检索结果-内蒙古大学图书馆

SSRN 2025年

作者： Chen, Zhengshi He, Juanjuan Liu, Xiaoming Tang, Jinshan College of Computer Science and Technology Wuhan University of Science and Technology Wuhan China Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan China Health Informatics Department of Health Administration Policy George Mason University FairfaxVA22030 United States

Precise medical image segmentation is crucial in clinical diagnosis and pathological analysis. Most segmentation methods are based on U-shaped convolutional neural networks (U-Net). Although U-Net performs well in medical image segmentation, as a method based on CNN, its main drawback lies in the difficulty of establishing long-range pixels dependencies and has a constrained receptive field, which restricts segmentation accuracy. Many models address this issue by incorporating Transformer models into U-Net architectures to better capture long-range dependencies. However, these methods often suffer from simple feature fusion techniques and limited receptive fields for local features. To address these challenges, we propose a dual-encoder framework, named MDCT-Unet, which combines Swin-Transformer and CNN for enhanced medical image segmentation. This framework introduces a novel dynamic feature fusion module to better integrate of local and global features. By combining channel and spatial attention mechanisms and inducing competition between them, we enhance the coupling of these two types of features, ensuring richer information representation. Moreover, we supplement the fused features into the decoder via skip connections to recover details lost during encoding. In addition, to better extract multi-scale local features from images, we design a dilated convolution encoder (DCE) as the CNN branch of our model. We conducted extensive experiments on four datasets: Synapse, ISIC2018, CHASEDB1, and MMWHS. The experimental results show that our method outperforms most current medical image segmentation methods © 2025, The Authors. All rights reserved.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Continual Test-Time Adaptation for Single Image Defocus Deblurring via Causal Siamese Networks

arXiv

引用

arXiv 2025年

作者： Cui, Shuang Li, Yi Li, Jiangmeng Tang, Xiongxin Su, Bing Xu, Fanjiang Xiong, Hui National Key Laboratory of Space Integrated Information System Institute of Software Chinese Academy of Sciences University of Chinese Academy of Sciences China Beijing Key Laboratory of Big Data Management and Analysis Methods Gaoling School of Artificial Intelligence Renmin University of China China Department of Computer Science & Engineering the Hong Kong University of Science and Technology Hong Kong

Single image defocus deblurring (SIDD) aims to restore an all-in-focus image from a defocused one. Distribution shifts in defocused images generally lead to performance degradation of existing methods during out-of-distribution inferences. In this work, we gauge the intrinsic reason behind the performance degradation, which is identified as the heterogeneity of lens-specific point spread functions. Empirical evidence supports this finding, motivating us to employ a continual test-time adaptation (CTTA) paradigm for SIDD. However, traditional CTTA methods, which primarily rely on entropy minimization, cannot sufficiently explore task-dependent information for pixel-level regression tasks like SIDD. To address this issue, we propose a novel Siamese networks-based continual test-time adaptation framework, which adapts source models to continuously changing target domains only requiring unlabeled target data in an online manner. To further mitigate semantically erroneous textures introduced by source SIDD models under severe degradation, we revisit the learning paradigm through a structural causal model and propose Causal Siamese networks (CauSiam). Our method leverages large-scale pre-trained vision-language models to derive discriminative universal semantic priors and integrates these priors into Siamese networks, ensuring causal identifiability between blurry inputs and restored images. Extensive experiments demonstrate that CauSiam effectively improves the generalization performance of existing SIDD methods in continuously changing domains. Copyright © 2025, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

TRNet: Two-Tier Recursion Network for Co-Salient Object Detection

引用

IEEE Transactions on Circuits and systems for Video technology 2025年

作者： Cong, Runmin Yang, Ning Liu, Hongyu Zhang, Dingwen Huang, Qingming Kwong, Sam Zhang, Wei Shandong University School of Control Science and Engineering Jinan250061 China Ministry of Education Key Laboratory of Machine Intelligence and System Control Jinan250061 China Beijing Jiaotong University Institute of Information Science Beijing100044 China Beijing Key Laboratory of Advanced Information Science and Network Technology Beijing100044 China Northwestern Polytechnical University Brain and Artificial Intelligence Laboratory School of Automation Xi'an710129 China University of Chinese Academy of Sciences School of Computer Science and Technology Beijing101408 China Lingnan University Hong Kong

Co-salient object detection (CoSOD) is to find the salient and recurring objects from a series of relevant images, where modeling inter-image relationships plays a crucial role. Different from the commonly used direct learning structure that inputs all the intra-image features into some well-designed modules to represent the inter-image relationship, we resort to adopting a recursive structure for inter-image modeling, and propose a two-tier recursion network (TRNet) to achieve CoSOD in this paper. The two-tier recursive structure of the proposed TRNet is embodied in two stages of inter-image extraction and distribution. On the one hand, considering the task adaptability and inter-image correlation, we design an inter-image exploration with recursive reinforcement module to learn the local and global inter-image correspondences, guaranteeing the validity and discriminativeness of the information in the step-by-step propagation. On the other hand, we design a dynamic recursion distribution module to fully exploit the role of inter-image correspondences in a recursive structure, adaptively assigning common attributes to each individual image through an improved semi-dynamic convolution. Experimental results on five prevailing CoSOD benchmarks demonstrate that our TRNet outperforms other competitors in terms of various evaluation metrics. The code and results of our method are available at https://***/rmcong/TRNetTCSVT2025. © 1991-2012 IEEE.

关键词： HTTP

来源：评论

学校读者我要写书评

暂无评论

PcdGS: A point cloud densification method for Gaussian Splatting

引用

computers & Graphics 2025年 130卷

作者： Jing Zhao Chenxi Li Shuhui Zhang Feng Wang Ying Yin Yuhan Liu School of Information Science and Engineering Yanshan University Qinhuangdao 066000 Hebei China Hebei Key Laboratory of Computer Virtual Technology and System Integration Qinhuangdao Hebei China

Novel view synthesis (NVS) from limited observations continues to be an important and persistent challenge. Currently, methods based on Neural Radiance Fields (NeRF) are not very efficient, and although methods based on 3D Gaussian Splatting (3DGS) outperform NeRF in terms of rendering quality and speed, they still lack sufficient details. To tackle these issues, we introduce a new method for densifying the point cloud, which enhances the rendering effect of 3DGS-based techniques under sparse view conditions. First, we introduce a mask-based densification technique to improve rendering details under limited input views. Second, We propose a monocular pixel depth-based mapping method that leverages a pre-trained model to predict depth, effectively normalizing point locations within the resulting point cloud. Lastly, we implement a filtering method based on depth and RGB color to minimize noise introduced by the additional data. We conduct comparative experiments on the LLFF, Mip-NeRF 360, and Blender datasets, demonstrating that our method outperforms existing approaches in both evaluation metrics and visual quality, thereby validating its effectiveness.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Towards realistic evaluation of cultural value alignment in large language models: Diversity enhancement for survey response simulation

引用

Information Processing and Management 2025年第4期62卷

作者： Liu, Haijiang Cao, Yong Wu, Xun Qiu, Chen Gu, Jinguang Liu, Maofu Hershcovich, Daniel School of Computer Science and Technology Wuhan University of Science and Technology Hubei Wuhan430065 China Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Hubei Wuhan430065 China Tübingen AI Center University of Tübingen Tübingen72074 Germany Division of Social Science The Hong Kong University of Science and Technology 511455 Hong Kong Department of Computer Science University of Copenhagen Copenhagen Denmark

Assessing Large Language Models (LLMs) alignment with human values has been a high priority in natural language processing. These models, praised as reservoirs of collective human knowledge, provoke an important question: Do they genuinely reflect the value preferences embraced by different cultures? We measure value alignment by simulating sociological surveys and comparing the distribution of preferences from model responses to human references. We introduce a diversity-enhancement framework featuring a novel memory simulation mechanism, which enables the generation of model preference distributions and captures the diversity and uncertainty inherent in LLM behaviors through realistic survey experiments. To better understand the causes of misalignment, we have developed comprehensive evaluation metrics. Our analysis of multilingual survey data illustrates that our framework improves the reliability of cultural value alignment assessments and captures the complexity of model responses across cultural contexts. Among the eleven models evaluated, the Mistral and Llama-3 series show superior alignment with cultural values, with Mistral-series models notably excelling in comprehending these values in both U.S. and Chinese contexts. © 2025 Elsevier Ltd

关键词： Digital elevation model

来源：评论

学校读者我要写书评

暂无评论

NavG: Risk-Aware Navigation in Crowded Environments Based on Reinforcement Learning with Guidance Points

arXiv

引用

arXiv 2025年

作者： Zhang, Qianyi Luo, Wentao Liu, Boyi Zhang, Ziyang Wang, Yaoyuan Liu, Jingtai Institute of Robotics and Automatic Information System Nankai University Tianjin Key Laboratory of Intelligent Robotics Tianjin China Advanced Computing and Storage Lab Huawei 2012 Lab China Department of Electronic and Computer Engineering The Kong Kong University of Science and Technology Hong Kong

Motion planning in navigation systems is highly susceptible to upstream perceptual errors, particularly in human detection and tracking. To mitigate this issue, the concept of guidance points—a novel directional cue within a reinforcement learning-based framework—is introduced. A structured method for identifying guidance points is developed, consisting of obstacle boundary extraction, potential guidance point detection, and redundancy elimination. To integrate guidance points into the navigation pipeline, a perception-to-planning mapping strategy is proposed, unifying guidance points with other perceptual inputs and enabling the RL agent to effectively leverage the complementary relationships among raw laser data, human detection and tracking, and guidance points. Qualitative and quantitative simulations demonstrate that the proposed approach achieves the highest success rate and near-optimal travel times, greatly improving both safety and efficiency. Furthermore, real-world experiments in dynamic corridors and lobbies validate the robot’s ability to confidently navigate around obstacles and robustly avoid pedestrians. © 2025, CC BY.

关键词： Travel time

来源：评论

学校读者我要写书评

暂无评论

Domain knowledge-guided geological named entities recognition of rock minerals based on prompt engineering with error feedback mechanism

引用

computers and Geosciences 2025年 201卷

作者： Qiu, Qinjun Ma, Yunxia Han, Peng Ma, Kai Huang, Zehua Tian, Miao Wu, Qirui Hubei Key Laboratory of Intelligent Vision Based Monitoring for Hydroelectric Engineering China Three Gorges University Hubei Yichang443002 China College of Computer and Information Technology China Three Gorges University Yichang443002 China School of Computer Science China University of Geosciences Wuhan430074 China CS&S Information System Engineering Co. Ltd China Key Laboratory of Geological Survey and Evaluation of Ministry of Education China University of Geosciences Wuhan430074 China School of Future Technology China University of Geosciences Wuhan430074 China

Geological reports contain a wealth of information about geological entities, such as rocks and minerals, which are of great significance for resource exploration, environmental assessment, 3D geological modeling, and intelligent prospecting. However, existing methods and models (e.g., deep learning-based approaches) for geological named entity recognition (GNER) heavily rely on large manually annotated corpora. This process is time-consuming and labor-intensive, and it faces limitations when dealing with complex entities in geological reports, such as long or nested entities. To address this issue, this paper proposes a rock and mineral NER method based on prompt engineering and domain knowledge guidance. First, preliminary entity recognition is conducted through labeling rather than extraction, mitigating the problem of repetitive recognition of nested entities. Second, we summarize and categorize the types of errors made by large language models(LLMs), incorporating geological knowledge guidance for secondary recognition to reduce common mistakes. Finally, secondary category validation is used to alleviate the "hallucination" problem, where LLMs mistakenly identify non-entities as entities. This method requires only two examples as training samples to guide the model, significantly reducing the workload of corpus annotation. Experiments were conducted on multiple LLMs (e.g., GPT-4o-0513, GPT-4o-0806, and Claude 3.5 sonnet). The results show that on our self-constructed dataset, compared to direct entity extraction, the accuracy of rock and mineral recognition is improved by approximately 17 % and 11 %, respectively, validating the effectiveness of combining domain knowledge with LLMs for GNER. © 2025

关键词： Mineral exploration

来源：评论

学校读者我要写书评

暂无评论

Energy-efficient and Privacy-preserving Edge Intelligence for 6G-Empowered Intelligent Transportation systems

引用

IEEE Network 2025年

作者： Zhu, Chenlu Fan, Xiaoxuan Deng, Xianjun Xiao, Ziheng Guo, Tingting Liu, Shenghao Sun, Jiaqi Park, Jong Hyuk Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan430074 China Wuhan Kedao Geographic Information Engineering Co. Wuhan China Department of Computer Science and Engineering Seoul National University of Science and Technology Seoul Korea Republic of

6G-empowered Intelligent Transportation systems (ITS) generate large amounts of data through millions of devices and sensors at the terminal and network edge. Edge intelligence advances the frontier of data-driven artificial intelligence (AI) to the network edge, which enables AI applications to better utilize edge data. Broader connectivity, higher device density, and stronger data exchange present challenges for reliable device communication and privacy data protection in 6G-empowered ITS. To address these challenges, this paper proposes an energy-efficient and privacy-preserving edge intelligence framework named EP-EI. EP-EI deploys a deep reinforcement learning-based cluster head selection model at the edge to ensure energy-efficient communication for terminal devices. Meanwhile, EP-EI designs a privacy-aware hierarchical computing framework for terminal-edge-cloud to prevent privacy leakage. Furthermore, the application scenarios, challenges, and future directions of EP-EI are discussed. Finally, simulation experiments in a specific intelligent transportation case study demonstrate that EP-EI can provide energy-efficient and privacy-protecting services. © 2025 IEEE.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Adaptive Backdoor Attacks with Reasonable Constraints on Graph Neural Networks

arXiv

引用

arXiv 2025年

作者： Dong, Xuewen Li, Jiachen Li, Shujun You, Zhichao Qu, Qiang Kholodov, Yaroslav Shen, Yulong School of Computer Science and Technology Xidian University The Engineering Research Center of Blockchain Technology Application and Evaluation Ministry of Education China The Shaanxi Key Laboratory of Blockchain and Secure Computing Xi’an710071 China University of Kent CanterburyCT2 7NP United Kingdom Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China Intelligent Transportation Systems Lab Innopolis University Innopolis Russia School of Computer Science and Technology Xidian University China The Shaanxi Key Laboratory of Network and System Security Xi’an710071 China

Recent studies show that graph neural networks (GNNs) are vulnerable to backdoor attacks. Existing backdoor attacks against GNNs use fixed-pattern triggers and lack reasonable trigger constraints, overlooking individual graph characteristics and rendering insufficient evasiveness. To tackle the above issues, we propose ABARC, the first Adaptive Backdoor Attack with Reasonable Constraints, applying to both graph-level and node-level tasks in GNNs. For graph-level tasks, we propose a subgraph backdoor attack independent of the graph’s topology. It dynamically selects trigger nodes for each target graph and modifies node features with constraints based on graph similarity, feature range, and feature type. For node-level tasks, our attack begins with an analysis of node features, followed by selecting and modifying trigger features, which are then constrained by node similarity, feature range, and feature type. Furthermore, an adaptive edge-pruning mechanism is designed to reduce the impact of neighbors on target nodes, ensuring a high attack success rate (ASR). Experimental results show that even with reasonable constraints for attack evasiveness, our attack achieves a high ASR while incurring a marginal clean accuracy drop (CAD). When combined with the state-of-the-art defense randomized smoothing (RS) method, our attack maintains an ASR over 94%, surpassing existing attacks by more than 7%. Copyright © 2025, The Authors. All rights reserved.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

SatCooper: Enhancing Cooperative Inference Analytics for Satellite Service via Multi-exit DNNs

引用

IEEE Transactions on Mobile Computing 2025年

作者： Zhang, Qiyang Wang, Shangguang Guan, Jinglong Donta, Praveen Kumar Ma, Xiao Prasad, RangaRao Venkatesha Dustdar, Schahram Liu, Xuanzhe Peking University School of Computer Science Beijing100871 China Beijing University of Posts and Telecommunications State Key Laboratory of Networking and Switching Technology Beijing China Stockholm University Department of Computer and Systems Sciences Kista16455 Sweden Beiyou Shenzhen Institute Shenzhen China Netherlands TU Wien Distributed System Group Wien1040 Austria UPF Barcelona Spain

As a key technology of intelligent satellite-enabled services in B5G or 6G networks, deploying Deep Neural Networks (DNN) models on satellites has been a notable trend, catering to the daily demand for extensive computing-intensive and latency-sensitive tasks. The computing resources are strategically deployed on satellites where sensor data is generated or collected, facilitating the fine-grained computational inference of DNN-based tasks. However, no prior study has comprehensively explored the crucial inference challenges-e.g., the trade-off between the number of tasks completed and accuracy and partitioning models in multi-exit models-in the resource-constrained space environment. Effective scheduling frameworks cater to various streams of inference tasks are scarce because inference performance may deviate from the ideal situation due to changes in task system status, such as task profiles and network state. To this end, we first formulate a gain-aware in-orbit computing inference problem to strike a proper trade-off between inference latency and the number of tasks completed by dynamically selecting optimal early exit points and model partitioning points. We propose an offline dynamic programming-based algorithm that provides an effective solution when comprehensive system details are to be predicted. We have developed an online learning-based method to schedule inference tasks with uncertain and dynamic system statuses in real-world situations. Our evaluation shows that, compared to baseline methods, the online learning-based algorithm can improve task gain by an average of 87.3% across various tasks. © 2002-2012 IEEE.

关键词： Dynamic programming

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：