Lightweight Super-Resolution with Self-Calibrated Convolution for Panoramic Videos.

Panoramic videos are shot by an omnidirectional camera or a collection of cameras, and can display a view in every direction. They can provide viewers with an immersive feeling. The study of super-resolution of panoramic videos has attracted much attention, and many methods have been proposed, especially deep learning-based methods. However, due to complex architectures of all the methods, they always result in a large number of hyperparameters. To address this issue, we propose the first lightweight super-resolution method with self-calibrated convolution for panoramic videos. A new deformable convolution module is designed first, with self-calibration convolution, which can learn more accurate offset and enhance feature alignment. Moreover, we present a new residual dense block for feature reconstruction, which can significantly reduce the parameters while maintaining performance. The performance of the proposed method is compared to those of the state-of-the-art methods, and is verified on the MiG panoramic video dataset.

A Self-Adaptive Response Strategy for Dynamic Multiobjective Evolutionary Optimization Based on Objective Space Decomposition.

Dynamic multiobjective optimization deals with simultaneous optimization of multiple conflicting objectives that change over time. Several response strategies for dynamic optimization have been proposed, which do not work well for all types of environmental changes. In this article, we propose a new dynamic multiobjective evolutionary algorithm based on objective space decomposition, in which the maxi-min fitness function is adopted for selection and a self-adaptive response strategy integrating a number of different response strategies is designed to handle unknown environmental changes. The self-adaptive response strategy can adaptively select one of the strategies according to their contributions to the tracking performance in the previous environments. Experimental results indicate that the proposed algorithm is competitive and promising for solving different DMOPs in the presence of unknown environmental changes. Meanwhile, the proposed algorithm is applied to solve the parameter tuning problem of a proportional integral derivative (PID) controller of a dynamic system, obtaining better control effect.

A Decomposition-Based Evolutionary Algorithm with Correlative Selection Mechanism for Many-Objective Optimization.

Decomposition-based evolutionary algorithms have been quite successful in dealing with multiobjective optimization problems. Recently, more and more researchers attempt to apply the decomposition approach to solve many-objective optimization problems. A many-objective evolutionary algorithm based on decomposition with correlative selection mechanism (MOEA/D-CSM) is also proposed to solve many-objective optimization problems in this article. Since MOEA/D-SCM is based on a decomposition approach which adopts penalty boundary intersection (PBI), a set of reference points must be generated in advance. Thus, a new concept related to the set of reference points is introduced first, namely, the correlation between an individual and a reference point. Thereafter, a new selection mechanism based on the correlation is designed and called correlative selection mechanism. The correlative selection mechanism finds its correlative individuals for each reference point as soon as possible so that the diversity among population members is maintained. However, when a reference point has two or more correlative individuals, the worse correlative individuals may be removed from a population so that the solutions can be ensured to move toward the Pareto-optimal front. In a comprehensive experimental study, we apply MOEA/D-CSM to a number of many-objective test problems with 3 to 15 objectives and make a comparison with three state-of-the-art many-objective evolutionary algorithms, namely, NSGA-III, MOEA/D, and RVEA. Experimental results show that the proposed MOEA/D-CSM can produce competitive results on most of the problems considered in this study.

Stochastic Recursive Gradient Support Pursuit and Its Sparse Representation Applications.

In recent years, a series of matching pursuit and hard thresholding algorithms have been proposed to solve the sparse representation problem with ℓ0-norm constraint. In addition, some stochastic hard thresholding methods were also proposed, such as stochastic gradient hard thresholding (SG-HT) and stochastic variance reduced gradient hard thresholding (SVRGHT). However, each iteration of all the algorithms requires one hard thresholding operation, which leads to a high per-iteration complexity and slow convergence, especially for high-dimensional problems. To address this issue, we propose a new stochastic recursive gradient support pursuit (SRGSP) algorithm, in which only one hard thresholding operation is required in each outer-iteration. Thus, SRGSP has a significantly lower computational complexity than existing methods such as SG-HT and SVRGHT. Moreover, we also provide the convergence analysis of SRGSP, which shows that SRGSP attains a linear convergence rate. Our experimental results on large-scale synthetic and real-world datasets verify that SRGSP outperforms state-of-the-art related methods for tackling various sparse representation problems. Moreover, we conduct many experiments on two real-world sparse representation applications such as image denoising and face recognition, and all the results also validate that our SRGSP algorithm obtains much better performance than other sparse representation learning optimization methods in terms of PSNR and recognition rates.

Nonnegative Matrix Factorization with Rank Regularization and Hard Constraint.

Nonnegative matrix factorization (NMF) is well known to be an effective tool for dimensionality reduction in problems involving big data. For this reason, it frequently appears in many areas of scientific and engineering literature. This letter proposes a novel semisupervised NMF algorithm for overcoming a variety of problems associated with NMF algorithms, including poor use of prior information, negative impact on manifold structure of the sparse constraint, and inaccurate graph construction. Our proposed algorithm, nonnegative matrix factorization with rank regularization and hard constraint (NMFRC), incorporates label information into data representation as a hard constraint, which makes full use of prior information. NMFRC also measures pairwise similarity according to geodesic distance rather than Euclidean distance. This results in more accurate measurement of pairwise relationships, resulting in more effective manifold information. Furthermore, NMFRC adopts rank constraint instead of norm constraints for regularization to balance the sparseness and smoothness of data. In this way, the new data representation is more representative and has better interpretability. Experiments on real data sets suggest that NMFRC outperforms four other state-of-the-art algorithms in terms of clustering accuracy.

Hierarchical Sparse Learning with Spectral-Spatial Information for Hyperspectral Imagery Denoising.

During the acquisition process hyperspectral images (HSI) are inevitably corrupted by various noises, which greatly influence their visual impression and subsequent applications. In this paper, a novel Bayesian approach integrating hierarchical sparse learning and spectral-spatial information is proposed for HSI denoising. Based on the structure correlations, spectral bands with similar and continuous features are segmented into the same band-subset. To exploit local similarity, each subset is then divided into overlapping cubic patches. All patches can be regarded as consisting of clean image component, Gaussian noise component and sparse noise component. The first term is depicted by a linear combination of dictionary elements, where Gaussian process with Gamma distribution is applied to impose spatial consistency on dictionary. The last two terms are utilized to fully depict the noise characteristics. Furthermore, the sparseness of the model is adaptively manifested through Beta-Bernoulli process. Calculated by Gibbs sampler, the proposed model can directly predict the noise and dictionary without priori information of the degraded HSI. The experimental results on both synthetic and real HSI demonstrate that the proposed approach can better suppress the existing various noises and preserve the structure/spectral-spatial information than the compared state-of-art approaches.

Joint Prior Learning for Visual Sensor Network Noisy Image Super-Resolution.

The visual sensor network (VSN), a new type of wireless sensor network composed of low-cost wireless camera nodes, is being applied for numerous complex visual analyses in wild environments, such as visual surveillance, object recognition, etc. However, the captured images/videos are often low resolution with noise. Such visual data cannot be directly delivered to the advanced visual analysis. In this paper, we propose a joint-prior image super-resolution (JPISR) method using expectation maximization (EM) algorithm to improve VSN image quality. Unlike conventional methods that only focus on upscaling images, JPISR alternatively solves upscaling mapping and denoising in the E-step and M-step. To meet the requirement of the M-step, we introduce a novel non-local group-sparsity image filtering method to learn the explicit prior and induce the geometric duality between images to learn the implicit prior. The EM algorithm inherently combines the explicit prior and implicit prior by joint learning. Moreover, JPISR does not rely on large external datasets for training, which is much more practical in a VSN. Extensive experiments show that JPISR outperforms five state-of-the-art methods in terms of both PSNR, SSIM and visual perception.

A memetic optimization strategy based on dimension reduction in decision space.

There can be a complicated mapping relation between decision variables and objective functions in multi-objective optimization problems (MOPs). It is uncommon that decision variables influence objective functions equally. Decision variables act differently in different objective functions. Hence, often, the mapping relation is unbalanced, which causes some redundancy during the search in a decision space. In response to this scenario, we propose a novel memetic (multi-objective) optimization strategy based on dimension reduction in decision space (DRMOS). DRMOS firstly analyzes the mapping relation between decision variables and objective functions. Then, it reduces the dimension of the search space by dividing the decision space into several subspaces according to the obtained relation. Finally, it improves the population by the memetic local search strategies in these decision subspaces separately. Further, DRMOS has good portability to other multi-objective evolutionary algorithms (MOEAs); that is, it is easily compatible with existing MOEAs. In order to evaluate its performance, we embed DRMOS in several state of the art MOEAs to facilitate our experiments. The results show that DRMOS has the advantage in terms of convergence speed, diversity maintenance, and portability when solving MOPs with an unbalanced mapping relation between decision variables and objective functions.

A multipopulation coevolutionary strategy for multiobjective immune algorithm.

How to maintain the population diversity is an important issue in designing a multiobjective evolutionary algorithm. This paper presents an enhanced nondominated neighbor-based immune algorithm in which a multipopulation coevolutionary strategy is introduced for improving the population diversity. In the proposed algorithm, subpopulations evolve independently; thus the unique characteristics of each subpopulation can be effectively maintained, and the diversity of the entire population is effectively increased. Besides, the dynamic information of multiple subpopulations is obtained with the help of the designed cooperation operator which reflects a mutually beneficial relationship among subpopulations. Subpopulations gain the opportunity to exchange information, thereby expanding the search range of the entire population. Subpopulations make use of the reference experience from each other, thereby improving the efficiency of evolutionary search. Compared with several state-of-the-art multiobjective evolutionary algorithms on well-known and frequently used multiobjective and many-objective problems, the proposed algorithm achieves comparable results in terms of convergence, diversity metrics, and running time on most test problems.

A partition-based active contour model incorporating local information for image segmentation.

Active contour models are always designed on the assumption that images are approximated by regions with piecewise-constant intensities. This assumption, however, cannot be satisfied when describing intensity inhomogeneous images which frequently occur in real world images and induced considerable difficulties in image segmentation. A milder assumption that the image is statistically homogeneous within different local regions may better suit real world images. By taking local image information into consideration, an enhanced active contour model is proposed to overcome difficulties caused by intensity inhomogeneity. In addition, according to curve evolution theory, only the region near contour boundaries is supposed to be evolved in each iteration. We try to detect the regions near contour boundaries adaptively for satisfying the requirement of curve evolution theory. In the proposed method, pixels within a selected region near contour boundaries have the opportunity to be updated in each iteration, which enables the contour to be evolved gradually. Experimental results on synthetic and real world images demonstrate the advantages of the proposed model when dealing with intensity inhomogeneity images.

Decomposition-based multiobjective evolutionary algorithm for community detection in dynamic social networks.

Community structure is one of the most important properties in social networks. In dynamic networks, there are two conflicting criteria that need to be considered. One is the snapshot quality, which evaluates the quality of the community partitions at the current time step. The other is the temporal cost, which evaluates the difference between communities at different time steps. In this paper, we propose a decomposition-based multiobjective community detection algorithm to simultaneously optimize these two objectives to reveal community structure and its evolution in dynamic networks. It employs the framework of multiobjective evolutionary algorithm based on decomposition to simultaneously optimize the modularity and normalized mutual information, which quantitatively measure the quality of the community partitions and temporal cost, respectively. A local search strategy dealing with the problem-specific knowledge is incorporated to improve the effectiveness of the new algorithm. Experiments on computer-generated and real-world networks demonstrate that the proposed algorithm can not only find community structure and capture community evolution more accurately, but also be steadier than the two compared algorithms.

MOEA/D with adaptive weight adjustment.

Recently, MOEA/D (multi-objective evolutionary algorithm based on decomposition) has achieved great success in the field of evolutionary multi-objective optimization and has attracted a lot of attention. It decomposes a multi-objective optimization problem (MOP) into a set of scalar subproblems using uniformly distributed aggregation weight vectors and provides an excellent general algorithmic framework of evolutionary multi-objective optimization. Generally, the uniformity of weight vectors in MOEA/D can ensure the diversity of the Pareto optimal solutions, however, it cannot work as well when the target MOP has a complex Pareto front (PF; i.e., discontinuous PF or PF with sharp peak or low tail). To remedy this, we propose an improved MOEA/D with adaptive weight vector adjustment (MOEA/D-AWA). According to the analysis of the geometric relationship between the weight vectors and the optimal solutions under the Chebyshev decomposition scheme, a new weight vector initialization method and an adaptive weight vector adjustment strategy are introduced in MOEA/D-AWA. The weights are adjusted periodically so that the weights of subproblems can be redistributed adaptively to obtain better uniformity of solutions. Meanwhile, computing efforts devoted to subproblems with duplicate optimal solution can be saved. Moreover, an external elite population is introduced to help adding new subproblems into real sparse regions rather than pseudo sparse regions of the complex PF, that is, discontinuous regions of the PF. MOEA/D-AWA has been compared with four state of the art MOEAs, namely the original MOEA/D, Adaptive-MOEA/D, [Formula: see text]-MOEA/D, and NSGA-II on 10 widely used test problems, two newly constructed complex problems, and two many-objective problems. Experimental results indicate that MOEA/D-AWA outperforms the benchmark algorithms in terms of the IGD metric, particularly when the PF of the MOP is complex.

Machine Learning-Based Figure of Merit Model of SIPOS Modulated Drift Region for U-MOSFET.

This paper presents a machine learning-based figure of merit model for superjunction (SJ) U-MOSFET (SSJ-UMOS) with a modulated drift region utilizing semi-insulating poly-crystalline silicon (SIPOS) pillars. This SJ drift region modulation is achieved through SIPOS pillars beneath the trench gate, focusing on optimizing the tradeoff between breakdown voltage (BV) and specific ON-resistance (RON,sp). This analytical model considers the effects of electric field modulation, charge-coupling, and majority carrier accumulation due to additional SIPOS pillars. Gaussian process regression is employed for the figure of merit (FOM = BV2/RON,sp) prediction and hyperparameter optimization, ensuring a reasonable and accurate model. A methodology is devised to determine the optimal BV-RON,sp tradeoff, surpassing the SJ silicon limit. The paper also delves into a discussion of optimal structural parameters for drift region, oxide thickness, and electric field modulation coefficients within the analytical model. The validity of the proposed model is robustly confirmed through comprehensive verification against TCAD simulation results.

DEs-Inspired Accelerated Unfolded Linearized ADMM Networks for Inverse Problems.

Many research works have shown that the traditional alternating direction multiplier methods (ADMMs) can be better understood by continuous-time differential equations (DEs). On the other hand, many unfolded algorithms directly inherit the traditional iterations to build deep networks. Although they achieve superior practical performance and a faster convergence rate than traditional counterparts, there is a lack of clear insight into unfolded network structures. Thus, we attempt to explore the unfolded linearized ADMM (LADMM) from the perspective of DEs, and design more efficient unfolded networks. First, by proposing an unfolded Euler LADMM scheme and inspired by the trapezoid discretization, we design a new more accurate Trapezoid LADMM scheme. For the convenience of implementation, we provide its explicit version via a prediction-correction strategy. Then, to expand the representation space of unfolded networks, we design an accelerated variant of our Euler LADMM scheme, which can be interpreted as second-order DEs with stronger representation capabilities. To fully explore this representation space, we designed an accelerated Trapezoid LADMM scheme. To the best of our knowledge, this is the first work to explore a comprehensive connection with theoretical guarantees between unfolded ADMMs and first-(second-) order DEs. Finally, we instantiate our schemes as (A-)ELADMM and (A-)TLADMM with the proximal operators, and (A-)ELADMM-Net and (A-)TLADMM-Net with convolutional neural networks (CNNs). Extensive inverse problem experiments show that our Trapezoid LADMM schemes perform better than well-known methods.

A Spatial-Spectral Relation-Guided Fusion Network for Multisource Optical RS Image Classification.

Multisource optical remote sensing (RS) image classification has obtained extensive research interest with demonstrated superiority. Existing approaches mainly improve classification performance by exploiting complementary information from multisource data. However, these approaches are insufficient in effectively extracting data features and utilizing correlations of multisource optical RS images. For this purpose, this article proposes a generalized spatial-spectral relation-guided fusion network ( S2 RGF-Net) for multisource optical RS image classification. First, we elaborate on spatial-and spectral-domain-specific feature encoders based on data characteristics to explore the rich feature information of optical RS data deeply. Subsequently, two relation-guided fusion strategies are proposed at the dual-level (intradomain and interdomain) to integrate multisource image information effectively. In the intradomain feature fusion, an adaptive de-redundancy fusion module (ADRF) is introduced to eliminate redundancy so that the spatial and spectral features are complete and compact, respectively. In interdomain feature fusion, we construct a spatial-spectral joint attention module (SSJA) based on interdomain relationships to sufficiently enhance the complementary features, so as to facilitate later fusion. Experiments on various multisource optical RS datasets demonstrate that S2 RGF-Net outperforms other state-of-the-art (SOTA) methods.

Multiscale Deep Learning for Detection and Recognition: A Comprehensive Survey.

Recently, the multiscale problem in computer vision has gradually attracted people's attention. This article focuses on multiscale representation for object detection and recognition, comprehensively introduces the development of multiscale deep learning, and constructs an easy-to-understand, but powerful knowledge structure. First, we give the definition of scale, explain the multiscale mechanism of human vision, and then lead to the multiscale problem discussed in computer vision. Second, advanced multiscale representation methods are introduced, including pyramid representation, scale-space representation, and multiscale geometric representation. Third, the theory of multiscale deep learning is presented, which mainly discusses the multiscale modeling in convolutional neural networks (CNNs) and Vision Transformers (ViTs). Fourth, we compare the performance of multiple multiscale methods on different tasks, illustrating the effectiveness of different multiscale structural designs. Finally, based on the in-depth understanding of the existing methods, we point out several open issues and future directions for multiscale deep learning.

Visual interpretable MRI fine grading of meniscus injury for intelligent assisted diagnosis and treatment.

Meniscal injury represents a common type of knee injury, accounting for over 50% of all knee injuries. The clinical diagnosis and treatment of meniscal injury heavily rely on magnetic resonance imaging (MRI). However, accurately diagnosing the meniscus from a comprehensive knee MRI is challenging due to its limited and weak signal, significantly impeding the precise grading of meniscal injuries. In this study, a visual interpretable fine grading (VIFG) diagnosis model has been developed to facilitate intelligent and quantified grading of meniscal injuries. Leveraging a multilevel transfer learning framework, it extracts comprehensive features and incorporates an attributional attention module to precisely locate the injured positions. Moreover, the attention-enhancing feedback module effectively concentrates on and distinguishes regions with similar grades of injury. The proposed method underwent validation on FastMRI_Knee and Xijing_Knee dataset, achieving mean grading accuracies of 0.8631 and 0.8502, surpassing the state-of-the-art grading methods notably in error-prone Grade 1 and Grade 2 cases. Additionally, the visually interpretable heatmaps generated by VIFG provide accurate depictions of actual or potential meniscus injury areas beyond human visual capability. Building upon this, a novel fine grading criterion was introduced for subtypes of meniscal injury, further classifying Grade 2 into 2a, 2b, and 2c, aligning with the anatomical knowledge of meniscal blood supply. It can provide enhanced injury-specific details, facilitating the development of more precise surgical strategies. The efficacy of this subtype classification was evidenced in 20 arthroscopic cases, underscoring the potential enhancement brought by intelligent-assisted diagnosis and treatment for meniscal injuries.

Negative Deterministic Information-Based Multiple Instance Learning for Weakly Supervised Object Detection and Segmentation.

Weakly supervised object detection (WSOD) and semantic segmentation with image-level annotations have attracted extensive attention due to their high label efficiency. Multiple instance learning (MIL) offers a feasible solution for the two tasks by treating each image as a bag with a series of instances (object regions or pixels) and identifying foreground instances that contribute to bag classification. However, conventional MIL paradigms often suffer from issues, e.g., discriminative instance domination and missing instances. In this article, we observe that negative instances usually contain valuable deterministic information, which is the key to solving the two issues. Motivated by this, we propose a novel MIL paradigm based on negative deterministic information (NDI), termed NDI-MIL, which is based on two core designs with a progressive relation: NDI collection and negative contrastive learning (NCL). In NDI collection, we identify and distill NDI from negative instances online by a dynamic feature bank. The collected NDI is then utilized in a NCL mechanism to locate and punish those discriminative regions, by which the discriminative instance domination and missing instances issues are effectively addressed, leading to improved object-and pixel-level localization accuracy and completeness. In addition, we design an NDI-guided instance selection (NGIS) strategy to further enhance the systematic performance. Experimental results on several public benchmarks, including PASCAL VOC 2007, PASCAL VOC 2012, and MS COCO, show that our method achieves satisfactory performance. The code is available at: https://github.com/GC-WSL/NDI.

CoT: Contourlet Transformer for Hierarchical Semantic Segmentation.

The Transformer-convolutional neural network (CNN) hybrid learning approach is gaining traction for balancing deep and shallow image features for hierarchical semantic segmentation. However, they are still confronted with a contradiction between comprehensive semantic understanding and meticulous detail extraction. To solve this problem, this article proposes a novel Transformer-CNN hybrid hierarchical network, dubbed contourlet transformer (CoT). In the CoT framework, the semantic representation process of the Transformer is unavoidably peppered with sparsely distributed points that, while not desired, demand finer detail. Therefore, we design a deep detail representation (DDR) structure to investigate their fine-grained features. First, through contourlet transform (CT), we distill the high-frequency directional components from the raw image, yielding localized features that accommodate the inductive bias of CNN. Second, a CNN deep sparse learning (DSL) module takes them as input to represent the underlying detailed features. This memory-and energy-efficient learning method can keep the same sparse pattern between input and output. Finally, the decoder hierarchically fuses the detailed features with the semantic features via an image reconstruction-like fashion. Experiments demonstrate that CoT achieves competitive performance on three benchmark datasets: PASCAL Context 57.21% mean intersection over union (mIoU), ADE20K (54.16% mIoU), and Cityscapes (84.23% mIoU). Furthermore, we conducted robustness studies to validate its resistance against various sorts of corruption. Our code is available at: https://github.com/yilinshao/CoT-Contourlet-Transformer.

Brain-Inspired Learning, Perception, and Cognition: A Comprehensive Review.

The progress of brain cognition and learning mechanisms has provided new inspiration for the next generation of artificial intelligence (AI) and provided the biological basis for the establishment of new models and methods. Brain science can effectively improve the intelligence of existing models and systems. Compared with other reviews, this article provides a comprehensive review of brain-inspired deep learning algorithms for learning, perception, and cognition from microscopic, mesoscopic, macroscopic, and super-macroscopic perspectives. First, this article introduces the brain cognition mechanism. Then, it summarizes the existing studies on brain-inspired learning and modeling from the perspectives of neural structure, cognitive module, learning mechanism, and behavioral characteristics. Next, this article introduces the potential learning directions of brain-inspired learning from four aspects: perception, cognition, understanding, and decision-making. Finally, the top-ten open problems that brain-inspired learning, perception, and cognition currently face are summarized, and the next generation of AI technology has been prospected. This work intends to provide a quick overview of the research on brain-inspired AI algorithms and to motivate future research by illuminating the latest developments in brain science.