Evaluating security and reliability for multi-agent systems (MAS) is urgent as they become increasingly prevalent in various applications. As an evaluation technique, existing adversarial attack frameworks face certain limitations, e.g., impracticality due to the requirement of white-box information or high control authority, and a lack of stealthiness or effectiveness as they often target all agents or specific fixed agents. To address these issues, we propose AdapAM, a novel framework for adversarial attacks on black-box MAS. AdapAM incorporates two key components: (1) Adaptive Selection Policy simultaneously selects the victim and determines the anticipated malicious action (the action would lead to the worst impact on MAS), balancing effectiveness and stealthiness. (2) Proxy-based Perturbation to Induce Malicious Action utilizes generative adversarial imitation learning to approximate the target MAS, allowing AdapAM to generate perturbed observations using white-box information and thus induce victims to execute malicious action in black-box settings. We evaluate AdapAM across eight multi-agent environments and compare it with four state-of-the-art and commonly-used baselines. Results demonstrate that AdapAM achieves the best attack performance in different perturbation rates. Besides, AdapAM-generated perturbations are the least noisy and hardest to detect, emphasizing the stealthiness.

Stochastic dynamical systems have emerged as fundamental models across numerous application domains, providing powerful mathematical representations for capturing uncertain system behavior. In this paper, we address the problem of runtime safety and reach-avoid probability prediction for discrete-time stochastic systems with online observations, i.e., estimating the probability that the system satisfies a given safety or reach-avoid specification. Unlike traditional approaches that rely solely on offline models, we propose a framework that incorporates real-time observations to dynamically refine probability estimates for safety and reach-avoid events. By introducing observation-aware barrier functions, our method adaptively updates probability bounds as new observations are collected, combining efficient offline computation with online backward iteration. This approach enables rigorous and responsive prediction of safety and reach-avoid probabilities under uncertainty. In addition to the theoretical guarantees, experimental results on benchmark systems demonstrate the practical effectiveness of the proposed method.

Abstract Moment estimation for stochastic differential equations (SDEs) is fundamental to the formal reasoning and verification of stochastic dynamical systems, yet remains challenging and is rarely available in closed form. In this paper, we study time-homogeneous SDEs with polynomial drift and diffusion, and investigate when their moments can be computed exactly. We formalize the notion of moment-solvable SDEs and propose a generic symbolic procedure that, for a given monomial, attempts to construct a finite-dimensional linear ordinary differential equation (ODE) system governing its moment, thereby enabling exact computation. We introduce a syntactic class of pro-solvable SDEs, characterized by a block-triangular structure, and prove that all polynomial moments of any pro-solvable SDE admit such finite ODE representations. This class strictly generalizes linear SDEs and includes many nonlinear models. Experimental results demonstrate the effectiveness of our approach.

The World Wide Web needs reliable predictive capabilities to respond to changes in user behavior and usage patterns. Time series forecasting (TSF) is a key means to achieve this goal. In recent years, the large language models (LLMs) for TSF (LLM4TSF) have achieved good performance. However, there is a significant difference between pretraining corpora and time series data, making it hard to guarantee forecasting quality when directly applying LLMs to TSF; fine-tuning LLMs can mitigate this issue, but often incurs substantial computational overhead. Thus, LLM4TSF faces a dual challenge of prediction performance and compute overhead. To address this, we aim to explore a method for improving the forecasting performance of LLM4TSF while freezing all LLM parameters to reduce computational overhead. Inspired by in-context learning (ICL), we propose LVICL. LVICL uses our vector-injected ICL to inject example information into a frozen LLM, eliciting its in-context learning ability and thereby enhancing its performance on the example-related task (i.e., TSF). Specifically, we first use the LLM together with a learnable context vector adapter to extract a context vector from multiple examples adaptively. This vector contains compressed, example-related information. Subsequently, during the forward pass, we inject this vector into every layer of the LLM to improve forecasting performance. Compared with conventional ICL that adds examples into the prompt, our vector-injected ICL does not increase prompt length; moreover, adaptively deriving a context vector from examples suppresses components harmful to forecasting, thereby improving model performance. Extensive experiments demonstrate the effectiveness of our approach.

Due to the selective absorption and scattering of light by diverse aquatic media, underwater images usually suffer from various visual degradations. Existing underwater image enhancement (UIE) approaches that combine underwater physical imaging models with neural networks often fail to accurately estimate imaging model parameters such as scene depth and veiling light, resulting in poor performance in certain scenarios. To address this issue, we propose a physical model-guided framework for jointly training a Deep Degradation Model (DDM) with any advanced UIE model. DDM includes three well-designed sub-networks to accurately estimate various imaging parameters: a veiling light estimation sub-network, a factors estimation sub-network, and a depth estimation sub-network. Based on the estimated parameters and the underwater physical imaging model, we impose physical constraints on the enhancement process by modeling the relationship between underwater images and desired clean images, i.e., outputs of the UIE model. Moreover, while our framework is compatible with any UIE model, we design a simple yet effective fully convolutional UIE model, termed UIEConv. UIEConv utilizes both global and local features through a dual-branch structure. UIEConv trained within our framework achieves remarkable enhancement results across diverse underwater scenes. Furthermore, as a byproduct of UIE, the trained depth estimation sub-network enables accurate underwater scene depth estimation. Extensive experiments conducted in various real underwater imaging scenarios, including deep-sea environments with artificial light sources, validate the effectiveness of our framework and the UIEConv model. Code is available at https://github.com/ddz16/UWEnhancer.

Image restoration represents a promising approach for addressing the inherent defects of image content distortion. Standard image restoration approaches suffer from high storage cost and the requirement towards the known degradation pattern, including type and degree, which can barely be satisfied in dynamic practical scenarios. In contrast, all-in-one image restoration (AiOIR) eliminates multiple degradations within a unified model to circumvent the aforementioned issues. However, according to our causal analysis, we disclose that two significant defects still exacerbate the effectiveness and generalization of AiOIR models: 1) the spurious correlation between non-degradation semantic features and degradation patterns; 2) the biased estimation of degradation patterns. To obtain the true causation between degraded images and restored images, we propose Causal-deconfounding Wavelet-disentangled Prompt Network (CWP-Net) to perform effective AiOIR. CWP-Net introduces two modules for decoupling, i.e., wavelet attention module of encoder and wavelet attention module of decoder. These modules explicitly disentangle the degradation and semantic features to tackle the issue of spurious correlation. To address the issue stemming from the biased estimation of degradation patterns, CWP-Net leverages a wavelet prompt block to generate the alternative variable for causal deconfounding. Extensive experiments on two all-in-one settings prove the effectiveness and superior performance of our proposed CWP-Net over the state-of-the-art AiOIR methods.

Explaining multi-agent systems (MAS) is urgent as these systems become increasingly prevalent in various applications. Previous work has provided explanations for the actions or states of agents, yet falls short in understanding the blackboxed agent’s importance within a MAS and the overall team strategy. To bridge this gap, we propose EMAI, a novel agent-level explanation approach that evaluates the individual agent’s importance. Inspired by counterfactual reasoning, a larger change in reward caused by the randomized action of agent indicates its higher importance. We model it as a MARL problem to capture interactions across agents. Utilizing counterfactual reasoning, EMAI learns the masking agents to identify important agents. Specifically, we define the optimization function to minimize the reward difference before and after action randomization and introduce sparsity constraints to encourage the exploration of more action randomization of agents during training. The experimental results in seven multi-agent tasks demonstrate that EMAI achieves higher fidelity in explanations compared to baselines and provides more effective guidance in practical applications concerning understanding policies, launching attacks, and patching policies.

Low-light image enhancement aims to improve visual quality under challenging lighting conditions while preserving details and color fidelity. Existing traditional algorithms and deep learning approaches, often struggle with balancing brightness enhancement and detail preservation, leading to issues such as overexposure, artifacts, and loss of high-frequency details. To address these challenges, we propose a novel method, Bio-Inspired Attention and Wavelet Diffusion (BIAWDiff), that integrates Retinex theory with bio-inspired attention and wavelet-based diffusion models to enhance low-light Images. BIAWDiff consists of three key modules: the Initial Light Restoration (ILR) module for brightness enhancement and noise reduction, the Rod Cell-Inspired Attention Refinement (RCAR) module for luminance refinement, and the Detail Refinement (DR) module for restoring high-frequency details. Experimental results demonstrate that BIAWDiff outperforms existing techniques, achieving superior results in brightness enhancement, noise reduction, and detail preservation, with an average PSNR increase of 5.1% and SSIM improvement of 3.2% on paired datasets, and a reduction in NIQE and BRISQUE by 7.4% and 8.6% on unpaired datasets.

Low-light image enhancement aims to improve lightness and eliminate degradation caused by low light. However, most current methods struggle to effectively handle the mixed degradations of both brightness and structure, leading to structural distortions and insufficient brightness enhancement. Additionally, existing Fourier-based methods learn amplitude and phase independently, yet overlook the intrinsic connection between brightness and structure. In this paper, we propose an amplitude-guidance low-light image enhancement network, which utilizes the Fourier transform to extract the amplitude and phase of images and reconstruct them using the network. Considering that uneven brightness distribution in images can lead to varying levels of structural degradation, we design an Amplitude-Guidance Self-Attention (AGSA) that uses amplitude to guide phase recovery, enabling it to handle different levels of structure degradation. Additionally, to further improve the enhancement capability of our network, we design a Frequency-based Channel Attention (FCA) that preserves more frequency information when compressing channels. Extensive experiments demonstrate the superiority of our proposed network over existing SOTA methods.

Image degradation results from a combination of factors. Recently, CNN-based image deblurring methods have made significant progress, but they rely heavily on the accuracy of paired data, which is impractical to collect for every camera. To address this, we propose a physical model for natural images that applies to various cameras. This model considers the diffusion effects of multiple factors during degradation and effectively simulates the degraded state of natural images. We then design the Defocus Map-based Kernel Prediction Network (DMKPN) for adaptive image quality enhancement. Specifically, we develop a DM-Attention Block to assist kernel prediction under the guidance of the defocus map and design Multi-Scale Modulation to filter information at each scale, making the most of image context. Additionally, Multi-Scale Loss is introduced to enhance network robustness. Experiments demonstrate that our method exhibits strong spatial adaptability and generates high-quality images with sharp edges.

Scene recognition, particularly for aerial and underwater images, often suffers from various types of degradation, such as blurring or overexposure. Previous works that focus on convolutional neural networks have been shown to be able to extract panoramic semantic features and perform well on scene recognition tasks. However, low-quality images still impede model performance due to the inappropriate use of high-level semantic features. To address these challenges, we propose an adaptive selection mechanism to identify the most important and robust regions with high-level features. Thus, the model can perform learning via these regions to avoid interference. implement a learnable mask in the neural network, which can filter high-level features by assigning weights to different regions of the feature matrix. We also introduce a regularization term to further enhance the significance of key high-level feature regions. Different from previous methods, our learnable matrix pays extra attention to regions that are important to multiple categories but may cause misclassification and sets constraints to reduce the influence of such regions. This is a plug-and-play architecture that can be easily extended to other methods. Additionally, we construct an Underwater Geological Scene Classification dataset to assess the effectiveness of our model. Extensive experimental results demonstrate the superiority and robustness of our proposed method over state-of-the-art techniques on two datasets.

Due to dark environments, optical aberrations, etc, the remote sensing images are often submerged under low contrast degradation, which greatly hinders their practical applications for agricultural management and other related tasks. The surface features of remote sensing images are often continuously distributed in space, thus, the sizes of the network’s receptive fields and its ability to learn long-range dependencies are crucial for restoring low-light remote sensing images. Existing methods based on CNN provide limited receptive fields, while Transformer-based methods are constrained by their quadratic computational complexity. To cope with these issues, we propose a novel low-light remote sensing image enhancement network that combines multi-scale receptive fields with frequency-domain attention. Specifically, this network employs multiple parallel kernels of varying sizes to learn multi-scale local features in the spatial domain and complements frequency-domain information to learn global long-range correlations, which achieves local-global feature extraction and further facilitates subsequent degraded images enhancement. We have conducted extensive experiments to demonstrate that our network outperforms existing methods quantitatively and achieves exceptional visual performance, which fully highlights the effectiveness and superiority of our method in enhancing low-light remote sensing images.

The low-light image enhancement has always been an important yet challenging task, which attracts significant attention in many fields. However, prior methods either ignore integrating semantic priors or depend on the masks generated by the pre-trained segmentation model. This way is complex and inevitably leads to inaccurate masks when facing unseen scenarios, which may be incompatible with the original feature and result in suboptimal performance. To address this issue, we first consider the high-frequency physical prior is more related to structural and textural properties, which embrace the rich semantic clues and can adaptively assist the learning process under various scenarios. Inspired by this, we propose the high-frequency semantic-aware guidance framework (HighFreNet) to leverage the guidance of semantic information tailored for enhancing low-light images. Specifically, the core parts are the novel Frequency-based Semantic Embedding Module (FSEM) and the Spatial-based Semantic Embedding Module (SSEM), which are separately designed to fully exploit the structure knowledge to modulate the original representation from frequency and spatial perspectives. Extensive experiments showcase that our method significantly outperforms the state-of-the-art methods on five benchmark datasets both in natural and remote sensing environments.

MLIR (Multi-Level Intermediate Representation) has rapidly become a foundational technology for modern compiler frameworks, enabling extensibility across diverse domains. However, ensuring the correctness and robustness of MLIR itself remains challenging. Existing fuzzing approaches—based on manually crafted templates or rule-based mutations—struggle to generate sufficiently diverse and semantically valid test cases, making it difficult to expose subtle or deep-seated bugs within MLIR’s complex and evolving code space. In this paper, we present FLEX, a novel self-adaptive fuzzing framework for MLIR. FLEX leverages neural networks for program generation, a perturbed sampling strategy to encourage diversity, and a feedback-driven augmentation loop that iteratively improves its model using both crashing and non-crashing test cases. Starting from a limited seed corpus, FLEX progressively learns valid syntax and semantics and autonomously produces high-quality test inputs. We evaluate FLEX on the upstream MLIR compiler against four state-of-the-art fuzzers. In a 30-day campaign, FLEX discovers 80 previously unknown bugs—including multiple new root causes and parser bugs—while in 24-hour fixed-revision comparisons, it detects 53× bugs (over 3.5 as many as the best baseline) and achieves 28.2% code coverage, outperforming the next-best tool by 42%. Ablation studies further confirm the critical role of both perturbed generation and diversity augmentation in FLEX’s effectiveness.

Self-supervised topological deep learning (TDL) represents a nascent but underexplored area with significant potential for modeling higher-order interactions in simplicial complexes and cellular complexes to derive representations of unlabeled graphs. Compared to simplicial complexes, cellular complexes exhibit greater expressive power. However, the advancement in self-supervised learning for cellular TDL is largely hindered by two core challenges: extrinsic structural constraints inherent to cellular complexes, and intrinsic semantic redundancy in cellular representations. The first challenge highlights that traditional graph augmentation techniques may compromise the integrity of higher-order cellular interactions, while the second underscores that topological redundancy in cellular complexes potentially diminish task-relevant information. To address these issues, we introduce Cellular Complex Contrastive Learning with Adaptive Trimming (CellCLAT), a twofold framework designed to adhere to the combinatorial constraints of cellular complexes while mitigating informational redundancy. Specifically, we propose a parameter perturbation-based augmentation method that injects controlled noise into cellular interactions without altering the underlying cellular structures, thereby preserving cellular topology during contrastive learning. Additionally, a cellular trimming scheduler is employed to mask gradient contributions from task-irrelevant cells through a bi-level meta-learning approach, effectively removing redundant topological elements while maintaining critical higher-order semantics. We provide theoretical justification and empirical validation to demonstrate that CellCLAT achieves substantial improvements over existing self-supervised graph learning methods, marking a significant attempt in this domain.

The competitive game between agents exists in many critical applications, such as military unmanned aerial vehicles. It is urgent to test these agents to reduce the significant losses caused by their failures. Existing studies mainly are to construct a testing agent that competes with the target agent to induce its failures. These approaches usually focus on a single task, requiring much more time for multi-task testing. However, if the previously tested tasks (source tasks) and the task to be tested (target task) share similar agents or task objectives, the transferable knowledge in source tasks can potentially increase the effectiveness of testing in the target task. We propose Demo2Test for conducting transfer testing of agents in the competitive environment, i.e., leveraging the demonstrations of failure scenarios from the source task to boost the testing effectiveness in the target task. It trains a testing agent with demonstrations and incorporates the action perturbation at key states to balance the number of revealed failures and their diversity. We conduct experiments in the simulated robotics competitive environments of MuJoCo. The results indicate that Demo2Test outperforms the best-performing baseline with improvements ranging from \(22.38\%\) to \(87.98\%\) , and \(12.69\%\) to \(60.98\%\) , in terms of the number and diversity of discovered failure scenarios, respectively.

Deep reinforcement learning has achieved remarkable success in competitive games, surpassing human performance in applications ranging from business competitions to video games. In competitive environments, agents face the challenge of adapting to continuously shifting adversary strategies, necessitating the ability to handle diverse scenarios. Existing studies primarily focus on evaluating agent robustness either through perturbing observations, which has practical limitations, or through training adversarial agents to expose weaknesses, which lacks strategy diversity exploration. There are also studies which rely on curiosity-based mechanism to explore the diversity, yet they may lack direct guidance to enhance identified decision-making flaws. In this paper, we propose a novel diversity-oriented testing framework (called AdvTest) to test the competitive game agent via constraint-guided adversarial agent training. Specifically, AdvTest adds constraints as the explicit guidance during adversarial agent training to make it capable of defeating the target agent using diverse strategies. To realize the method, three challenges need to be addressed, i.e., what are the suitable constraints, when to introduce constraints, and which constraint should be added. We experimentally evaluate AdvTest on the commonly-used competitive game environment, StarCraft II. The results on four maps show that AdvTest exposes more diverse failure scenarios compared with the commonly-used and state-of-the-art baselines.

Graph contrastive learning is a general learning paradigm excelling at capturing invariant information from diverse perturbations in graphs. Recent works focus on exploring the structural rationale from graphs, thereby increasing the discriminability of the invariant information. However, such methods may incur in the mis-learning of graph models towards the interpretability of graphs, and thus the learned noisy and task-agnostic information interferes with the prediction of graphs. To this end, with the purpose of exploring the intrinsic rationale of graphs, we accordingly propose to capture the dimensional rationale from graphs, which has not received sufficient attention in the literature. The conducted exploratory experiments attest to the feasibility of the aforementioned roadmap. To elucidate the innate mechanism behind the performance improvement arising from the dimensional rationale, we rethink the dimensional rationale in graph contrastive learning from a causal perspective and further formalize the causality among the variables in the pre-training stage to build the corresponding structural causal model. On the basis of the understanding of the structural causal model, we propose the dimensional rationale-aware graph contrastive learning approach, which introduces a learnable dimensional rationale acquiring network and a redundancy reduction constraint. The learnable dimensional rationale acquiring network is updated by leveraging a bi-level meta-learning technique, and the redundancy reduction constraint disentangles the redundant features through a decorrelation process during learning. Empirically, compared with state-of-the-art methods, our method can yield significant performance boosts on various benchmarks with respect to discriminability and transferability. The code implementation of our method is available at https://github.com/ByronJi/DRGCL.

Marine radar is employed across multiple fields, notably in navigation, meteorology, defense, and security. Marine radar images are highly sensitive to sea clutter, highlighting the crucial importance of sea clutter suppression in radar image processing. However, existing algorithms for sea clutter suppression often struggle to effectively generalize in complex marine environments. In this paper, we introduce RadarDiff, a novel approach that leverages diffusion models to enhance sea clutter suppression in marine radar plan-position indicator (PPI) images. We treat sea clutter suppression as an image-to-image translation task and propose a novel data augmentation method to create image pairs with and without sea clutter. Additionally, we introduce a unique loss function designed to address the challenge of small targets disappearing after suppression. To our knowledge, we are the first to utilize the diffusion-based model in sea clutter suppression for radar PPI images. Our quantitative and qualitative results demonstrate significant improvements compared to traditional denoising methods and classical GAN-based models.

Retinex-based methods have achieved significant progress in enhancing low-light images benefits for its disentanglement property. However, existing methods either ignore the semantic priors or randomly leverage them only in the spatial domain, which leads to insufficient coupling and limits the performance gains. Considering the lightness mainly exists in the amplitude component and the rest is related to the phase component, making it optimal to combine the Retinex decomposition with the Fourier transform to achieve customized restoration. In this paper, we propose a novel method RetinexFour tailored for low-light image enhancement. Specifically, it consists of Phase-Guided Multi-head Self-Attention (PG-MSA) and Local Spatial Attention (LSA) to allow for the reconstruction of structure from spatial-frequency perspectives. To achieve exposure correction, we introduce Selective Amplitude feature Fusion (SAFF) by combining the original and complementary amplitude to achieve global lightness adjustment. Extensive experiments demonstrate the superiority of our method over other SOTA methods on four benchmark datasets.

Multi-agent systems (MASs) have achieved remarkable success in multi-robot control, intelligent transportation, and multiplayer games, etc. Thorough testing for MAS is urgently needed to ensure its robustness in the face of constantly changing and unexpected scenarios. Existing methods mainly focus on single-agent system testing and cannot be directly applied to MAS testing due to the complexity of MAS. To our best knowledge, there are fewer studies on MAS testing. While several studies have focused on adversarial attacks on MASs, they primarily target failure detection from an attack perspective, i.e., discovering failure scenarios, while ignoring the diversity of scenarios. In this paper, to highlight a typical balance between exploration (diversifying behaviors) and exploitation (detecting failures), we propose an advanced testing framework for MAS called with diversity-guided exploration and adaptive critical state exploitation. It incorporates both individual diversity and team diversity, and designs an adaptive perturbation mechanism to perturb the action at the critical states, so as to trigger more and more diverse failure scenarios of the system. We evaluate MASTest on two popular MAS simulation environments: Coop Navi and StarCraft II. Results show that the average distance of the resulting failure scenarios is increased by 29.55%-103.57% and 74.07%-370.00% on two environments compared to the baselines. Also, the failure patterns found by MASTest are improved by 71.44%-300.00% and 50%-500.00% on two experimental environments compared to the baselines.

As a new form of Earth-observation requirement, dense points usually contain a large number of points of interest (Pols) which are distributed in a wide area and need to be planed by involving several satellites to perform the tasks collaboratively. This challenges the usage of satellites when visible time window is calculated and decided separately for each Pol, causing frequent switching among a lot of Pol captures. While traditional methods are more suitable for observing fewer Pols, denser points require a different approach to fully utilize satellite resources and avoid inefficient tasking. Meanwhile, because Pols are geographically clustered and dispersed in different regions, more satellites need to be analyzed in order to generate a collaborative planning result. This paper proposed a dense-point aggregation method that uses clustering to generate a hybrid task representation based on the geographic distribution of Pols. A collaborative plan modeling and solving algorithm is proposed to provide a compatible optimization with this hybrid representation. The efficacy of the proposed method is demonstrated in the experiment to show the advantage of the proposed method.

Due to atmospheric turbulence, optical system limitations, satellite platform jitter, and other reasons, remote sensing images inevitably undergo different degrees of degradation. Employing the deep learning method to improve the on-orbit image quality faces many challenges such as lack of data, limited computing resources, network architecture design, and so on. Among these factors, establishing a physics-guided dataset during the image restoration stage and avoiding unforeseen effects such as ringing pose a significant challenge for remote sensing image restoration. This letter proposes an optical imaging degradation simulation model and Transformer-based algorithm to improve remote sensing image quality. First, we model the degradation result from phase to image of optical remote sensing imaging using Zernike Polynomials, thus, a large-scale paired dataset is constructed. Then, a multi-level feature fusion transformer is introduced to mitigate the defect during restoration. The proposed algorithm incorporates a multi-level feature fusion module to fuse feature information from multi-scales effectively. Additionally, a multi-level space and frequency loss function is introduced to enhance the learning of high-frequency information to ensure that the edge suppresses noise amplification and ringing effects during recovery. Finally, experimental results on synthetic data show that our method improved by 25.4% and 22.3% with the blurred images on the PSNR index and SSIM index. Visual results on the GaoFen-1/2A PMS images have enhanced clarity and suppressed artifacts such as ringing which demonstrate the effectiveness and capability of our proposed method.

The presence of blur is prevalent in satellite remote sensing images (RSIs), and its detrimental impact on downstream applications cannot be overlooked. Current deep learning approaches for image deblurring have gained substantial attention due to their effectiveness and fast inference speed. However, these methods often heavily rely on extensive paired training datasets and lack interpretability. Existing deblurring datasets primarily include regular scenes while remote sensing images exhibit distinct blurring mechanisms. Consequently, deep learning methods lacking prior physical knowledge can only tackle the image deblurring problem in specific scenarios, but hard to achieve satisfactory results on remote sensing images. To address these problems, it is essential to construct a remote sensing image dataset that incorporates the realistic causes of blurriness and integrate prior knowledge into the methods. In this work, we first analyze the satellite imaging system and use Zernike polynomials to approximate the optical aberrations to simulate the RSI blurring process which ensures the proposed dataset adhering solid physical principles. Moreover, we propose a novel physics-guided RSI deblurring (PGRSID) network that integrates an explicit Wiener deconvolution process in both spatial and deep feature space. This integration better leverages the physical interpretation to facilitate effective learning for the RSI deblurring network. We further incorporate denoise loss and cycle consistency loss in the objective function to facilitate the model’s learning process for RSI deblurring. Extensive experiments are conducted on both our synthetic dataset and real GF-1A/PMS data. Qualitative and quantitative experiment results highlight the effectiveness and superiority of our physics-guided deblurring network for satellite RSI.

Video action segmentation under timestamp supervision has recently received much attention due to lower annotation costs. Most existing methods generate pseudo-labels for all frames in each video to train the segmentation model. However, these methods suffer from incorrect pseudo-labels, especially for the semantically unclear frames in the transition region between two consecutive actions, which we call ambiguous intervals. To address this issue, we propose a novel framework from the perspective of clustering, which includes the following two parts. First, pseudo-label ensembling generates incomplete but high-quality pseudo-label sequences, where the frames in ambiguous intervals have no pseudo-labels. Second, iterative clustering iteratively propagates the pseudo-labels to the ambiguous intervals by clustering, and thus updates the pseudo-label sequences to train the model. We further introduce a clustering loss, which encourages the features of frames within the same action segment more compact. Extensive experiments show the effectiveness of our method.

Low visibility and severe noise are two main degradations in extreme low-light images. Nevertheless, existing low-light image enhancement methods often fail to handle real low-light images with strong noise. To address this issue, We propose a deep unfolding network based on the robust Retinex model with an additional noise term. In particular, we design an optimization model with implicit priors and employ the proximal gradient descent (PGD) technique to alternately solve three iterative sub-problems of the optimization model in a data-driven manner. The proposed method combines the interpretability of model-based methods with the speed and strong fitting ability of learning-based methods. In addition, we collect an extreme low-light sRGB image dataset (E-LOL) containing noisy low/normal-light image pairs. Extensive experimental results demonstrate that our method outperforms state-of-the-art methods in enhancing noisy low-light images and obtains better-exposed illumination, richer colors and textures.

The low-light image enhancement has long been a critical need in practical applications. Existing methods require either paired or unpaired datasets. Zero-shot methods avoid the requirement of datasets, but they simply enhance the illumination component of the entire image with traditional gamma transformation, which causes color deviation and fails to process low-light images with uneven illumination. Also, these methods often do not take noise into account. We propose a zero-shot low-light image enhancement method. First, we decompose the image into illumination and reflectance according to the Retinex theory. The decomposed reflectance usually contains noise, so we estimate and remove the noise from the reflectance. To enhance the illumination, we design a hybrid illumination enhancement curve that combines gamma transformation and linear transformation. Also, we use a convolutional neural network to estimate the parametric maps in the curve to achieve pixel-level illumination enhancement, so our method can robustly process low-light images with uneven illumination. Extensive experiments demonstrate that our method outperforms recent state-of-the-art methods qualitatively and quantitatively.

When a facial image is blurred, it significantly affects high-level vision tasks such as face recognition. The purpose of facial image deblurring is to recover a clear image from a blurry input image, which can improve the recognition accuracy, etc. However, general deblurring methods do not perform well on facial images. Therefore, some face deblurring methods have been proposed to improve performance by adding semantic or structural information as specific priors according to the characteristics of the facial images. In this paper, we survey and summarize recently published methods for facial image deblurring, most of which are based on deep learning. First, we provide a brief introduction to the modeling of image blurring. Next, we summarize face deblurring methods into two categories: model-based methods and deep learning-based methods. Furthermore, we summarize the datasets, loss functions, and performance evaluation metrics commonly used in the neural network training process. We show the performance of classical methods on these datasets and metrics and provide a brief discussion on the differences between model-based and learning-based methods. Finally, we discuss the current challenges and possible future research directions.

With the rapid prevalence of smart mobile devices and the dramatic proliferation of location-based social networks (LBSNs), location-based recommendation has become an important means to help people discover attractive and interesting points of interest (POIs). However, the extreme sparsity of user-POI matrix and cold-start issue create severe challenges, causing CF-based methods to degrade significantly in their recommendation performance. Moreover, location-based recommendation requires spatiotemporal context awareness and dynamic tracking of the user's latest preferences in a real-time manner.

Sequence pattern mining is an important mining task in data mining. However, most researches focus on improving the efficiency of algorithms, more and more attentions are paid to independently analyzing each frequent sequential pattern, which could bring biases to the final decisions. To understand the whole situation with sequence patterns, this paper proposes a systematic approach called Timing-IdeaGraph to build a directed cognition graph. Firstly, with consideration of big data on event sequences, an efficient algorithm is applied to capture frequent sequential patterns. Next, duplicate patterns are removed. After that, we merge relevant patterns and visualize them into a directed cognition graph. In order to make the approach human-centric, we propose an algorithm to identify bridge events and patterns which would proactively trigger human's deep cognition, e.g., creative design, for better decision making. Two real case studies are introduced to show how to use Timing-IdeaGraph in a computer supported cooperative environment.

Learning an appropriate feature representation across source and target domains is one of the most effective solutions to domain adaptation problems. Conventional cross-domain feature learning methods rely on the Reproducing Kernel Hilbert Space (RKHS) induced by a single kernel. Recently, Multiple Kernel Learning (MKL), which bases classifiers on combinations of kernels, has shown improved performance in the tasks without distribution difference between domains. In this paper, we generalize the framework of MKL for cross-domain feature learning and propose a novel Transfer Feature Representation (TFR) algorithm. TFR learns a convex combination of multiple kernels and a linear transformation in a single optimization which integrates the minimization of distribution difference with the preservation of discriminating power across domains. As a result, standard machine learning models trained in the source domain can be reused for the target domain data. After rewritten into a differentiable formulation, TFR can be optimized by a reduced gradient method and reaches the convergence. Experiments in two real-world applications verify the effectiveness of our proposed method.

Aircraft detection in satellite images is generally difficult due to the variations of aircraft type, pose, size and complex background. In this paper, we propose a new aircraft detection framework based on objectiveness detection techniques (e.g., BING) and Convolutional Neural Networks (CNN). The advantages are two folds. On one hand, we first introduce the CNN for aircraft detection, as CNN can learn rich features from the raw data automatically and has yielded a state-of-the-art performance in many object detection tasks. On the other hand, the use of candidate object regions proposed by BING achieves a high object detection rate and saves time simultaneously. Experimental results show that the proposed method is fast and effective to detect aircrafts in complex airport scenes. We also construct a dataset for aircraft detection obtained from Google Earth.

The land use and land cover classification is an important and hot research topic in remote sensing image processing. How to use information effectively in remote sensing data to categorize different land use and land cover scenes needs urgent attention. In this paper, we analysis the Bag-of-Word model based feature extracting method systematically, and propose the Saliency Map Cooperated (SMC) coding strategy according characters of remote sensing images. The proposed SMC takes into account both the primary objects and partial of large scale objects in remote sensing images, with little effecting on texture dominated images. Extensive experimental results show the efficiency of the proposed SMC coding strategy.

Idea Graph is a core component of Idea Discovery, which discovers idea by converting unstructured data into a scenario graph. Since the scenario graph is complex and heterogeneous, the layouts generated by general graph layout algorithms can't well support human cognition. To tackle this issue, a novel graph layout algorithm named CiFDAL is proposed, which is a hybrid of circular layout algorithm and Force-Directed Algorithm (FDA). Overall, it places clusters and key nodes on two nested circles, and different hierarchies distinguish their different importance. Specifically, it uses FDA to ensure the related nodes being closer in distance. Additionally, it improves the classical random initialized FDA by adopting a better initial position set and iterative node-position exchange technique. Experimental results demonstrate the superiority of our algorithm by comparing with several benchmarks implemented in a famous visualization tool - GraphViz.

With the rapid technological development of various different satellite sensors, a huge volume of high-resolution image data sets can now be obtained and widely used in military and civilian fields. Detecting typical targets in satellite images is a challenging task due to the complicated background. Traditional manually engineered features (i.e. HOG, Gabor feature and Hough transform, etc.) do not work well for massive high-resolution remote sensing image data. Thus, we are expected to find an efficient way to automatically learn the presentations from the massive image data and increase the computational efficiency of target detection. Comparing to the general objects in nature images, the edge information of targets in satellite images shows more distinctive and concise characteristics. This paper proposes a new target detection framework based on Edge Boxes and Convolutional Neural Networks (CNN). CNN can learn rich features automatically and is invariant to small rotation and shifts, has achieved state of-the-art performance in many image classification databases. Edge Boxes can generate a smaller set of object proposals based on the edges of objects. The proposed method can reduce the computational time of the detector. Extensive experiments demonstrate that the proposed framework is effective in typical target detection systems.

Recently, Retrospective Event Detection attracts much attention. Most researches focus on detecting coarse-grained events or frequent events. However, they neglect to discover fine grained events or important rare events which are significant for human decision making. The important rare events are different from the frequent events revealing common patterns, their features are unnoticed and cannot be effectively extracted from the historical data. To tackle this issue, a systematic approach called RCFGED is proposed to simultaneously detect coarse and fine-grained events by incorporating Chance Discovery theory with topic modeling. The approach employs a Chance Discovery algorithm called Idea Graph, which mines the latent term relations for converting the corpus into a term graph. Then, a semantic-relation extraction approach is proposed based on topic modeling to enrich the graph. Lastly, a graph analytical method is employed to detect the events from the graph. An experiment demonstrates the superiority of RCFGED by comparing with benchmarks.

Supervised metric learning plays a substantial role in statistical classification. Conventional metric learning algorithms have limited utility when the training data and testing data are drawn from related but different domains (i.e., source domain and target domain). Although this issue has got some progress in feature-based transfer learning, most of the work in this area suffers from non-trivial optimization and pays little attention to preserving the discriminating information. In this paper, we propose a novel metric learning algorithm to transfer knowledge from the source domain to the target domain in an information-theoretic setting, where a shared Mahalanobis distance across two domains is learnt by combining three goals together: 1) reducing the distribution difference between different domains; 2) preserving the geometry of target domain data; 3) aligning the geometry of source domain data with its label information. Based on this combination, the learnt Mahalanobis distance effectively transfers the discriminating power and propagates standard classifiers across these two domains. More importantly, our proposed method has closed-form solution and can be efficiently optimized. Experiments in two real-world applications demonstrate the effectiveness of our proposed method.

A complex or ill-structured problem cannot be solved only replying on computer since they require human's nonlinear thinking and even innovation. In this paper, taking respective advantages of computer and human, we propose a novel computational knowledge environment (CKE) where human is able to cognize tacit and new knowledge for complex or ill-structured problem solving, through fusing potential knowledge discovered from the collected information data supported by computer. Following the CKE framework, we develop a creativity technique called InnoSpider which greatly support human's perception, intuition, reasoning and cognition for quick decision making. A case study have verified the effectiveness of CKE, and have indicated InnoSpider can drive human to make high-quality decisions in a shorter time.

In recent years, Chance Discovery as an extension of data mining has been presented to discover rare but significant events, i.e., chances, for human decision making from large amounts of data. KeyGraph or IdeaGraph as a chance mining algorithm can capture these chances by converting the unstructured data into a scenario graph. However, they both fail to eliminate the interference of frequent events when uncovering rare events, causing a bottleneck of capturing important rare events. In this paper, we propose an improved algorithm of IdeaGraph to address this issue. It takes rare events as the essential components to preserve them from being filtered when forming a cluster. On base of that, it conducts cluster refining such as pruning and ranking to optimize the construction of a scenario graph. Additionally, it provides an enhanced method to evaluate important rare events by measuring the significance of an event on the perspectives of the co-occurring frequency and the probability distribution. An experiment demonstrates the superiority of our algorithm on capturing important rare events by comparing with benchmark algorithms.

The contours of polygons generated by the image segmentation technique show jagged outlines and a large number of redundant points. Therefore, the original segmentation contours hardly conform to geographic information system (GIS) data-producing standards without generalization. With the complexity of high spatial resolution remote sensing imagery data, with variable sizes of geographic features and their different distributive patterns, it is hard to build a global contour optimization parameter model to guide parameter settings in large regions effectively. Furthermore, it is also difficult to automatically give a unique set of parameters per object simultaneously. In order to meet the actual requirements of GIS data production, we present an adaptively improved algorithm based on the Douglas-Peucker (DP) algorithm, named AIDP, that integrates the criteria of vertical and radial distance restriction, and design a corresponding parameter-adaptive acquisition method. The proposed AIDP method is evaluated by comparing it with the most widely used DP algorithm implemented in the ArcGIS through visual inspection, quantitative measurements, and applications to water body contours. The experimental results show that AIDP can not only acquire generalization parameters automatically but also greatly speed up the data processing workflow with acceptable results.

Server and cluster consolidating is very common in cloud computing era. However, it is not easy to consolidate heterogeneous high-availability (HA) clusters due to the lack of unified administrative tool for managing various kinds of high-availability clusters developed by different vendors. To solve this problem, an SOA-based API gateway, ConHA, is proposed in this paper. ConHA provides unified web service APIs and the functionalities for managing heterogeneous HA cluster. ConHA is designed in a scalable and extensible way. The security issues are also discussed in this paper.

Knowledge discovery in texts (KDT) has been widely applied for business data analysis, but it only reveals a common pattern based on large amounts of data. Since 2000, chance discovery (CD) as an extension of KDT has been proposed to detect rare but significant events or situations regarded as chance candidates for human decision making. Key Graph is a useful and important algorithm as well as a tool in CD for mining and visualizing these chances. However, a scenario graph visualized by Key Graph is machine-oriented, causing a bottleneck of human cognition. Traditional knowledge discovery also runs into the similar problem. In this paper, we propose a human-oriented algorithm called IdeaGraph which can generate a rich scenario graph for human's perception, comprehension and even innovation. IdeaGraph not only works on discovering more rare and significant chances, but also focuses on uncovering latent relationships among chances for gaining richer and deeper human insights. Our experiment has validated the advantages of IdeaGraph by comparing with Key Graph.

In order to obtain complete and correct information for road line extraction from remote sensing image, the complementary of two kinds of line feature is discussed and a feature fusion method is proposed. The method is implemented by cross validating line features of the LSD and the SRM according their spatial relationship. The results of experiments demonstrated the complementary of these two kinds features, and the performance of road extraction with the fused features can be improved obviously than with any single kind of line feature.

We propose a novel dynamic network coding retransmission scheme which can effectively mask packet losses and have a quite low decoding delay. By using network coding, we reduce the retransmission waiting time, and by using the implicit information of seen scheme, we acquire the exact number of packets the receiver needs for decoding packets. As our scheme does not require or estimate the loss rate to send redundancies in a constant rate, it is more practical to be implemented in a real system. Furthermore, we incorporate network coding with a load factor based congestion control algorithm which is easy and efficient to be implemented in practical systems. Simulation results show that our scheme significantly outperforms the previous coding approach in reducing decoding delay without sacrificing throughput. It achieves the near-zero congestion loss and ¿zero¿ error loss in wireless networks, can be easily and effectively implemented in the practical system.

Low Earth orbit (LEO) satellite networks are capable of providing wireless connectivity seamlessly and continuously to any part of the world with guaranteed short round-trip propagation delay. As a key part of next generation network (NGN) infrastructure, next generation satellite networks are expected to support a variety of applications with diverse performance requirements. This paper argues that the constellation tomography for the LEO satellite network is a preliminary step for efficient satellite network monitoring and performance promotion. To measure the constellation, a divide-and-conquer mechanism is developed for each parameter estimation by delay probing. The delay measurement is only carried out between two terminals located at the same geographic positions. Performance evaluation on several popular polar LEO constellations proves the accuracy and efficiency of the developed constellation tomography algorithms in divide-and-conquer manner. The geographic position limitation of the delay probing terminals for valid constellation inference is also analyzed in the paper.

Internet traffic has been proven to be long-tailed and often modeled by lognormal distribution, Weibull or Pareto distributions theoretically. However, these mathematical models hinder us in traffic analysis and evaluation studies due to their complex representations and theoretical properties. This paper proposes a hyper-Erlang model (mixed Erlang distribution) for such a long-tailed network traffic approximation. It fits network traffic with long-tailed characteristic into a mixed Erlang distribution directly to facilitate our further analysis. Compared with the well-known hyperexponential based method, the mixed Erlang model is more accurate in fitting the tail behavior and also computationally efficient. Further investigations on the M/G/1 queueing behavior also prove the efficiency of the mixed Erlang based approximation

Based on evolutionary computation, a novel real-time route planner for unmanned air vehicles is presented. In the evolutionary route planner, the individual candidates are evaluated with respect to the workspace so that the computation of the configuration space is not required. The planner incorporates domain-specific knowledge, can handle unforeseeable changes of the environment, and take into account different kinds of mission constraints such as minimum route leg length and flying altitude, maximum turning angle, and fixed approach vector to goal position. Furthermore, the novel planner can be used to plan routes both for a single vehicle and for multiple ones. With Digital Terrain Elevation Data, the resultant routes can increase the surviving probability of the vehicles using the terrain masking effect.

Collecting network traffic is becoming a more challenging task in passive network measurement due to the rapid growth of link speed. Flow-based network traffic capture and storage is an efficient way for high-speed network measurement. Based on the statistical investigation of the correlations between flow size and the maximum packet interinterval time of consecutive packets within a flow, we obtain the empirical conditional distribution functions for some popular TCP protocol-based application flows, and then propose a probability-guaranteed adaptive timeout algorithm (PGAT) for flow termination decision. The assessment criteria for the flow termination decision algorithm is systematically developed. Comparisons on flow generation ratio, flow intact ratio, and mean flow extra retaining time metrics indicate that the PGAT algorithm can obtain more attractive performance than other schemes.