive comparison of Cultural MOQPSO with some state-of-the-art evolutionary algorithms on several benchmark test functions, including ZDT, DTLZ and CEC2009 test instances, demonstrates the effectiveness of the proposed algorithm. [ABSTRACT FROM AUTHOR]

The link prediction algorithm which based on node similarity is the research hotspot in recent years. In addition, there are some methods which based on the network community structure information to predict the missing links, however, these studies only concerned about the obvious information between different communities such as direct links. We found that it is hard to predict the missing links if the two communities have little direct connections. In fact, there is similarity between communities such as the similarity between nodes and this similarity is significant for prediction. So, we define a community similarity feature which named community relevance by using not only the obvious information but also the latent information between different communities in this paper. Then a novel algorithm which based on the community relevance and ruler inference is proposed to predict missing links. In this method, we extract the community structure by using the local information of the network first. Next, calculate the relevance of each pair of communities by using the new community relevance indices. Finally, a simple prediction model which based on ruler inference is applied to estimate the probability of the missing links. It is shown that the proposed method has more effective prediction accuracy and the community relevance features improve the predictor with low time complexity, with experiments on benchmark networks and real-world networks in different scales, and compared with other ten sate of the art approaches. [ABSTRACT FROM AUTHOR]

Unsupervised feature selection plays an important role in hyperspectral image processing. It is a very challenge issue to select an effective feature subset with the unavailability of class labels. To select the features maximally preserving the information of original features, a maximum joint mutual information (MJMI) criterion is defined. Since the high-order distribution involved in MJMI is hard to calculate, a maximum information and minimum redundancy (MIMR) criterion is derived as the low-order approximation of MJMI. From information theory, many classical unsupervised feature selection criteria can also be considered as the low-order approximations of MJMI. Compared with them, MIMR requires more relaxed approximation condition. Moreover, a new clonal selection algorithm (CSA) in artificial immune system is devised to optimize the selected features with the guidance of MIMR. Experimental results on several hyperspectral datasets demonstrate that the proposed method obtains better feature subsets compared with classical unsupervised feature selection methods. [ABSTRACT FROM AUTHOR]

In the area of pattern recognition, Low Rank Representation (LRR) is an efficient method in recovering the subspace structure of the dataset. However, LRR is unsupervised. Without any label information, LRR constructs an informative graph which is then combined with the mature graph-based semi-supervised learning (GSSL) framework to complete the classification task. In this paper, we propose a new low rank learning method which constructs the low rank representation matrix utilizing label information to obtain a more informative graph. This method integrates the low rank graph construction and the label information propagation processes together. Thus the optimization of the low rank representation and the soft label prediction function are calculated iteratively at the same time. We name this method as Semi-Supervised Low Rank Learning (SSLRL). It enhanced the classification performance of traditional LRR-Graph based SSL by 5–30% and the running time is reduced from hundreds to less than ten seconds. Based on this method, a new outlier detection strategy is presented. This strategy succeeds with an AUC of at least 93% even if the detection condition of LRR is not satisfied. The effectiveness of SSLRL is demonstrated in semi-supervised classification, outlier detection, and salient detection tasks. These extensive experimental results highlight the outperforming of our method over state-of-the-art methods. [ABSTRACT FROM AUTHOR]

In this paper, we investigate the resource scheduling assignment problem in cellular mobile networks by considering both the inter-cell interference and intra-cell interference simultaneously. The task of this problem is to find the minimum required bandwidth to satisfy channel demand from each cell without interference constraints violation. Different from existing works, a novel two-phase hyper-heuristic technique which integrates harmony search and a set of prior information based heuristics is proposed to solve it. We validate performance of our approach by integrating a local search procedure in the later iterations. The proposed algorithm is tested on a set of benchmark problems, and the results are compared with the best state-of-the-art approaches. The results show that the method proposed in this article works effectively on the benchmark problems and has better performance on most problems than the algorithms that are investigated. [ABSTRACT FROM AUTHOR]

Ensemble learning has been a hot topic in machine learning due to its successful utilization in many applications. Rough set theory has been proved to be an excellent mathematical tool for dimension reduction. In this paper, based on rough set, a novel framework for ensemble is proposed. In our proposed framework, the relationship among attributes in rough subspace is first considered, and the maximum dependency degree of attribute is first employed to effectively reduce the searching space of reducts and augment the diversity of selected reducts. In addition, in order to choose an appropriate reduct from the dynamic reduct searching space, an assessment function which can balance the accuracy and diversity is utilized. At last, a new method, i.e., Dynamic Rough Subspace based Selective Ensemble (DRSSE), which is derived from our framework is given. By repeatedly changing the searching space of reducts and selecting the next reduct from the changed searching space, DRSSE finally trains an ensemble system with these selected reducts. Compared with several available ensemble methods, experimental results with several datasets demonstrate that DRSSE can lead to a comparative or even better performance. [ABSTRACT FROM AUTHOR]

Diversity and accuracy are the two key factors that decide the ensemble generalization error. Constructing a good ensemble method by balancing these two factors is difficult, because increasing diversity is at the cost of reducing accuracy normally. In order to improve the performance of an ensemble while avoiding the difficulty derived of balancing diversity and accuracy, we propose a novel method that weights each classifier in the ensemble by maximizing three different quadratic forms. In this paper, the optimal weight of individual classifiers is obtained by minimizing the ensemble error, rather than analyzing diversity and accuracy. Since it is difficult to minimize the general form of the ensemble error directly, we approximate the error in an objective function subject to two constraints ( ∑ w i = 1 and − 1 < w i < 1 ). Particularly, we introduce an error term with a weight vector w 0 , and subtract this error with the quadratic form to obtain our approximated error. This subtraction makes minimizing the approximation form equivalent to maximizing the original quadratic form. Theoretical analysis finds that when the value of the quadratic form is maximized, the error of an ensemble system with the corresponding optimal weight w * will be smallest, especially compared with the ensemble with w 0 . Finally, we demonstrate improved classification performance from the experimental results of an artificial dataset, UCI datasets and PolSAR image data. [ABSTRACT FROM AUTHOR]

Spectral correlation between each band of multispectral (MS) image is an important characteristic. In this paper, a novel pan-sharpening method inspired by distributed compressed sensing (DCS) theory is presented, which considers the correlation characteristic among the MS bands as prior information in the restoration model. Two basic image formation models reflecting the relationships of the low-resolution multispectral (LRMS) image and the high-resolution panchromatic (HRP) image to the unknown high-resolution multispectral (HRMS) image are constructed. In order to exactly recover the HRMS image from the measurements, a joint sparsity model (JSM) is employed to solve the ill-posed inverse problem. The basic assumption of JSM is that each HRMS spectral band shares a sparse common component and a sparse innovation component. The choice of dictionaries that are used to sparsely represent the common and innovation components is very important. The common component can be sparsely coded by a dictionary, which is learned from the source HRP image patches. Each innovation component can be sparsely represented by a hybrid dictionary, which is composed of discrete cosine transform (DCT) bases, Gabor bases, wavelet ‘db1’ bases, ridgelet bases and the learned dictionary atoms. By solving the l 1 -norm optimization problem, the unknown HRMS image can be estimated. The proposed method and the state-of-the-art methods are performed on simulated and real remote sensing images. Experimental results demonstrate that the proposed pan-sharpening method shows better performance than other well-known methods in terms of quantitative assessment and visual analysis. [ABSTRACT FROM AUTHOR]

In this paper, a patch based change detection method for polarimetric synthetic aperture radar (PolSAR) data is proposed. Because of the inherent speckle interference in SAR system, a despeckling procedure is important for change detection. However, the residual speckle still exists in the filtered data and is unevenly distributed, which is not considered in the available change detectors. Besides that, the detection methods with despeckling procedure cannot be adjusted based on the constant false alarm rate (CFAR). Specifically, the available PolSAR change detection methods are inefficient for the strong speckle interference cases due to the absence of the despeckling procedure. In order to overcome these drawbacks, an improved change detection framework for PolSAR data is proposed in this paper. The main innovations in the new framework include: (1) a despeckling procedure is added for PolSAR change detection, which makes the algorithm robust to strong noise; (2) a new equivalent number of looks (ENL) estimator is proposed for the PolSAR/SAR data filtered by non-local means filter; (3) the proposed method which detects the changes based on the filtered data can be adjusted with different CFARs. The experiments on both synthetic and real PolSAR datasets have demonstrated that the effectiveness of the proposed patch based PolSAR change detector (PPCD). [ABSTRACT FROM AUTHOR]

The investigation of link prediction in networks is an important issue in many disciplines. The research of prediction algorithms which required short time but high accuracy is still a challenging task. Most of the existing algorithms are based on the topological information of the networks, including the local or global similarity indices. It is found that the hierarchical organization and community structure information may indeed provide insights for link prediction. In this paper, we propose a simple link prediction method, which fully explore the community structure information of the networks. Firstly, the community structure of the networks under different resolutions is extracted. Then, a simple frequency statistical model is applied to calculate how many times that a pair of nodes divided into the same community under different resolutions. Finally, the probability of the missing links is calculated. The performance of our algorithm is demonstrated by comparing with other seven well-known methods on two kinds of networks in different scales. The results indicate that our approach not only has a good performance on the accuracy, but also has a lower time complexity than any other algorithms which are based on hierarchical structure of the network. [ABSTRACT FROM AUTHOR]

Highlights: [•] Pan-sharpening is the fusion of multispectral image and panchromatic image. [•] We model pan-sharpening into an image restoration problem. [•] Sparsity and local autoregressive model regularizations are used in the method. [•] Two dictionaries are constructed using the K-SVD algorithm. [•] Experiments prove the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

Abstract: Low rank representation is capable of capturing the global structure of mixed subspaces which are usually assumed to be independent. However, its computation is time-consuming. In practice, the data always distributes on subspaces that intersect or even overlap with each other. So the local structure of the data among the overlapping parts is important. Sparsity is a good property to accelerate the algorithm and capture the local linear structure. The drawback is that it breakups the low rank property of the reconstruction coefficient matrix when combining with low rank representation. In order to combine the two advantages properly, in this paper, we introduce a new constraint to the low rank representation matrix, which is called sparse congruency. Fortunately, we find that this new constraint is a simplification to the low rank and sparse constraints. Several experiments are implemented to demonstrate the efficiency of our method in semi-supervised classification. [Copyright &y& Elsevier]

Abstract: A hybrid memetic algorithm, called a memetic algorithm with double mutation operators (MADM), is proposed to deal with the problem of global optimization. In this paper, the algorithm combines two meta-learning systems to improve the ability of global and local exploration. The double mutation operators in our algorithms guide the local learning operator to search the global optimum; meanwhile the main aim is to use the favorable information of each individual to reinforce the exploitation with the help of two meta-learning systems. Crossover operator and elitism selection operator are incorporated into MADM to further enhance the ability of global exploration. In the first part of the experiments, six benchmark problems and six CEC2005׳s problems are used to test the performance of MADM. For the most problems, the experimental results demonstrate that MADM is more effective and efficient than other improved evolutionary algorithms for numerical optimization problems. In the second part of the experiments, MADM is applied to a practical problem, clustering complex and linearly non-separable datasets, with a satisfying result. [Copyright &y& Elsevier]

Abstract: This paper proposes a new feature descriptor, edge orientation difference histogram (EODH) descriptor, which is a rotation-invariant and scale-invariant feature representation. The main orientation of each edge pixel is obtained through steerable filter and vector sum. Based on the main orientation, we construct the EODH descriptor for each edge pixel. Finally, we integrate the EODH and Color-SIFT descriptor, and build an effective image retrieval system based on weighted codeword distribution using the integrated feature descriptor. Experiments show that the codebook-based image retrieval method achieves the best performance on the given benchmark problems comparing to the state-of-the-art methods. [Copyright &y& Elsevier]

Abstract: Multiple Kernel Learning (MKL) aims to seek a better result than single kernel learning by combining a compact set of sub-kernels. However, MKL with L1-norm easily discards the sub-kernels with complementary information and MKL with often gets the redundant solution. To address these problems, a Selective Multiple Kernel Learning (SMKL) method, inspired by Ensemble Learning (EL), is proposed. Comparing MKL with , SMKL obtains a sparse solution by a pre-selection procedure. Comparing MKL with L1-norm, SMKL preserves the sub-kernels with complementary information by guaranteeing the high discrimination and large diversity of pre-selected sub-kernels. For quantifying the discrimination and diversity of sub-kernels, a new kernel evaluation is designed. SMKL reduces the scale of MKL optimization and saves the memory storing of the sub-kernels, which extends the scale of problem that MKL could solve. Specially, a fast SMKL method using constraint is focused, which needs no MKL optimization process. It means that the memory is hardly a limitation for MKL with the large scale problem. Experiments state that our method is effective for classification. [Copyright &y& Elsevier]

We present an Augmentative Contrastive Learning for One-Shot Object Detection method that is inspired by the co-attention and co-excitation (CoAE) method. In the One-shot Object Detection (OSOD) task, the target image contains rich background information that influences the outcomes of different categories of objects more significantly. As a result, the network frequently suggests objects that do not fall under this category, leading to false detections. To learn the similarity between the target object and the query patch, we built the data augmentation module of object switch by similarity, encourage and restrain module. It primarily consists of the following three components: 1) To improve the contrast between the foreground and background, we propose an object switch module based on data augmentation and feature similarity; 2) To decrease the likelihood of false detections, we propose an encourage and restrain module that allows the network to encourage the recommendation of similar objects while restricting the recommendation of different categories of objects; and 3) To increase classification results, we use the nonlinear projector. We perform tests on the PASCAL VOC and MS COCO datasets to confirm the efficacy of our technique. [ABSTRACT FROM AUTHOR]

Abstract: Image compression based on block-based Discrete Cosine Transform (BDCT) inevitably produces annoying blocking artifacts because each block is transformed and quantized independently. This paper proposes a new deblocking method for BDCT compressed images based on sparse representation. To remove blocking artifacts, we obtain a general dictionary from a set of training images using the K-singular value decomposition (K-SVD) algorithm, which can effectively describe the content of an image. Then, an error threshold for orthogonal matching pursuit (OMP) is automatically estimated to use the dictionary for image deblocking by the compression factor of compressed image. Consequently, blocking artifacts are significantly reduced by the obtained dictionary and the estimated error threshold. Experimental results indicate that the proposed method is very effective in dealing with the image deblocking problem from compressed images. [Copyright &y& Elsevier]

Abstract: The Kuramoto model is modified by introducing a negative coupling strength, which is a generalization of the original one. Among the abundant dynamics, the clustering phenomenon of the modified Kuramoto model is analyzed in detail. After clustering appears in a network of coupled oscillators, the nodes are split into several clusters by their phases, in which the phases difference within each cluster is less than a threshold and larger than a threshold between different clusters. We show that this interesting phenomenon can be applied to identify the complete sub-graphs and further applied to graph coloring problems. Simulations on test beds of graph coloring problems have illustrated and verified the scheme. [Copyright &y& Elsevier]

Abstract: Generalized fuzzy c-means clustering algorithm with improved fuzzy partitions (GIFP_FCM) is a novel fuzzy clustering algorithm. However when GIFP_FCM is applied to image segmentation, it is sensitive to noise in the image because of ignoring the spatial information contained in the pixels. In order to solve this problem, a novel fuzzy clustering algorithm with non local adaptive spatial constraint (FCA_NLASC) is proposed in this paper. In the proposed method, a novel non local adaptive spatial constraint term is introduced to modify the objective function of GIFP_FCM. The characteristic of this technique is that the adaptive spatial parameter for each pixel is designed to make the non local spatial information of each pixel playing a different role in guiding the noisy image segmentation. Segmentation experiments on synthetic and real images, especially magnetic resonance (MR) images, are performed to assess the performance of an FCA_NLASC in comparison with GIFP_FCM and fuzzy c-means clustering algorithms with local spatial constraint. Experimental results show that the proposed method is robust to noise in the image and more effective than the comparative algorithms. [ABSTRACT FROM AUTHOR]

Abstract: In this paper, a reversible integer to integer time domain lapped transform (RTDLT) is introduced. TDLT can be taken as a combination of time domain pre- and post-filter modules with discrete cosine transform (DCT). Different from TDLT, the filters and DCT in our proposed RTDLT are realized from integer to integer by multi-lifting implementations after factorizing the filtering and transforming matrixes into triangular elementary reversible matrices (TERMs). Lifting implementations are realized by only shift and addition without any floating-point multiplier to reduce complexity. The proposed method can realize progressive lossy-to-lossless image compression with a single bit-stream. Simulation results show that RTDLT-based compression system obtains comparable or even higher compression-ratio in lossless compression than that of JPEG2000 and JPEG-LS, as well as gratifying rate distortion performance in lossy compression. Besides, RTDLT keeps low-complexity in hardware realization because it can be parallel implemented on the block level. [ABSTRACT FROM AUTHOR]

Abstract: We study projective (anticipatory, exact and lag) synchronization of time-delayed chaotic systems in a driven–response complex network (DRCN), where the nodes are not partially linear and the scale factors are different from each other. Two synchronization criteria are presented; the first is easy to satisfy with simple limitation and the second relaxes the previous limitation and can be executed only by adding a simple linear feedback control to every node. As a special case, projective synchronization in a DRCN without time delay is analyzed by using a different method. The corresponding synchronization criterion is given, which can be realized by adopting single-node adaptive control. This paper extends previous work, where the nodes of the DRCN are partially linear, there is limitation of the coupling matrix or the scale factors of the nodes are all equal. Numerical examples are given to demonstrate the effectiveness of the proposed synchronization criteria. Due to the complexity of the different scale factors, we select the chaotic data from the DRCN presented in this paper and apply the data selected in image encryption. Simulation results show that our method is efficient with a large key space, high sensitivity to initial conditions and high speed. [Copyright &y& Elsevier]

Abstract: Ng–Jordan–Weiss (NJW) method is one of the most widely used spectral clustering algorithms. For a K clustering problem, this method partitions data using the largest K eigenvectors of the normalized affinity matrix derived from the dataset. It has been demonstrated that the spectral relaxation solution of K-way grouping is located on the subspace of the largest K eigenvectors. However, we find from a lot of experiments that the top K eigenvectors cannot always detect the structure of the data for real pattern recognition problems. So it is necessary to select eigenvectors for spectral clustering. We propose an eigenvector selection method based on entropy ranking for spectral clustering (ESBER). In this method, first all the eigenvectors are ranked according to their importance on clustering, and then a suitable eigenvector combination is obtained from the ranking list. In this paper, we propose two strategies to select eigenvectors in the ranking list of eigenvectors. One is directly adopting the first K eigenvectors in the ranking list. Different to the largest K eigenvectors of NJW method, these K eigenvectors are the most important eigenvectors among all the eigenvectors. The other eigenvector selection strategy is to search a suitable eigenvector combination among the first Km (Km>K) eigenvectors in the ranking list. The eigenvector combination obtained by this strategy can reflect the structure of the original data and lead to a satisfying spectral clustering result. Furthermore, we also present computational complexity reduction strategies for ESBER method to deal with large-scale datasets. We have performed experiments on UCI benchmark datasets, MNIST handwritten digits datasets, and Brodatz texture datasets, adopting NJW method for a baseline comparison. The experimental results show that ESBER method is more robust than NJW method. Especially, ESBER method with the latter eigenvector selection strategy can obtain satisfying clustering results in most cases. [Copyright &y& Elsevier]

Abstract: This paper presents two embedded feature selection algorithms for linear-chain CRFs named GFSA_LCRF and PGFSA_LCRF. GFSA_LCRF iteratively selects a feature incorporating which into the CRF will improve the conditional log-likelihood of the CRF most at one time. For time efficiency, only the weight of the new feature is optimized to maximize the log-likelihood instead of all weights of features in the CRF. The process is iterated until incorporating new features into the CRF can not improve the log-likelihood of the CRF noticeably. PGFSA_LCRF adopts pseudo-likelihood as evaluation criterion to iteratively select features to improve the speed of GFSA_LCRF. Furthermore, it scans all candidate features and forms a small feature set containing some promising features at certain iterations. Then, the small feature set will be used by subsequent iterations to further improve the speed. Experiments on two real-world problems show that CRFs with significantly fewer features selected by our algorithms achieve competitive performance while obtaining significantly shorter testing time. [Copyright &y& Elsevier]

Abstract: The investigation of community structures is one of the most important problems in the field of complex networks and has countless applications in different disciplines: biology, computer, social sciences, etc. Many community detection algorithms have been developed in various fields recently. The vast majority of these algorithms only find disjoint communities; however, in many real-world networks communities often overlap to some extent. In this paper, we propose an efficient method for adjusting these classical algorithms to match the requirement for discovering overlapping communities in complex networks, which is based on a local definition of community strength. The method can in principle be applied with any clustering algorithm. Tests on a set of computer generated and real-world networks give excellent results. In particular, we show that the method can also allow one to availably analyze the problem of unstable nodes in community detection, which is very helpful for understanding the structural properties of the networks correctly and comprehensively. [Copyright &y& Elsevier]

Abstract: The quantum-inspired immune clonal algorithm (QICA) is a rising intelligence algorithm. Based on evolutionary game theory and QICA, a quantum-inspired immune algorithm embedded with evolutionary game (EGQICA) is proposed to solve combination optimization problems. In this paper, we map the quantum antibody’s finding the optimal solution to player’s pursuing maximum utility by choosing strategies in evolutionary games. Replicator dynamics is used to model the behavior of the quantum antibody and the memory mechanism is also introduced in this work. Experimental results indicate that the proposed approach maintains a good diversity and achieves superior performance. [Copyright &y& Elsevier]

Abstract: A novel analytic approach is presented to study the population of excitatory and inhibitory spiking neurons in this paper. The evolution in time of the population dynamic equation is determined by a partial differential equation. A new function is proposed to characterize the population of excitatory and inhibitory spiking neurons, which is different from the population density function discussed by most researchers. And a novel evolution equation, which is a nonhomogeneous parabolic type equation, is derived. From this, the stationary solution and the firing rate of the stationary states are given. Last, by the Fourier transform, the time dependent solution is also obtained. This method can be used to analyze the various dynamic behaviors of neuronal populations. [Copyright &y& Elsevier]

Abstract: A computational model, inspired by visual cortical mechanisms of contextual modulation, is presented in this paper, and is applied to detect perceptually salient contours. The presented model incorporates two mechanisms of contextual modulation, surround suppression and collinear facilitation. An oriented filterbank generated by Gaussian derivatives and their Hilbert transform is proposed for pre-processing. The operators of surround suppression and collinear facilitation are applied to the orientation energy resulting from the outputs of oriented filterbank. To avoid augmenting the noise when the facilitation operator enhances the saliency parts, we employ a contrast enhancement transformation for the facilitation operator. For drawing the binary contours, we present an automatic thresholding approach for post-processing. The performance of our model is tested by artificial images with heavy noise and nature images with texture background. Results show that the model has a good performance on extracting the salient contours from images. [Copyright &y& Elsevier]

Abstract: The biological immune system is a highly parallel and distributed adaptive system. The information processing abilities of the immune system provide important insights into the field of computation. Based on immunodominance in the biological immune system and the clonal selection mechanism, a novel data mining method, Immune Dominance Clonal Multiobjective Clustering algorithm (IDCMC), is presented. The algorithm divides an individual population into three sub-populations according to three different measurements, and adopts different evolution and selection strategies for each sub-population. The update of each sub-population, however, is not carried out in isolation. The periodic combination operation of the analysis of the three sub-populations represents considerable advantages in its global search ability. The clustering task is a multiobjective optimization problem, which is more robust with respect to the variety of cluster structures of different datasets than a single-objective clustering algorithm. In addition, the new algorithm can determine the number of clusters automatically, which should identify the most promising clustering solutions in the candidate set. The experimental results, using artificial datasets with different manifold structure and handwritten digit datasets, show that the IDCMC outperforms the PESA-II-based clustering method, the genetic algorithm-based clustering technique and the original K-Means algorithm in solving most of the problems tested. [Copyright &y& Elsevier]