Multi-stack fuel cell system(MFCS) are an important basis for large-scale application of solid oxide fuel cell(SOFC) technology, MFCS can provide higher system power and longer service life. As the number of stacks in...
详细信息
Sensing 3D objects is critical when 2D object recognition is not accessible. A robot pre-trained on a large point-cloud dataset will encounter unseen classes of 3D objects after deploying it. Therefore, the robot shou...
Sensing 3D objects is critical when 2D object recognition is not accessible. A robot pre-trained on a large point-cloud dataset will encounter unseen classes of 3D objects after deploying it. Therefore, the robot should be able to learn continuously in real-world scenarios. Few-shot class-incremental learning (FSCIL) requires the model to learn from few-shot new examples continually and not forget past classes. However, there is an implicit but strong assumption in the FSCIL that the distribution of the base and incremental classes is the same. In this paper, we focus on cross-domain FSCIL for point-cloud recognition. We decompose the catastrophic forgetting into base class forgetting and incremental class forgetting and alleviate them separately. We utilize the base model to discriminate base samples and new samples by treating base samples as in-distribution samples, and new objects as out-of-distribution samples. We retain the base model to avoid catastrophic forgetting of base classes and train an extra domain-specific module for all new samples to adapt to new classes. At inference, we first discriminate whether the sample belongs to the base class or the new class. Once classified at the model level, test samples are then passed to the corresponding model for class-level classification. To better mitigate the forgetting of new classes, we adopt the soft label and hard label replay together. Extensive experiments on synthetic-to-real incremental 3D datasets show that our proposed method can balance the performance between the base and new objects and outperforms the previous state-of-the-art methods.
There is a long-standing problem of repeated patterns in correspondence problems, where mismatches frequently occur because of inherent ambiguity. The unique position information associated with repeated patterns make...
详细信息
There is a long-standing problem of repeated patterns in correspondence problems, where mismatches frequently occur because of inherent ambiguity. The unique position information associated with repeated patterns makes coordinate representations a useful supplement to appearance representations for improving feature correspondences. However, the issue of appropriate coordinate representation has remained unresolved. In this study, we demonstrate that geometric-invariant coordinate representations, such as barycentric coordinates, can significantly reduce mismatches between features. The first step is to establish a theoretical foundation for geometrically invariant coordinates. We present a seed matching and filtering network (SMFNet) that combines feature matching and consistency filtering with a coarse-to-fine matching strategy in order to acquire reliable sparse correspondences. We then introduce Degree, a novel anchor-to-barycentric (A2B) coordinate encoding approach, which generates multiple affine-invariant correspondence coordinates from paired images. Degree can be used as a plug-in with standard descriptors, feature matchers, and consistency filters to improve the matching quality. Extensive experiments in synthesized indoor and outdoor datasets demonstrate that Degree alleviates the problem of repeated patterns and helps achieve state-of-the-art performance. Furthermore, Degree also reports competitive performance in the third image Matching Challenge at CVPR 2021. This approach offers a new perspective to alleviate the problem of repeated patterns and emphasizes the importance of choosing coordinate representations for feature correspondences.
The complexity of coupled risks,which refer to the compounded effects of interacting uncertainties across multiple interdependent objectives,is inherent to cities functioning as dynamic,interdependent systems.A disrup...
详细信息
The complexity of coupled risks,which refer to the compounded effects of interacting uncertainties across multiple interdependent objectives,is inherent to cities functioning as dynamic,interdependent systems.A disruption in one domain ripples across various urban systems,often with unforeseen *** to this complexity are people,whose behaviors,needs,and vulnerabilities shape risk evolution and response *** cities as complex systems centered on human needs and behaviors is essential to understanding the complexities of coupled urban *** paper adopts a complex systems perspective to examine the intricacies of coupled urban risks,emphasizing the critical role of human decisions and behavior in shaping these *** focus on two key dimensions:cascading hazards in urban environments and cascading failures across interdependent exposed systems in *** risk assessment models often fail to capture the complexity of these processes,particularly when factoring in human *** tackle these challenges,we advocate for a standardized taxonomy of cascading hazards,urban components,and their *** its core is a people-centric perspective,emphasizing the bidirectional interactions between people and the systems that serve *** on this foundation,we argue the need for an integrated,people-centric risk assessment framework that evaluates event impacts in relation to the hierarchical needs of people and incorporates their preparedness and response *** leveraging real-time data,advanced simula-tions,and innovative validation methods,this framework aims to enhance the accuracy of coupled urban risk *** effectively manage coupled urban risks,cities can draw from proven strategies in real complex ***,given the escalating uncertainties and complexities associated with climate change,prioritizing people-centric strategies is *** approach will empower cities to bui
Due to the popularization of distributed generators (DGs) and diversity of loads, hybrid microgrid, mixing AC/DC subgrids, has gradually become a popular research topic. However, there is lack of research results to a...
详细信息
Due to the popularization of distributed generators (DGs) and diversity of loads, hybrid microgrid, mixing AC/DC subgrids, has gradually become a popular research topic. However, there is lack of research results to achieve the control objectives of precise AC/DC bus voltage/frequency restoration and global power sharing among DGs in hybrid microgrid within a predefined time. In this article, a distributed predefined-time controller (DPTC) is designed to achieve the above objectives with unknown load power by employing a classK1 function and defining a unified error. The convergence time of bus voltage and output power of converters can be adjusted by a predefined parameter. Moreover, a distributed predefined-time observer is proposed to rely less on direct load measurements and guarantee the controller implementation in emergencies when load information is unavailable. Through hardwarein-the-loop experiment tests, the effectiveness of the DPTC is verified in scenarios of load change and plug-and-play. Comparative experiment indicates that the proposed controller has the potential for convenient adjustment of convergence time and the advantage of small overshoot.
The early and effective diagnosis of Alzheimer's disease (AD) and mild cognitive impairment (MCI) has received increasing attention in recent years. However, currently available deep learning methods often ignore ...
详细信息
The early and effective diagnosis of Alzheimer's disease (AD) and mild cognitive impairment (MCI) has received increasing attention in recent years. However, currently available deep learning methods often ignore the contextual spatial information contained in structural MRI images used for early diagnosis and classification of Alzheimer's disease. This may lead us to miss important structural details by failing to adequately capture the potential connections between each slice and its neighboring slices. This lack of contextual information may cause the accuracy of the network model to suffer, which in turn affects its generalization ability and application in real-life scenarios. To explore deeper the connection between spatial context slices, this research is designed to develop a new network model to effectively detect or predict AD by digging into the deeper spatial contextual structural information. In this paper, we design a spatial context network based on 3D convolutional neural network to learn the multi-level structural features of brain MRI images for AD classification. The experimental results show that the model has good stability, accuracy and generalization ability. Our experimental method had a classification accuracy of 92.6% in the AD/CN comparison, 74.9% in the AD/MCI comparison, and 76.3% in the MCI/CN comparison. In addition, this paper demonstrates the effectiveness of the proposed network model through ablation experiments.
Dynamic regulation of DNA origami nanostructures is important for the fabrication of intelligent DNA nanodevices. Toehold-mediated strand displacement is a common regulation strategy, which utilizes trigger strands to...
详细信息
Dynamic regulation of DNA origami nanostructures is important for the fabrication of intelligent DNA nanodevices. Toehold-mediated strand displacement is a common regulation strategy, which utilizes trigger strands to assemble and disassemble nanostructures. Such trigger strands are required to be completely complementary to the corresponding substrate strands, which strictly demands orthogonality and accuracy of the sequence design. Herein, we present a disassembly strategy of DNA origami dimers based on polymerase-triggered strand displacement, where the polymerase primers, as the trigger strands, were only partially complementary to the toehold region of the substrate strands. To demonstrate the programmability of trigger strands, we utilized primers with different sequence combination patterns to disassemble DNA origami dimers. The statistical summary of AFM images and fluorescence curves proved the feasibility of the new strategy. The utilization of polymerase-triggered strand displacement on the disassembly of DNA origami structures enriches the toolbox for the dynamic regulation of DNA nanostructures.
Transient stability is an important metric for assessing the operational state of a power system. However, due to the inherent complexity of the power systems, it is difficult to achieve stable and precise transient s...
详细信息
Transient stability is an important metric for assessing the operational state of a power system. However, due to the inherent complexity of the power systems, it is difficult to achieve stable and precise transient stability assessment (TSA). This article proposes a novel data-driven long short-term memory with self-attention mechanism and focal loss function (LSTM-SAF) model to achieve a rapid and reliable TSA scheme. First, an improved wrapper approach involving a genetic algorithm is established to obtain concise and effective input features, which can enhance model performance and efficiency. Then, an LSTM network combined with a self-attention mechanism is developed to learn reliable TSA paradigms, in which the self-attention mechanism can further explore the information relationships of temporal features extracted from the LSTM, thereby significantly improving TSA accuracy. In addition, to resolve the lack of insufficient training related to sample imbalance, a new focal loss function is designed to guide model training. This article provides a complete TSA scheme (including offline training and online execution) that considers both assessment performance and response speed. The effectiveness of the proposed model is verified by the numerical testing results on IEEE 39 bus system, NPCC 140 bus system, IEEE 145 bus system and IEEE 300 bus system.
Current state-of-the-art approaches for few-shot action recognition achieve promising performance by conducting frame-level matching on learned visual features. However, they generally suffer from two limitations: i) ...
详细信息
ISBN:
(纸本)9798350301298
Current state-of-the-art approaches for few-shot action recognition achieve promising performance by conducting frame-level matching on learned visual features. However, they generally suffer from two limitations: i) the matching procedure between local frames tends to be inaccurate due to the lack of guidance to force long-range temporal perception;ii) explicit motion learning is usually ignored, leading to partial information loss. To address these issues, we develop a Motion-augmented Long-short Contrastive Learning (MoLo) method that contains two crucial components, including a long-short contrastive objective and a motion autodecoder. Specifically, the long-short contrastive objective is to endow local frame features with long-form temporal awareness by maximizing their agreement with the global token of videos belonging to the same class. The motion autodecoder is a lightweight architecture to reconstruct pixel motions from the differential features, which explicitly embeds the network with motion dynamics. By this means, MoLo can simultaneously learn long-range temporal context and motion cues for comprehensive few-shot matching. To demonstrate the effectiveness, we evaluate MoLo on five standard benchmarks, and the results show that MoLo favorably outperforms recent advanced methods. The source code is available at https://***/alibaba-mmai-research/MoLo.
image matting aims to estimate the opacity of foreground objects in order to accurately extract them from the background. Existing methods are only concerned with RGB features to obtain alpha mattes, limiting the perc...
详细信息
暂无评论