Uncertain Regions Research Articles

Decentralized Multi-Agent Search for Moving Targets Using Road Network Gaussian Process Regressions

Unmanned aerial vehicles (UAVs) can collaborate as teams to accomplish diverse mission objectives, such as target search and tracking. This paper introduces a method that leverages accumulated target-density information over the course of a UAV mission to adapt path-planning rewards, guiding UAVs toward areas with a higher likelihood of target presence. The target density is modeled using a Gaussian process, which is iteratively updated as the UAVs search the environment. Unlike conventional search algorithms that prioritize unexplored regions, this approach incentivizes revisiting target-rich areas. The target-density information is shared across UAVs using decentralized consensus filters, enabling cooperative path selection that balances the exploration of uncertain regions with the exploitation of known high-density areas. The framework presented in this paper provides an adaptive cooperative search method that can quickly develop an understanding of the region’s target-dense areas, helping UAVs refine their search. Through Monte Carlo simulations, we demonstrate this method in both a 2D grid region and road networks, showing up to a 26% improvement in target density estimates.

Some Methods for Indicating Cartographic Uncertainty, Fifteenth through Eighteenth Centuries

We have a strong tendency to trust maps as accurate depictions of the world, and most early modern cartographers are content to enjoy that prima facie trust without raising questions about the trustworthiness of their sources. In this article I will examine several methods that cartographers used from the fifteenth to the eighteenth centuries of departing from this convention, and indicating to their viewers in a forthright manner which parts of their map they were certain about, and which they were uncertain about. Some of these methods include listing sites about whose location the cartographer is uncertain, using a different graphic style to depict unknown coastlines, using signs to distinguish between certain and uncertain regions, and surrendering to uncertainty and reprinting varying maps of the same region together. Determining what earlier scholars did not know, and how they dealt with that lack of knowledge, is an essential step in producing the history of knowledge.

Framework to process vehicles uncertain locations for intelligent transportation

Many factors affect the precision and accuracy of location data. These factors include, but not limited to, environmental obstructions (e.g., high buildings and forests), hardware issues (e.g., malfunctioning and poor calibration), and privacy concerns (e.g., users denying consent to fine-grained location tracking). These factors lead to uncertainty about users’ location which in turn affects the quality of location-aware services. This paper proposes a novel framework called UMove, which stands for uncertain movements, to manage the trajectory of moving objects under location uncertainty. The UMove framework employs the connectivity (i.e., links between edges) and constraints (i.e., travel time and distance) on road network graphs to reduce the uncertainty of the object’s past, present, and projected locations. To accomplish this, UMove incorporates (i) a set-based pruning algorithm to reduce or eliminate uncertainty from imprecise trajectories; and (ii) a wrapper that can extend user-defined probability models designed to predict future locations of moving objects under uncertainty. Intensive experimental evaluations based on real data sets of GPS trajectories collected by Didi Chuxing in China prove the efficiency of the proposed UMove framework. In terms of accuracy, for past exact-location inference, UMove achieves rates from 88% to 97% for uncertain regions with sizes of 75 meters and 25 meters respectively; for future exact-location inference, accuracy rates reach up to 72% and 82% for 75 meters and 25 meters of uncertain regions.

Pollution area identification, receptor model-oriented sources and probabilistic health hazards to prioritize control measures for heavy metal management in soil

Identifying the primary source of heavy metals (HMs) pollution and the key pollutants is crucial for safeguarding eco-health and managing risks in industrial vicinity. For this purpose, this investigation was carried out to investigate the pollution area identification with soil static environmental capacity (QI), receptor model-oriented critical sources, and Monte Carlo simulation (MCS) based probabilistic environmental and human health hazards associated with HMs in agricultural soils of Narayanganj, Bangladesh. The average concentration of Cr, Ni, Cu, Cd, Pb, Co, Zn, and Mn were 98.67, 63.41, 37.39, 1.28, 23.93, 14.48, 125.08, and 467.45 mg/kg, respectively. The geoaccumulation index identified Cd as the dominant metal, indicating heavy to extreme contamination in soils. The QI revealed that over 99% of the areas were polluted for Ni and Cd with less uncertain regions whereas Cr showed a significant portion of areas with uncertain pollution status. The positive matrix factorization (PMF) model identified three major sources: agricultural (29%), vehicular emissions (25%), and industrial (46%). The probabilistic assessment of health hazards indicated that both carcinogenic and non-carcinogenic risks for adult male, adult female, and children were deemed unacceptable. Moreover, children faced a higher health hazard compared to adults. For adult male, adult female, and children, industrial operations contributed 48.4%, 42.7%, and 71.2% of the carcinogenic risks, respectively and these risks were associated with Ni and Cr as the main pollutants of concern. The study emphasizes valuable scientific insights for environmental managers to tackle soil pollution from HMs by effectively managing anthropogenic sources. It could aid in devising strategies for environmental remediation engineering and refining industry standards.

Learning a reactive potential for silica-water through uncertainty attribution

The reactivity of silicates in aqueous solution is relevant to various chemistries ranging from silicate minerals in geology, to the C-S-H phase in cement, nanoporous zeolite catalysts, or highly porous precipitated silica. While simulations of chemical reactions can provide insight at the molecular level, balancing accuracy and scale in reactive simulations in the condensed phase is a challenge. Here, we demonstrate how a machine-learning reactive interatomic potential trained on PaiNN architecture can accurately capture silicate-water reactivity. The model was trained on a dataset comprising 400,000 energies and forces of molecular clusters at the ωB97X-D3/def2-TZVP level. To ensure the robustness of the model, we introduce a general active learning strategy based on the attribution of the model uncertainty, that automatically isolates uncertain regions of bulk simulations to be calculated as small-sized clusters. The potential reproduces static and dynamic properties of liquid water and solid crystalline silicates, despite having been trained exclusively on cluster data. Furthermore, we utilize enhanced sampling simulations to recover the self-ionization reactivity of water accurately, and the acidity of silicate oligomers, and lastly study the silicate dimerization reaction in a water solution at neutral conditions and find that the reaction occurs through a flanking mechanism.

UDBRNet: A novel uncertainty driven boundary refined network for organ at risk segmentation.

Organ segmentation has become a preliminary task for computer-aided intervention, diagnosis, radiation therapy, and critical robotic surgery. Automatic organ segmentation from medical images is a challenging task due to the inconsistent shape and size of different organs. Besides this, low contrast at the edges of organs due to similar types of tissue confuses the network's ability to segment the contour of organs properly. In this paper, we propose a novel convolution neural network based uncertainty-driven boundary-refined segmentation network (UDBRNet) that segments the organs from CT images. The CT images are segmented first and produce multiple segmentation masks from multi-line segmentation decoder. Uncertain regions are identified from multiple masks and the boundaries of the organs are refined based on uncertainty data. Our method achieves remarkable performance, boasting dice accuracies of 0.80, 0.95, 0.92, and 0.94 for Esophagus, Heart, Trachea, and Aorta respectively on the SegThor dataset, and 0.71, 0.89, 0.85, 0.97, and 0.97 for Esophagus, Spinal Cord, Heart, Left-Lung, and Right-Lung respectively on the LCTSC dataset. These results demonstrate the superiority of our uncertainty-driven boundary refinement technique over state-of-the-art segmentation networks such as UNet, Attention UNet, FC-denseNet, BASNet, UNet++, R2UNet, TransUNet, and DS-TransUNet. UDBRNet presents a promising network for more precise organ segmentation, particularly in challenging, uncertain conditions. The source code of our proposed method will be available at https://github.com/riadhassan/UDBRNet.

CTFNet: Coarse-to-Fine Segmented Lane Line Detection in Complex Road Conditions

To maintain robustness in complex and uncontrollable real-world driving scenarios, this paper proposes a new segmentation-based coarse-to-fine lane line model (CTFNet). Which embeds dual-pathway attention (DPA) in the coarse segmentation encoder-decoder architecture to fuse high and low-level features with dual inputs, taking the strengths and complementing the weaknesses, and at the same time being able to capture more spatial detail information. However, the extracted lane line cues are limited in extreme conditions. As a result, a feature localization module (FLM) is proposed which extracts the global contextual information of the occluded region along the vertical and horizontal axes and determines lane line location by predicting the confidence of the lane lines based on the extracted information. Additionally, some regions of the initial feature map of the coarse segmentation network are difficult to distinguish between classes, the uncertain region refinement module (URRM) is designed in the fine stage to gradually refine the uncertain pixels using the relationship between adjacent features. Finally, the model is extensively tested on the tvtLANE data set, and the results show that CTFNet outperforms most state-of-the-art methods with an F1-measure of 91.48%, which not only reduces false detection but also maintains good robustness in extremely difficult scenarios.

Accelerating high-entropy alloy discovery: efficient exploration via active learning

The exploration of the complex composition space for high entropy alloys (HEAs) is extremely challenging and resource intensive using traditional materials discovery approaches. Here, we apply Bayesian optimization in the form of active learning with a neural network model to efficiently explore the vast composition space of HEAs with a focus on predicting their stable phases. For example, by focusing data acquisition on the uncertain regions, we achieved a testing accuracy of 95% with 27% of an experimental HEA dataset, comparable to the accuracy (94.6%) of a random forest model trained with 80% of the full dataset (2198 quinary HEAs). Similarly, with just ∼2% of a CALPHAD dataset we achieved a testing accuracy for phase predictions above 96%, which is comparable to the accuracy (above 97%) achieved when an XGboost model is trained with nearly the full dataset (664,650 quinary HEAs). Thus, our approach greatly facilitates both computational and experimental exploration of HEA design spaces.

Lung Nodule Segmentation and Uncertain Region Prediction With an Uncertainty-Aware Attention Mechanism.

Radiologists possess diverse training and clinical experiences, leading to variations in the segmentation annotations of lung nodules and resulting in segmentation uncertainty. Conventional methods typically select a single annotation as the learning target or attempt to learn a latent space comprising multiple annotations. However, these approaches fail to leverage the valuable information inherent in the consensus and disagreements among the multiple annotations. In this paper, we propose an Uncertainty-Aware Attention Mechanism (UAAM) that utilizes consensus and disagreements among multiple annotations to facilitate better segmentation. To this end, we introduce the Multi-Confidence Mask (MCM), which combines a Low-Confidence (LC) Mask and a High-Confidence (HC) Mask. The LC mask indicates regions with low segmentation confidence, where radiologists may have different segmentation choices. Following UAAM, we further design an Uncertainty-Guide Multi-Confidence Segmentation Network (UGMCS-Net), which contains three modules: a Feature Extracting Module that captures a general feature of a lung nodule, an Uncertainty-Aware Module that produces three features for the annotations' union, intersection, and annotation set, and an Intersection-Union Constraining Module that uses distances between the three features to balance the predictions of final segmentation and MCM. To comprehensively demonstrate the performance of our method, we propose a Complex-Nodule Validation on LIDC-IDRI, which tests UGMCS-Net's segmentation performance on lung nodules that are difficult to segment using common methods. Experimental results demonstrate that our method can significantly improve the segmentation performance on nodules that are difficult to segment using conventional methods.

Polyp segmentation with interference filtering and dynamic uncertainty mining.

Objective.Accurate polyp segmentation from colo-noscopy images plays a crucial role in the early diagnosis and treatment of colorectal cancer. However, existing polyp segmentation methods are inevitably affected by various image noises, such as reflections, motion blur, and feces, which significantly affect the performance and generalization of the model. In addition, coupled with ambiguous boundaries between polyps and surrounding tissue, i.e. small inter-class differences, accurate polyp segmentation remains a challenging problem.Approach.To address these issues, we propose a novel two-stage polyp segmentation method that leverages a preprocessing sub-network (Pre-Net) and a dynamic uncertainty mining network (DUMNet) to improve the accuracy of polyp segmentation. Pre-Net identifies and filters out interference regions before feeding the colonoscopy images to the polyp segmentation network DUMNet. Considering the confusing polyp boundaries, DUMNet employs the uncertainty mining module (UMM) to dynamically focus on foreground, background, and uncertain regions based on different pixel confidences. UMM helps to mine and enhance more detailed context, leading to coarse-to-fine polyp segmentation and precise localization of polyp regions.Main results.We conduct experiments on five popular polyp segmentation benchmarks: ETIS, CVC-ClinicDB, CVC-ColonDB, EndoScene, and Kvasir. Our method achieves state-of-the-art performance. Furthermore, the proposed Pre-Net has strong portability and can improve the accuracy of existing polyp segmentation models.Significance.The proposed method improves polyp segmentation performance by eliminating interference and mining uncertain regions. This aids doctors in making precise and reduces the risk of colorectal cancer. Our code will be released athttps://github.com/zyh5119232/DUMNet.

Progressive Feature Self-Reinforcement for Weakly Supervised Semantic Segmentation

Compared to conventional semantic segmentation with pixel-level supervision, weakly supervised semantic segmentation (WSSS) with image-level labels poses the challenge that it commonly focuses on the most discriminative regions, resulting in a disparity between weakly and fully supervision scenarios. A typical manifestation is the diminished precision on object boundaries, leading to deteriorated accuracy of WSSS. To alleviate this issue, we propose to adaptively partition the image content into certain regions (e.g., confident foreground and background) and uncertain regions (e.g., object boundaries and misclassified categories) for separate processing. For uncertain cues, we propose an adaptive masking strategy and seek to recover the local information with self-distilled knowledge. We further assume that confident regions should be robust enough to preserve the global semantics, and introduce a complementary self-distillation method that constrains semantic consistency between confident regions and an augmented view with the same class labels. Extensive experiments conducted on PASCAL VOC 2012 and MS COCO 2014 demonstrate that our proposed single-stage approach for WSSS not only outperforms state-of-the-art counterparts but also surpasses multi-stage methods that trade complexity for accuracy.

One at a Time: Progressive Multi-Step Volumetric Probability Learning for Reliable 3D Scene Perception

Numerous studies have investigated the pivotal role of reliable 3D volume representation in scene perception tasks, such as multi-view stereo (MVS) and semantic scene completion (SSC). They typically construct 3D probability volumes directly with geometric correspondence, attempting to fully address the scene perception tasks in a single forward pass. However, such a single-step solution makes it hard to learn accurate and convincing volumetric probability, especially in challenging regions like unexpected occlusions and complicated light reflections. Therefore, this paper proposes to decompose the complicated 3D volume representation learning into a sequence of generative steps to facilitate fine and reliable scene perception. Considering the recent advances achieved by strong generative diffusion models, we introduce a multi-step learning framework, dubbed as VPD, dedicated to progressively refining the Volumetric Probability in a Diffusion process. Specifically, we first build a coarse probability volume from input images with the off-the-shelf scene perception baselines, which is then conditioned as the basic geometry prior before being fed into a 3D diffusion UNet, to progressively achieve accurate probability distribution modeling. To handle the corner cases in challenging areas, a Confidence-Aware Contextual Collaboration (CACC) module is developed to correct the uncertain regions for reliable volumetric learning based on multi-scale contextual contents. Moreover, an Online Filtering (OF) strategy is designed to maintain representation consistency for stable diffusion sampling. Extensive experiments are conducted on scene perception tasks including multi-view stereo (MVS) and semantic scene completion (SSC), to validate the efficacy of our method in learning reliable volumetric representations. Notably, for the SSC task, our work stands out as the first to surpass LiDAR-based methods on the SemanticKITTI dataset.

Enhancing the Design of Experiments on the Fatigue Life Characterisation of Fibre-Reinforced Plastics by Incorporating Artificial Neural Networks.

Fatigue life testing is a complex and costly matter, especially in the case of fibre-reinforced thermoplastics, where other parameters in addition to force alone must be taken into account. The number of tests required therefore increases significantly, especially if the influence of different fibre orientations is to be taken into account. It is therefore important to gain the greatest possible amount of knowledge from the limited number of available tests. In order to achieve this, this study aims to utilise adaptive sampling, which is used in numerous areas of computational engineering, for the design of experiments on fatigue life testing. Artificial neural networks (ANNs) are therefore trained on data for the short-fibre-reinforced material PBT GF30, and their areas of greatest model uncertainty are queried. This was undertaken with ANNs from various numbers of hidden layers, which were analysed for their performance. The ideal case turned out to be four hidden layers, for which a squared error as small as 1 × 10-3 was recorded. Locally resolved, the ANN was used to identify the region of greatest uncertainty for samples of vertical orientation and small numbers of cycles. With information such as this, additional data can be obtained in such uncertain regions in order to improve the model prediction-almost halving the recorded error to only 0.55 × 10-3. In this way, a model of comparable value can be found with less experimental effort, or a model of better quality can be set up with the same experimental effort.

Reliable Model Predictive Vibration Control for Structures with Nonprobabilistic Uncertainties

This paper proposes a novel reliable model predictive control (MPC) method for active vibration control of structure with nonprobabilistic uncertainties. First, the framework of reliable MPC is established by integrating nonprobabilistic reliability constraints into nominal MPC. Based on the first‐order Taylor expansion and first‐passage theory, an efficient nonprobabilistic reliability analysis method that is suitable for online computation is proposed. A nonprobabilistic Kalman filter is further proposed for determine system states and their uncertain region. Unlike most robust MPC approaches, the proposed reliable MPC focuses on the satisfaction of state constraints in terms of structural reliability and is more suitable for structures with stringent safety requirements. Compared to existing reliability‐based vibration control methods, reliable MPC requires no knowledge of disturbance and exhibits greater adaptability to load environments. The effectiveness and superiority of the proposed reliable MPC are validated through a numerical example and an engineering case study.

ProbIBR: Fast Image-Based Rendering with Learned Probability-Guided Sampling.

We present a general, fast, and practical solution for interpolating novel views of diverse real-world scenes given a sparse set of nearby views. Existing generic novel view synthesis methods rely on time-consuming scene geometry pre-computation or redundant sampling of the entire space for neural volumetric rendering, limiting the overall efficiency. Instead, we incorporate learned MVS priors into the neural volume rendering pipeline while improving the rendering efficiency by reducing sampling points under the guidance of depth probability distributions. Specifically, fewer but important points are sampled under the guidance of depth probability distributions extracted from the learned MVS architecture. Based on the learned probability-guided sampling, we develop a sophisticated neural volume rendering module that effectively integrates source view information with the learned scene structures. We further propose confidence-aware refinement to improve the rendering results in uncertain, occluded, and unreferenced regions. Moreover, we build a four-view camera system for holographic display and provide a real-time version of our framework for free-viewpoint experience, where novel view images of a spatial resolution of 512×512 can be rendered at around 20 fps on a single GTX 3090 GPU. Experiments show that our method achieves 15 to 40 times faster rendering compared to state-of-the-art baselines, with strong generalization capacity and comparable high-quality novel view synthesis performance.

Uncertain region mining semi-supervised object detection

Uncertain region mining semi-supervised object detection

Active learning algorithm through the lens of rejection arguments

Active learning is a paradigm of machine learning which aims at reducing the amount of labeled data needed to train a classifier. Its overall principle is to sequentially select the most informative data points, which amounts to determining the uncertainty of regions of the input space. The main challenge lies in building a procedure that is computationally efficient and that offers appealing theoretical properties; most of the current methods satisfy only one or the other. In this paper, we use the classification with rejection in a novel way to estimate the uncertain regions. We provide an active learning algorithm and prove its theoretical benefits under classical assumptions. In addition to the theoretical results, numerical experiments are carried out on synthetic and non-synthetic datasets. These experiments provide empirical evidence that the use of rejection arguments in our active learning algorithm is beneficial and allows good performance in various statistical situations.

Domain Adaptive Object Detection via Balancing between Self-Training and Adversarial Learning.

Deep learning based object detectors struggle generalizing to a new target domain bearing significant variations in object and background. Most current methods align domains by using image or instance-level adversarial feature alignment. This often suffers due to unwanted background and lacks class-specific alignment. A straightforward approach to promote class-level alignment is to use high confidence predictions on unlabeled domain as pseudo-labels. These predictions are often noisy since model is poorly calibrated under domain shift. In this paper, we propose to leverage model's predictive uncertainty to strike the right balance between adversarial feature alignment and class-level alignment. We develop a technique to quantify predictive uncertainty on class assignments and bounding-box predictions. Model predictions with low uncertainty are used to generate pseudo-labels for self-training, whereas the ones with higher uncertainty are used to generate tiles for adversarial feature alignment. This synergy between tiling around uncertain object regions and generating pseudo-labels from highly certain object regions allows capturing both image and instance-level context during the model adaptation. We report thorough ablation study to reveal the impact of different components in our approach. Results on five diverse and challenging adaptation scenarios show that our approach outperforms existing state-of-the-art methods with noticeable margins.

Weakly Supervised Semantic Segmentation via Box-driven Masking and Filling Rate Shifting.

Semantic segmentation has achieved huge progress via adopting deep Fully Convolutional Networks (FCN). However, the performance of FCN-based models severely rely on the amounts of pixel-level annotations which are expensive and time-consuming. Considering that bounding boxes also contain abundant semantic and objective information, an intuitive solution is to learn the segmentation with weak supervisions from the bounding boxes. How to make full use of the class-level and region-level supervisions from bounding boxes to estimate the uncertain regions is the critical challenge for the weakly supervised learning task. In this paper, we propose a mixture model to address this problem. First, we introduce a box-driven class-wise masking model (BCM) to remove irrelevant regions of each class. Moreover, based on the pixel-level segment proposal generated from the bounding box supervision, we calculate the mean filling rates of each class to serve as an important prior cue to guide the model ignoring the wrongly labeled pixels in proposals. To realize the more fine-grained supervision at instance-level, we further propose the anchor-based filling rate shifting module. Unlike previous methods that directly train models with the generated noisy proposals, our method can adjust the model learning dynamically with the adaptive segmentation loss. Thus it can help reduce the negative impacts from wrongly labeled proposals. Besides, based on the learned high-quality proposals with above pipeline, we explore to further boost the performance through two-stage learning. The proposed method is evaluated on the challenging PASCAL VOC 2012 benchmark and achieves 74.9% and 76.4% mean IoU accuracy under weakly and semi-supervised modes, respectively. Extensive experimental results show that the proposed method is effective and is on par with, or even better than current state-of-the-art methods. Code will be available at: https://github.com/developfeng/BCM.

Uncertainty-aware refinement framework for ovarian tumor segmentation in CECT volume.

Ovarian cancer is a highly lethal gynecological disease. Accurate and automated segmentation of ovarian tumors in contrast-enhanced computed tomography (CECT) images is crucial in the radiotherapy treatment of ovarian cancer, enabling radiologists to evaluate cancer progression and develop timely therapeutic plans. However, automatic ovarian tumor segmentation is challenging due to factors such as inhomogeneous background, ambiguous tumor boundaries, and imbalanced foreground-background, all of which contribute to high predictive uncertainty for a segmentationmodel. To tackle these challenges, we propose an uncertainty-aware refinement framework that aims to estimate and refine regions with high predictive uncertainty for accurate ovarian tumor segmentation in CECTimages. To this end, we first employ an approximate Bayesian network to detect coarse regions of interest (ROIs) of both ovarian tumors and uncertain regions. These ROIs allow a subsequent segmentation network to narrow down the search area for tumors and prioritize uncertain regions, resulting in precise segmentation of ovarian tumors. Meanwhile, the framework integrates two guidance modules that learn two implicit functions capable of mapping query features sampled according to their uncertainty to organ or boundary manifolds, guiding the segmentation network to facilitate information encoding of uncertainregions. Firstly, 367 CECT images are collected from the same hospital for experiments. Dice score, Jaccard, Recall, Positive predictive value (PPV), 95% Hausdorff distance (HD95) and Average symmetric surface distance (ASSD) for the testing group of 77 cases are 86.31%, 73.93%, 83.95%, 86.03%, 15.17 mm and 2.57 mm, all of which are significantly better than that of the other state-of-the-art models. And results of visual comparison shows that the compared methods have more mis-segmentation than our method. Furthermore, our method achieves a Dice score that is at least 20% higher than the Dice scores of other compared methods when tumor volumes are less than 20 cm , indicating better recognition ability to small regions by our method. And then, 38 CECT images are collected from another hospital to form an external testing group. Our approach consistently outperform the compared methods significantly, with the external testing group exhibiting substantial improvements across key evaluation metrics: Dice score (83.74%), Jaccard (69.55%), Recall (82.12%), PPV (81.61%), HD95 (12.31mm), and ASSD (2.32mm), robustly establishing its superiorperformance. Experimental results demonstrate that the framework significantly outperforms the compared state-of-the-art methods, with decreased under- or over-segmentation and better small tumor identification. It has the potential for clinicalapplication.