Cross-scene hyperspectral image classification aims to enable the model to complete the classification of unlabeled target domain data by learning from labeled source domain data. Aiming at the problem that most current cross-scene hyperspectral image classification algorithms do not fully consider the cross-domain feature representation and category decision boundary optimization, a cross-domain Feature Extraction and Category Decision collaborative optimization (FECD) network is proposed. First, an adaptive feature discovery based on dynamic masks is designed. In this mechanism, the dynamically scaled masks are applied to the 3D representation of source and target domain data to generate an informative feature space and enhance the cross-scene discrimination potential of the model. Second, a dual-stream convolutional cross-domain feature extraction based on Mamba stream and ViT stream is constructed. Long sequence modeling and convolutional attention mechanisms are used to capture cross-domain spectral features between pixel, and self-attention mechanisms and multi-scale convolution are used to excavate cross-domain space patterns of pixel. Finally, a category decision based on the co-optimization of dual-stream classifiers is implemented. The spectral and spatial boundaries learned by the dual streams are fused to optimize the category decision. Therefore, the risk of false labeling is avoided while obtaining more accurate category boundaries. Compared with seven state-of-the-art algorithms on three widely used datasets, FECD obtains better categorization results on three categorization metrics: OA, AA, and Kappa.

In recent years, attention mechanisms have been widely used in many fields due to their excellent image focusing ability to produce more discriminative feature representations. However, in human pose estimation, methods based on attention mechanisms tend to have high computational overhead and are difficult to process video data in real time. In addition, existing algorithms do not make good use of the similarity between consecutive frames, and often repeat the computation many times on the same image. Therefore, this paper proposes a method based on a local attention mechanism and temporal prediction. The method first passes the input image through a body detector and then focuses attention on the head of the person, generating a large module of head information perception. This helps to find all the people in the image, avoiding missed detections, and this approach, which uses a local attention mechanism, has a small computational overhead. Then, to make the network layers closer to each other while keeping the parameters sparse, the features generated by the deep network will be reconstructed and compared with the input image. Finally, in order to reduce repetitive computation, the method determines the similarity between the preceding and following frames by means of multiple sampling points, which is used to determine whether the information from the previous frame is used to guide the localization of the nodes in the following frame. This allows the algorithm to remain real time when processing video. Experiments on the COCO and PoseData I datasets show that the algorithm outperforms all 10 comparison algorithms in terms of both accuracy and image continuity.

Evolutionary computation (EC)-based neural architecture search (NAS) has achieved remarkable performance in the automatic design of neural architectures. However, the high computational cost associated with evaluating searched architectures poses a challenge for these methods, and a fixed form of learning rate (LR) schedule means greater information loss on diverse searched architectures. This paper introduces an efficient EC-based NAS method to solve these problems via an innovative meta-learning framework. Specifically, a meta-learning-rate (Meta-LR) scheme is used through pretraining to obtain a suitable LR schedule, which guides the training process with lower information loss when evaluating each individual. An adaptive surrogate model is designed through an adaptive threshold to select the potential architectures in a few epochs and then evaluate the potential architectures with complete epochs. Additionally, a periodic mutation operator is proposed to increase the diversity of the population, which enhances the generalizability and robustness. Experiments on CIFAR-10, CIFAR-100, and ImageNet1K datasets demonstrate that the proposed method achieves high performance comparable to that of many state-of-the-art peer methods, with lower computational cost and greater robustness.

Markov Random Fields (MRF) effectively capture local contextual information by modeling the spatial dependencies between pixels, which helps highlight details and enhances segmentation smoothness. To fully exploit MRF for synthetic aperture radar (SAR) image segmentation, we propose a novel edge-enhanced cascaded MRF (ECMRF) approach. Specifically, we introduce multiple edge-constrained filters to emphasize SAR image boundaries and provide relatively clean features. Building on this, we present a cascaded MRF framework that sequentially integrates region-level and pixel-level segmentation with feature perturbation and fusion to generate the final segmentation output. The framework comprises four key components: (1) a region-level MRF, regulated by edge features, to achieve precise region segmentation; (2) a pixel-level MRF with selective label smoothing to refine edges and reduce noise clusters; (3) equal-channel feature perturbation to increase feature diversity; and (4) a random probability-based feature fusion scheme to merge the input features. Experimental results demonstrate that our ECMRF outperforms six state-of-the-art comparable methods, underscoring its competitive performance.

In satellite video object tracking, the individual frame analysis method is usually used for target localization, ignoring informative cues of the dynamic scene. Temporal information could contribute to identifying the target from distractors. In this work, a novel dynamic scene learning reasoning tracker is proposed for satellite videos, which reasons over temporal dynamic information to derive the target location. It is inspired by the tracking pattern through human perception and reasoning. First, static-dynamic united analysis is designed to construct dynamic scenes by concatenating the static searching results along the temporal dimension. Second, the information of each response object is aggregated by wavelet transforms. Meanwhile, these scenes are projected into low-frequency and high-frequency subspaces, which could imitate different levels of perceptions of humans for scenes. Third, an object-aware reasoning transformer is proposed to utilize the temporal dynamics of input response objects. In each subspace, it models the mutual interactions between dynamic objects and further learns the intrinsic property of each object for target reasoning. Finally, to obtain the current reasoning result, inverse wavelet transforms are utilized to integrate the results of low-frequency and high-frequency subspaces. The effectiveness of the proposed method is validated on three public satellite video datasets, including SV248S, SkySat, and VISO. Qualitative and quantitative experimental results show that the proposed tracker outperforms 22 popular approaches in seven challenging tracking satellite scenarios.

Multilabel feature selection solves the dimension distress of high-dimensional multilabel data by selecting the optimal subset of features. Noisy and incomplete labels of raw multilabel data hinder the acquisition of label-guided information. In existing approaches, mapping the label space to a low-dimensional latent space by semantic decomposition to mitigate label noise is considered an effective strategy. However, the decomposed latent label space contains redundant label information, which misleads the capture of potential label relevance. To eliminate the effect of redundant information on the extraction of latent label correlations, a novel method named SLOFS via shared latent sublabel structure and simultaneous orthogonal basis clustering for multilabel feature selection is proposed. First, a latent orthogonal base structure shared (LOBSS) term is engineered to guide the construction of a redundancy-free latent sublabel space via the separated latent clustering center structure. The LOBSS term simultaneously retains latent sublabel information and latent clustering center structure. Moreover, the structure and relevance information of nonredundant latent sublabels are fully explored. The introduction of graph regularization ensures structural consistency in the data space and latent sublabels, thus helping the feature selection process. SLOFS employs a dynamic sublabel graph to obtain a high-quality sublabel space and uses regularization to constrain label correlations on dynamic sublabel projections. Finally, an effective convergence provable optimization scheme is proposed to solve the SLOFS method. The experimental studies on the 18 datasets demonstrate that the presented method performs consistently better than previous feature selection methods.

The oriented target detection algorithm based on deep learning has made significant progress and has been widely applied in various fields, including remote sensing. However, existing methods still face challenges in large-sized targets and targets with similar backgrounds, leading to unsatisfactory detection performance in these scenarios. To address these issues, this paper proposes two modules on the basis of the feature pyramid: the Multi-Scale Feature Fusion Module and the Feature Compensation Module. The Multi-Scale Feature Fusion Module effectively integrates features from different levels, filters out noise introduced during the fusion process, and allows the network to focus more on target regions. The Feature Compensation Module provides semantic information compensation for the highest-level feature map, enhancing the feature representation capability. Extensive experiments were conducted on the DOTA and DIOR-R datasets. The experimental results demonstrate that the introduction of these two modules significantly improves the detection accuracy of the baseline algorithm.

Instance segmentation in the field of remote sensing imagery is recognized as a complex and difficult task. Previous approaches suffer from inadequate feature fusion, insufficient learning of shape information, and lack of segmentation of object edges. To address these challenges, we introduce FEA-Net(Fusion Edge-Aware Instance Segmentation Network), a multiple information fusion model for remote sensing image instance segmentation. Our model makes the predicted instance masks more accurate and can effectively improve the instance segmentation performance of high-resolution remote sensing images. We have evaluated our method on two datasets, NWPU VHR-10, and the iSAID. The experimental results demonstrate the effectiveness of our method, showing strong performance.

The visual question answering (VQA) method applied to remote sensing images (RSIs) can complete the interaction of image information and text information, which avoids professional barriers in different RSIs processing fields. The current methods face challenges in both fully utilizing the global and local information of the image to interact with the question information and addressing the issue of inter-class interference. To address these challenges, this paper proposes a remote sensing visual question answering (RSVQA) model based on the mask-based dual-stream feature mutual attention network (MADNet). First, the dual-stream feature extraction module of the image is used to obtain image features, and the deep and shallow layer feature encoding module is used to obtain question features. Second, the attention mechanism is introduced and combined with the pointwise multiplication method to utilize of the dual-stream features that were extracted in the earlier step. Finally, an answer relevance modulation module based on a binary mask vector is implemented to filter out irrelevant answers. In the experiments, the performance of the proposed strategy is evaluated using two datasets collected by aerial and Sentinel-2 sensors. In our study, we propose a model that outperforms previous approaches, achieving a 6.89% increase in overall accuracy (OA) over the baseline. This enhancement is notable for its persistence, even when the training data is reduced by half, as evidenced by our experiments on the low-resolution dataset.

Significant progress has been achieved in the development of oriented target detection algorithms based on deep learning, which have found widespread application in various fields, including remote sensing. However, existing methods struggle with adjusting model size and often exhibit unsatisfactory detection performance for targets that overlap, are large, or have similar backgrounds. To address these challenges, this letter proposes an oriented target detection algorithm called Oriented you only look once X (YOLOX), which integrates several optimization techniques. Specifically, to meet the requirements of oriented detection while enhancing feature extraction, we introduce a new network architecture that includes an orientation detection branch and a multiscale feature fusion module (MSFFM). An MSFFM based on attention weights is proposed to integrate features across scales while minimizing noise. In addition, to mitigate the impact of the number of positive samples on the original loss function and focus the network’s attention on learning challenging targets, an object-aware reweighted loss function is introduced in this study. This approach dynamically adjusts the loss contribution for each target. Two models of different sizes are developed using the Oriented YOLOX scaling strategy to cater to scenarios prioritizing either accuracy or speed. Extensive experiments on the dataset for object detection in aerial images (DOTA) and object detection in optical remote sensing images (DIOR-R) datasets demonstrate that Oriented YOLOX performs better in detecting challenging targets. Compared with other oriented target detection methods, this approach not only achieves higher detection accuracy but also reduces parameter counts, improving inference speed.

Surrounding contexts are generally perceived as interfering with object tracking in satellite videos, leading to model drift. From another perspective, they can also be seen as reference objects of the tracked target, the dynamic interactions between them could provide essential information. In this article, a high-order relation learning transformer (HRLT) is proposed for satellite video object tracking, which not only models the high-order interactions of different target-context pairs but also reasons the associations between these high-order relations across multiple frames. First, a spatial high-order relation reasoning (SHR2) module is designed to model the high-order interactions between the target and scene contexts. Second, a temporal high-order relation reasoning (THR2) module is proposed to associate and reason these spatial high-order relations across multiple frames. Third, historical high-order relations are collected to provide more reasoning bases for the current frame prediction. Finally, qualitative and quantitative evaluations are performed on the SV248S, SkySat, and VISO datasets. The results show that HRLT outperforms 20 popular methods in different challenging scenarios.

Tiny objects in satellite videos are usually not independent individuals, there exist rich semantic and temporal relations with each other. Thus, modeling and reasoning the variation of such intrinsic relationships can be beneficial for tiny object tracking. In this paper, a relation learning reasoning method is proposed for tiny object tracking in satellite videos. The core of the proposed is the relation reasoning network that consists of a key context module, a global semantic module, and a relation reasoning module sequentially. First, the key context module exploits global key contexts which explicitly or implicitly contribute to the target object, modeling the intrinsic relations with the target. Second, to reason the contribution, the global semantic module analyses the interaction between them in the same frame. Third, the relation reasoning module deduces the target based on the variation of the semantic relations among different frames. Such a relation learning reasoning approach which takes the target as the core is aligned with the satellite tiny object tracking task, significantly improves the identification performance in dense similarity scenes and the retrieval ability after completely occluded. Furthermore, the proposed method is shown to report improved qualitative and quantitative results on Jilin-1 and SkySat satellite video datasets.

The differentiable neural architecture search (NAS) framework has obtained extensive attention and achieved remarkable performance due to its search efficiency. However, most existing differentiable NAS methods still suffer from issues of model collapse, degenerated search-evaluation correlation, and inefficient hardware deployment, which causes the searched architectures to be suboptimal in accuracy and cannot meet different computation resource constraints (e.g., FLOPs and latency). In this article, we propose a novel resource-constrained NAS (ReCNAS) method, which can efficiently search high-performance architectures that satisfy the given constraints, and deal with the issues observed in previous differentiable NAS methods from three aspects: search space, search strategy, and resource adaptability. First, we introduce an elastic densely connected layerwise search space, which decouples the architecture depth representation from the search of candidate operations to alleviate the aggregation of skip connections and architecture redundancies. Second, a scheme of group annealing and progressive pruning is proposed to improve the efficiency and bridge the search-evaluation gap, which steadily forces the architecture parameters close to binary distribution and progressively prunes the inferior operations. Third, we present a novel resource-constrained architecture generation method, which prunes the redundant channel throughout the search based on dynamic programming, making the searched architecture scalable to different devices and requirements. Extensive experimental results demonstrate the efficiency and search stability of our ReCNAS, which is capable of discovering high-performance architectures on different datasets and tasks, surpassing other NAS methods, while tightly meeting the target resource constraints without any tuning required. Besides, the searched architectures show strong generalizability to other complex vision tasks.

Existing fusion-based local community detection algorithms have achieved good results. However, when assigning a node to a community, similarity functions are sometimes used, which only use node information, while ignoring connection information within the community. These algorithms sometimes fail to find influential nodes, which eventually leads to the failure to find a complete local community. To address these problems, a new local community detection algorithm is proposed in this article. Two strategies, of strong fusion followed by weak fusion, are used alternately to fuse nodes. Compared with using two fusion strategies alone, the alternating loop method can improve the solution of the algorithm in each stage. In strong fusion, we propose a new membership function that considers both node information and connection information in the local community. This improves the quality of the fused node while preserving the structure of the current community. In weak fusion, we propose a parameter-based similarity measure, which can detect influential nodes for a local community. We also propose a local community evaluation metric, which does not require true division to determine the optimal local community under different parameters. Experiments, compared to six state-of-the-art algorithms, show that the proposed algorithm improves accuracy and stability, and also demonstrate the effectiveness of the new local community evaluation metrics in parameter selection.

Recently, most convolutional neural network-based methods use convolutional kernels of fixed size to extract features, which ignore the inherent spatial structure information of ground objects and lose spatial details. In addition, rough first-order statistics is not enough to capture subtle differences between different categories and extract non local context information. To address these issues, a hyperspectral image (HSI) classification method based on multi-scale cross-branch response and second-order channel attention (MCRSCA) is proposed in this paper. Firstly, a multi-scale cross-branch response module (MCBR) is proposed, which uses convolution kernels of different sizes for feature extraction. It adds and concatenates the features of different scales respectively to obtain rich and complementary spatial context information. Then, element multiplication and element addition are performed on the fused multi-scale features to promote the propagation of the multi-scale information and enhance the nonlinear expression ability. Next, the second-order channel attention module (SOCA) is designed to interact the channel information through the feature covariance matrix to obtain the long-term dependence between channels. This module pays more attention to the significant channels and suppresses the redundant channels. Finally, the residual connection is used to embed MCBR and SOCA into the residual block to improve the gradient back propagation and accelerate the training process. Experiments on four commonly used HSI benchmark datasets show that the results of MCRSCA is competitive compared with other state-of-the-art methods.

This paper proposes a novel segmentation algorithm for synthetic aperture radar (SAR) images. The algorithm performs region-level segmentation based on edge feature and label assistance (REFLA). It demonstrates improved performance in terms of segmentation accuracy while better preserving image edges. Firstly, an edge detection scheme is implemented, which fuses information from two advanced edge detection methods, thereby obtaining a more precise edge strength map (ESM). Secondly, a Canny algorithm is performed to divide the SAR image into edge regions and homogeneous regions, and different smoothing templates are selected according to pixel positions. Therefore, an anisotropic smoothing on the SAR image can be achieved, aiming at suppressing the noise within targets while also accurately maintaining the target boundaries. Thirdly, K-means clustering is applied on the smoothed result, to generate an initial set of labels. Using ESM and the initial labels as inputs, a watershed transformation and a majority voting strategy are employed to realize an initial segmentation at the region level. Finally, a label-aided region merging (LaRM) strategy is used to correctly segment the wrongly labeled regions, to give the final segmentation result. The LaRM, with merging rules based on label rather than gray characteristics, can avoid the need for calculating a large number of complex formulae, thus accelerating the region merging. Results are presented of experiments, on both simulated and real SAR images, in which the proposed REFLA method is compared against six state-of-the-art algorithms from the literature. REFLA achieves higher accuracy, while better retaining the image edges.

Synthetic aperture radar (SAR) is widely used in the field of modern remote sensing due to its high resolution for a comparatively small antenna. However, there are still some difficulties in the processing of SAR images. In particular, accurate segmentation of small targets and image corners remains an important challenge, as these can easily be lost during conventional image smoothing and denoising methods. To address this, we propose an SAR image segmentation algorithm based on constrained smoothing and hierarchical label correction (CSHLC). First, a Canny algorithm is used to extract the edges of SAR images, and the Gaussian smoothing is performed on SAR images under edge constraints to achieve noise reduction so that the edges of small and big targets are well preserved. Second, a preliminary K-means clustering is conducted on the smoothing results, and then, a Markov random field (MRF) model is used on the clustering results (“original label” results), iteratively calculating a maximum likelihood set of pixel labels. Finally, through two label correction methods, pixel group counting comparison (PGCC) and gray similarity comparison (GSC), the labels of the MRF output are further checked and corrected to obtain final segmentation results. Compared with seven state-of-the-art algorithms, simulation results on both simulated SAR images and real SAR images show that the proposed CSHLC delivers higher accuracy while better retaining corners and small targets.

Nonlocal convolutional neural networks have difficulties in dealing with the imbalanced samples in hyperspectral images effectively, so the networks cannot achieve ideal experiment results. Therefore, this paper proposes an adaptive projection attention-based simplified nonlocal neural network for hyperspectral image classification. Firstly, the local information is calculated in horizontal and vertical directions. Then the information is passed to a simplified nonlocal network to learn the global semantic information. The simplified nonlocal network can reduce information redundancy and improve classification accuracy at the same time. Secondly, the global semantic information is adaptively projected according to the spatial features and compressed using multi-scale pooling layers. After that, the pooled results are reassigned channel weights through two fully connected layers and extended using multi-scale pooling layers. Then the extended features are concatenated with the global semantic information, which can alleviate the imbalanced sample existing in the dataset. Then a simplified nonlocal approach is used to fuse shallow and deep information to improve the robustness and classification performance of the network. In this paper, experiments of the proposed method are conducted on three widely used hyperspectral datasets compared with those of seven state-of-the-art algorithms, and satisfactory overall and average accuracies are achieved, demonstrating the effectiveness of the proposed algorithm.

Attention mechanism-based Hyperspectral Image (HSI) classification algorithms typically extract spectral and spatial features by spectral attention and spatial attention network respectively. However, these algorithms lack joint attention and ignore imbalanced samples, leading to insufficient information extraction. To address this problem, this paper proposes a novel HSI classification algorithm based on the pyramidal coordinate attention and weighted self-distillation (PCA-WSD). To perform the joint attention of spectral and spatial features, the proposed PCA mechanism uses spectral attention to cope with the diverse spatial features. The PCA mechanism consists of two components. First, the spatial pyramid coordinate squeeze (SPCS) is designed to aggregate spatial features with local and global information. Then, the tailored spatial pyramid coordinate excitation (SPCE) adaptively enhances their informative spectral features for the obtained spatial features, realizing the joint attention to spectral-spatial features. Further, considering the imbalance of samples, WSD is proposed. Specifically, weighted cross-entropy is integrated into WSD. Extensive experiments are evaluated on the four HSI benchmark datasets: Indian Pine (IP), Pavia University (UP), Kennedy Space Center (KSC), and Pavia Center (PC). Compared with the seven advanced algorithms, experimental results of the proposed algorithm1. reveal superior classification performance, especially for the imbalanced samples.

Recently, the study on learned iterative shrinkage thresholding algorithm (LISTA) has attracted increasing attentions. A large number of experiments as well as some theories have proved the high efficiency of LISTA for solving sparse coding problems. However, existing LISTA methods are all serial connection. To address this issue, we propose a novel extragradient based LISTA (ELISTA), which has a residual structure and theoretical guarantees. Moreover, most LISTA methods use the soft thresholding function, which has been found to cause a large estimation bias. Therefore, we propose a thresholding function for ELISTA instead of soft thresholding. From a theoretical perspective, we prove that our method attains linear convergence. Through ablation experiments, the improvements of our method on the network structure and the thresholding function are verified in practice. Extensive empirical results verify the advantages of our method.

As a critical step for Polarimetric Synthetic Aperture Radar (PolSAR) images interpretation, PolSAR classification have attracted growing interests in the field of remote sensing. Recently, many novel ideas and models based on deep learning have emerged to solve the task of PolSAR image classification. The encode-decode network structure of Fully Convolutional Network (FCN) is proved to be effective for this task. However, due to the inherent disadvantages of FCN and the complex high-dimensional feature representation of PolSAR images, there are still some issues need to be addressed. Aiming at the problem that the edge of adjacent regions is not enough finely classified and the regional consistency of the same object class is relatively weak, we propose a novel PolSAR image classification method called DBFCN, which combines a well-designed edge-aware network and the improved FCN. The experimental results verify that it can effectively improve the classification accuracy of PolSAR images.

Faster R-CNN has gained great result in SAR image object detection. But there are still hard samples affecting the final mean average precision (mAP). In this paper, we design an improved cross-entropy loss function with the attention of hard samples, and use it in Faster R-CNN. The obtained results on SAR OD data and SAR OD+ data illustrate our method can increase the precision of the exact hard samples efficiently, thus improving the total precision.

With the development of remote sensing satellite technology, the resolution of remote sensing images is constantly improved, but there are difficulties in obtaining labeled SAR image datasets for target detection and recognition. To address the problem that only limited SAR image target detection and recognition data are available, a novel data augmentation method based on convolutional neural network is proposed. Firstly, the Synthetic Aperture Radar (SAR) image target detection and recognition dataset SAR_OD was produced based on the synthesis of military targets and background images in MSTAR dataset. But considering the fact that the number of targets in each image in SAR_OD is still not enough for training a target detection model with good performance, we augmented SAR_OD and then we obtained SAR_OD+ dataset. It is proved that the model trained on SAR_OD+ dataset is significantly improved in the evaluation index by the data augmentation method proposed in this paper, especially in the experiments using only 50% of the training data. Therefore, the proposed data augmentation method can be used to improve the performance of SAR image target detection and recognition model in the case of limited labeled data.

As a fundamental but challenging task in the interpretation of remote sensing images, scene classification plays an important role in various applications and has become an active research topic. Many previous works have demonstrated the remarkable performance of the deep convolutional neural networks (CNNs) for remote sensing scene classification. However, the progress made by CNN-based methods for scene classification has gradually reached saturation in recent years, due to the serious dependence on the pretrained CNN models, the limitations of manually designed network architecture and the disadvantages of existing data sets. In this article, a new paradigm to automatically design a suitable CNN architecture for scene classification is investigated. We propose an efficient architecture search framework to discover optimal network architectures in continuous search space with the gradient-based optimization method. Our framework consists of two stages: the search phase and the evaluation phase. During the search process, a greedy and progressive search strategy is introduced to search network building blocks (i.e., cells) through bilevel optimization. Besides, we propose a simple architecture regularization scheme to further improve the search efficiency and the robustness of discovered architectures. After the search process, the optimal cell architectures are determined and then repeatedly stacked to construct the final network for evaluation. For the data set, we propose a mergence strategy to build a new large-scale remote sensing scene image data set that contains rich scene categories and image diversity, making it feasible to find a new CNN model with strong generalization ability for scene classification. Extensive experiments demonstrate the efficiency of the proposed search strategies and the impressive classification performance of searched CNN architectures on seven public benchmark data sets, including four large-scale data sets and three small-scale data sets.

Convolutional neural networks (CNN) are widely used and effective deep learning methods for image classification tasks. But the architecture of CNN such as LetNet and AlexNet were designed elaborately by experts because designing the neural networks is time-consuming and requires expert knowledge. This paper proposed a quantum-inspired evolutionary algorithm to search the neural architectures. First, we encode CNNs into quantum chromosomes and distinguish these chromosomes from the Convolutional Layer, Pooling Layer, Fully-connected Layer and Disabled Layer with its range. Second, quantum chromosomes are updated by applying quantum gates and find the best individual with quantum genetic algorithm. Third, we can predict the network performance after a few steps of stochastic gradient descent by means of evaluation estimate strategy so that we can stop training the bad networks early, which can speed up evolutionary process. The proposed algorithm is examined and compared with some state-of-art methods for image classification in three benchmark datasets. The experimental results prove the proposed algorithm can search a strong classifier robustly. In addition, it performs better than the general evolutionary algorithm. More importantly, with the help of evaluation estimate strategy, it is substantially faster than the algorithms without evaluation estimate strategy which means we can take less time to search a good network for the given task.

Stacked auto-encoder with weight decay (SAE-WD) and convolutional neural network (CNN) have great performances in PolSAR image classification. But the performances of them highly depend on proper hyperparameter configurations. In this paper, we apply a hyperparameter algorithm (called MARSAOP previously proposed by us) to automatically find good hyper-parameter configurations for them. The obtained results on two real PolSAR images suggest MARSAOP could still perform well on deep learning models and save manpower to tune the hyper-parameters.

Synthetic aperture radar (SAR) image despeckling is recognized as the basis for SAR image processing and interpretation. Over the past decades, many impressed speckle reduction methods have been developed and achieved good performance under certain circumstances. However, how to suppress speckle noise in a homogeneous region while more effectively protecting details and avoid distortion of data features caused by homomorphic transformation is still an urgent problem. In this paper, a novel speckle reduction algorithm based on generative adversarial network (GAN) is proposed, which contains a generator and a discriminator. For the generator that is used directly for subsequent noise reduction, a total variation (TV) loss function is added. Meanwhile, we directly learn the mapping between the input image and the ground truth rather than the logarithmic transformation. Indeed, the improved lightweight discriminative network will also provide learning guidance for the generator. Experiments on simulatedSAR images and real SAR images demonstrate the improvement in visual and statistical performance comparing to the state-of-the-art despeckling algorithms.

Machine learning techniques have achieved remarkable development in recent years. However, the performance of many machine learning models usually involves careful tuning of hyperparameters. The hyperparameter optimization (HPO) is usually a high-dimensional black box optimization problem and often faces expensive function evaluations. Besides, the task of HPO has gained great attention in academy and industry. In this paper, a novel method for hyperparameter optimization is proposed, referred to as surrogate model assisted quantum-inspired evolutionary algorithm (SA-QEA), which incorporates the principles of quantum-inspired evolutionary algorithm (QEA) and an efficient search framework based on a surrogate model. In the proposed algorithm, we adopt a single individual QEA with neighborhood exploration as the evolution scheme to generate the candidate solutions, and multivariate adaptive regression splines (MARS) is used as a surrogate to approximate the objective function around the individuals. Through conducting comprehensive experimental evaluations on two benchmark problems and three machine learning models, we test our proposed algorithm and compare it with other widely used methods. The results achieve competitive performance and demonstrate the effectiveness of SA-QEA for hyperparameter optimization.

In this paper, we analyze the performance of a novel deep feature fusion network when applied to the problem of remote sensing scene classification. So far, many classical convolutional neural network models have shown remarkable performance in image classification. With the availability of the latest high resolution remote sensing image data, traditions CNN models‘ performance has been considerably reduced. In order to tackle this condition, the deep convolutional neural networks are used in recent studies. Their classification accuracy depends on the depth of the network, while a deeper network will bring about higher computational complexity. In this work, we employ a deep feature fusion model for remote sensing scene classification, which uses the features extracted from Deep ResNet50 and VGG16 which are pre-trained and fine-tuned. The analysis of the experimental data prove the feasibility of the feature fusion network in remote sensing scene classification.

Polarimetric synthetic aperture radar (PolSAR) image classification plays an important role in remote sensing image processing. In recent years, stacked auto-encoder (SAE) has obtained a series of excellent results in PolSAR image classification. The recently proposed projective dictionary pair learning (DPL) model takes both accuracy and time consumption into consideration, and another recently proposed semicoupled dictionary learning (SCDL) model gives a new way to fit different features. Based on the SAE, DPL, and SCDL models, we propose a novel semicoupled projective DPL method with SAE (SAE-SDPL) for PolSAR image classification. Our method can get the classification result efficiently and correctly and meanwhile giving a new method to fit different features. In this paper, three PolSAR images are used to test the performance of SAE-SDPL. Compared with some state-of-the-art methods, our method obtains excellent results in PolSAR image classification.

With the rapid development of various technologies of satellite sensor, synthetic aperture radar (SAR) image has been an import source of data in the application of change detection. In this paper, a novel method based on a convolutional neural network (CNN) for SAR image change detection is proposed. The main idea of our method is to generate the classification results directly from the original two SAR images through a CNN without any preprocessing operations, which also eliminate the process of generating the difference image (DI), thus reducing the influence of the DI on the final classification result. In CNN, the spatial characteristics of the raw image can be extracted and captured by automatic learning and the results with stronger robustness can be obtained. The basic idea of the proposed method includes three steps: it first produces false labels through unsupervised spatial fuzzy clustering. Then we train the CNN through proper samples that are selected from the samples with false labels. Finally, the final detection results are obtained by the trained convolutional network. Although training the convolutional network is a supervised learning fashion, the whole process of the algorithm is an unsupervised process without priori knowledge. The theoretical analysis and experimental results demonstrate the validity, robustness, and potential of our algorithm in simulated and real data sets. In addition, we try to apply our algorithm to the change detection of heterogeneous images, which also achieves satisfactory results.

Change detection in synthetic aperture radar (SAR) images is to detect the changes happening during a period of time in the same area, which has important application research value. In this paper, we propose a novel method based on spatial fuzzy clustering (SFCM) and deep auto-encoder for the change-detection of SAR. In this method, the difference image (DI) is generated by the log-ratio operator. Then, the spatial fuzzy clustering (SFCM) algorithm is used to analyze the DI. The spatial fuzzy clustering (SFCM) algorithm adds spatial information to the fuzzy cluster, which effectively reduces the influence of speckle noise. Finally, we choose appropriate samples to train the deep auto-encoder. Real data and theoretical analysis show the effectiveness and robustness of the proposed method.

This paper presents an improved single-pass fuzzy c-means algorithm, which is referred to as Weighted Single-Pass Fuzzy c-Means Algorithm Based on Density Peaks (dpwSPFCM). The classical clustering methods can deal with the small-scale data problems rather than the large-scale data problems. In addition, the traditional single-pass fuzzy c-means algorithm is sensitive to the order of input data. In the proposed algorithm, the samples are weighted and reordered according to the density peaks of the data. The dpwSPFCM combines data segmentation and sample weighting technique based on density characteristics, which contributes to getting better clustering results. Experimental results on several UCI datasets have shown that dpwSPFCM has better performance than several well-known algorithms, i.e., FCM, online FCM(OFCM) and single-pass FCM(SPFCM).

In this paper, two multi-objective clustering ensemble algorithms are proposed named MOCLED and MOCNCD. MOCLED is different from MOCLE on three points. First, different clustering algorithms are used to produce some new individuals in evolutionary process. Second, a new screening mechanism is added. In each generation, the worst individual is replaced by the best individual. Third, a new objective function is added to ensure a diverse population. MOCNCD is the same as MOCLED except the crossover operator. We replace it with a new proposed cluster ensemble algorithm, IDICLENS. Experimental results reveal the advantages of our method on finding good partitions.

In this paper, we recommend a novel method based on log-mean operator and stacked auto-encoder which is used in the change detection for synthetic aperture radar images. The approach detects the changed and unchanged areas by designing a stacked Auto-encoder. The main guideline is to produce a difference image (DI) through the log-mean operator, and then distinguish the changed and unchanged regions with the trained stacked auto-encoder. The log-mean operator can roughly classify the changed and unchanged regions, but there also some inaccuracy in the difference image. Then, the stacked Auto-encoder can repair the different image further. Experimental results compared with other methods show that the method is effective.

Polarimetric synthetic aperture radar (PolSAR) image classification is a vital application in remote sensing image processing. In general, PolSAR image classification is actually a high-dimensional nonlinear mapping problem. The methods based on sparse representation and deep learning have shown a great potential for PolSAR image classification. Therefore, a novel PolSAR image classification method based on multilayer projective dictionary pair learning (MDPL) and sparse auto encoder (SAE) is proposed in this paper. First, MDPL is used to extract features, and the abstract degree of the extracted features is high. Second, in order to get the nonlinear relationship between elements of feature vectors in an adaptive way, SAE is also used in this paper. Three PolSAR images are used to test the effectiveness of our method. Compared with several state-of-the-art methods, our method achieves very competitive results in PolSAR image classification.

This paper presents a differential evolutionary clustering approach to solve the optimization of the dimension weights in subspace, which is referred to as Soft Subspace Clustering Using Differential Evolutionary Algorithm (DESSC). The classical clustering methods can handle the low-dimensional rather than the high-dimensional data due to the curse of dimensionality. In addition, many subspace clustering approaches are sensitive to the initial points, and the results converge to local rather than global optimum. In the proposed algorithm, a novel technique for cluster data is developed to update the dimension weights by using differential evolution. DESSC combines the merits of differential evolution and the advantages of Soft Subspace Clustering. This contributes to avoiding trapping in local optimum and gets a stable clustering result. Moreover, it is robust and easy to implement. Experimental results on both synthetic and real data have shown that DESSC significantly outperformed several well-known algorithms, i.e., ESSC, FWKM, EWKM and LAC in almost all experiments.

The original Artificial Immune Network (aiNet) clustering algorithm cannot get an ideal result when the boundaries of the dataset are not clear or the noise is present. In this paper, an improved Artificial Immune Network algorithm for data clustering based on Secondary competition (cs-aiNet) is proposed to solve this problem. The strategy named competition selection is introduced to select a node set that is able to reflect the structure of the dataset. No special prior knowledge is needed in the cs-aiNet clustering algorithm. Experiments show that the new method is competitive with regard to the original clustering algorithms.

This paper presents a novel method for hyperspectral classification combining multiple features and exploiting spatial information at the same time. We proposed a supervised classification method under the Markov random field (MRF)-based framework. Firstly using the probability SVM to map multiple features from different low-level subspace to the same semantic space (probability space), then integrating these features in semantic space with MRF-based model to enforce a smooth and accurate representation, in addition the manifold distance has been used in MRF-based model to measure the similarity of two point. To further improve the classification accuracy, a new approach of building the adaptive neighborhood has been proposed and used in our method. As our model is a derivable and convex problem, gradient descent can be used to solve this problem with less computational and time cost. Experimental results on real hyperspectral dataset shows that the proposed method provides improved classification accuracy in terms of the overall accuracy, average accuracy and kappa statistic.

Quantum-behaved particle swarm optimization (QPSO) algorithm simulates quantum mechanics among individuals. For improving the local search ability of QPSO and guiding the search, an improved QPSO algorithm based on combining the dynamic mutation and cooperative background (MCQPSO) is proposed in this paper. The dynamic Cauchy mutation strategy is introduced to enhance the global search ability. The cooperative background strategy is used to change the updating mode of the particles in order to guarantee the effectiveness and simplification. The MCQPSO algorithm keeps the diversity of the population, and increasing convergence rates. Results compared with some previous study show that the MCQPSO algorithm performs much better than the Sun Jun's Cooperative Quantum-Behaved Particle Swarm Optimization (sunCQPSO) and WQPSO algorithm in terms of the image segmentation accuracy and the computation efficiency.

This paper proposes a quantum immune clone algorithm to solve the constrained multi-objective optimization problem. Firstly, constraints deviation value is added to objective function value to form a new objective function value, which translates the constrained multi-objective optimization problem into an unconstrained multi-objective optimization problem. Secondly, it does not only retain the feasible non-dominated solutions, but also utilizes the non-feasible solutions which have small constraint deviation value and objective function value. The appearing of the non-feasible solutions expands the search scope and makes it easy to evolve solutions near the Pareto front. Then, a quantum rotating gate is designed to accelerate the computational speed. At last, crossover and mutation are used to obtain better individuals. Compared with the state-of-art algorithm, simulation results show that the proposed algorithm has a better improvement on GD distance and on the diversity.

Biclustering is of great significance in the analysis of gene expression data and is proven to be a NP-hard problem. Among the existing intelligent optimization algorithms used in the gene expression data analysis, most concentrate on the global search ability but ignore the inherent trajectory information of gene expression data, so the search efficiency is low. In this paper, a pattern-driven local search operator is incorporated in the binary Particle Swarm Optimization (PSO) algorithm in order to improve the search efficiency. Experiments show that our approach is valid.

Community detection is important in understanding the structures and functions of complex networks. Many algorithms have been proposed. The most popular algorithms detect the communities through optimizing a criterion function known as modularity, which suffer from the resolution limit problem. Some algorithms require the number of communities as a prior. In this paper, a non-modularity based compression optimization algorithm for community detection is proposed without any prior knowledge, which is efficient and is suitable for large scale networks.

There is an increasing recognition on community detection in complex networks in recent years. In this study, we improve a recently proposed memetic algorithm for community detection in networks. By introducing a Population Generation via Label Propagation (PGLP) tactic, an Elitism Strategy (ES) and an Improved Simulated Annealing Combined Local Search (ISACLS) strategy, the improved memetic algorithm called (iMeme-Net) is put forward for solving community detection problems. Experiments on both computer-generated and real-world networks show the effectiveness and the multi-resolution ability of the proposed method.

A number of studies has focused on the community detection in complex networks in recent years. Single-objective approaches which have only one optimization function (e.g., modularity or modularity density) may have weaknesses such as just a single community structure can be obtained or resolution limit. In this paper, a spectral clustering-based adaptive hybrid multi-objective harmony search algorithm (SCAH-MOHSA) combined with a local search strategy is proposed to detect the community structure in complex networks. At first, an improved spectral method is employed to convert the community detection problem into a data clustering issue while the length of the representation of a harmony in the harmony memory can be determined. Then, an adaptive hybrid multi-objective harmony search algorithm is used to solve the multi-objective optimization problem so as to resolve the community structure. The experiments on both synthetic and real world networks demonstrate our method achieves partition results which fit the real situation in an even better fashion.

In this paper, we present a cluster algorithm which is an improvement of the multi-objective clustering ensemble algorithm (MOCLE), which is denoted as IMOCLE for short. First, we introduce a new clustering objective function to measure the individual difference in the optimization process so as to remain the diversity of the population. Then, a clustering ensemble technique is applied to MOCLE to obtain more competitive individual. The proposed algorithm can also ensure good partitions not be eliminated. The performance of the proposed algorithm has been compared with MOCLE over a suit of gene datasets. The experimental results show that, the superiority of the proposed method in terms of capability found the optimum number of clusters, and accuracy.

In this paper, we proposed a new approach to solve the clustering problem in which the cluster number is uncertainty. It utilizes IWO (Invasive Weed Optimization) algorithm to optimize two fuzzy clustering objective function simultaneously, and a variable-length real-coded scheme has been adopted, the variable length weed encodes the cluster centers with variable numbers. In order to keep the diversity of the weeds, we introduce a new mechanism called feedback update mechanism to update the individuals which the corresponding number of cluster centers has been eliminated in one generation. Finally, the Silhouette index is used to select the best solution. The algorithm is used to cluster 15 artificial data sets and 4 real life data sets and shows good performance.

Based on the concepts and principles of quantum computing, a novel clustering algorithm, called a quantum-inspired immune clonal clustering algorithm based on watershed (QICW), is proposed to deal with the problem of image segmentation. In QICW, antibody is proliferated and divided into a set of subpopulation groups. Antibodies in a subpopulation group are represented by multi-state gene quantum bits. In the antibody's updating, the quantum mutation operator is applied to accelerate convergence. The quantum recombination realizes the information communication between the subpopulation groups so as to avoid premature convergences. In this paper, the segmentation problem is viewed as a combinatorial optimization problem, the original image is partitioned into small blocks by watershed algorithm, and the quantum-inspired immune clonal algorithm is used to search the optimal clustering centre, and make the sequence of maximum affinity function as clustering result, and finally obtain the segmentation result. Experimental results show that the proposed method is effective for texture image and SAR image segmentation, compared with the genetic clustering algorithm based on watershed (W-GAC), and the k-means algorithm based on watershed (W-KM).

As a global optimizing algorithm, genetic algorithm (GA) is applied to solve the problem of multicast more and more. GA has more powerful searching ability than traditional algorithm, however its property of “prematurity” makes it difficult to get a good multicast tree. A quantum-inspired evolutionary algorithm (QEA) to deal with multicast routing problem is presented in this paper, which saliently solves the “prematurity” problem in Genetic based multicast algorithm. Furthermore, in QEA, the individuals in a population are represented by multistate gene quantum bits and this representation has a better characteristic of generating diversity in population than any other representations. In the individual's updating, the quantum rotation gate strategy is applied to accelerate convergence. The algorithm has the property of simple realization and flexible control. The simulation results show that QEA has a better performance than CS and conventional GA.

Based on the clonal selection theory of the immune system, a novel optimal algorithm, called a directional immune clonal selection algorithm (DICSA), is proposed to design RF diplexer. In DICSA, antibody is proliferated and divided into a set of subpopulation groups. In the antibody's updating, the clonal mutation is applied to avoid premature convergences. The clonal selection realizes the information communication between the subpopulation groups so as to improve the search efficiency. DICSA is applied to a practical problem, designing RF diplexer. The results show that DICSA has stable performance during the optimization process with a satisfactory result.

Based on the concepts and principles of quantum computing, a novel immune clonal algorithm, called a quantum-inspired immune clonal algorithm (QICA), is proposed to deal with the problem of global optimization. In QICA, the antibody is proliferated and divided into a set of subpopulation groups. The antibodies in a subpopulation group are represented by multistate gene quantum bits. In the antibody's updating, the general quantum rotation gate strategy and the dynamic adjusting angle mechanism are applied to accelerate convergence. The quantum not gate is used to realize quantum mutation to avoid premature convergences. The proposed quantum recombination realizes the information communication between subpopulation groups to improve the search efficiency. Theoretical analysis proves that QICA converges to the global optimum. In the first part of the experiments, 10 unconstrained and 13 constrained benchmark functions are used to test the performance of QICA. The results show that QICA performs much better than the other improved genetic algorithms in terms of the quality of solution and computational cost. In the second part of the experiments, QICA is applied to a practical problem (i.e., multiuser detection in direct-sequence code-division multiple-access systems) with a satisfying result.