检索结果-内蒙古大学图书馆

NUC-Net: Non-uniform Cylindrical Partition Network for Efficient LiDAR Semantic Segmentation

IEEE Transactions on Circuits and Systems for Video Technology 2025年

作者： Wang, Xuzhi Feng, Wei Kong, Lingdong Wan, Liang Tianjin Normal University College of Computer and Information Engineering Tianjin300380 China Tianjin Key Laboratory of Student Mental Health and Intelligence Assessment China Tianjin University College of Intelligence and Computing Tianjin300350 China National University of Singapore Department of Computer Science 117597 Singapore

LiDAR semantic segmentation plays a vital role in autonomous driving. Existing voxel-based methods for LiDAR semantic segmentation apply uniform partition to the 3D Li- DAR point cloud to form a structured representation based on cartesian/cylindrical coordinates. Although these methods show impressive performance, the drawback of existing voxel-based methods remains in two aspects: (1) it requires a large enough input voxel resolution, which brings a large amount of computation cost and memory consumption. (2) it does not well handle the unbalanced point distribution of LiDAR point cloud. In this paper, we propose a non-uniform cylindrical partition network named NUC-Net to tackle the above challenges. Specifically, we propose the Arithmetic Progression of Interval (API) method to non-uniformly partition the radial axis and generate the voxel representation which is representative and efficient. Moreover, we propose a non-uniform multi-scale aggregation method to improve contextual information. Our method achieves state-of-the-art performance on SemanticKITTI and nuScenes datasets with much faster speed and much less training time. And our method can be a general component for LiDAR semantic segmentation, which significantly improves both the accuracy and efficiency of the uniform counterpart by 4× training faster and 2× GPU memory reduction and 3× inference speedup. We further provide theoretical analysis towards understanding why NUC is effective and how point distribution affects performance. Code is available at https://***/alanWXZ/NUC-Net. © 1991-2012 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Exploring Invariance Matters for Domain Generalization

引用

IEEE Transactions on Image Processing 2025年 34卷 3336-3351页

作者： Wang, Shanshan He, Houmeng Yang, Xun Liu, Zhipu Zhong, Yuanhong Zhang, Xingyi Wang, Meng Anhui University National Key Laboratory of Opto-Electronic Information Acquisition and Protection Technology Institutes of Physical Science and Information Technology Hefei230601 China University of Science and Technology of China School of Information Science and Technology Department of Electronic Engineering and Information Science Hefei230026 China Chongqing University of Technology School of Computer Science and Engineering Chongqing400054 China Chongqing University School of Microelectronics and Communication Engineering Chongqing400030 China Anhui University Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education School of Computer Science and Technology Hefei230601 China Hefei University of Technology School of Computer Science and Information Engineering Hefei230009 China

Domain generalization (DG) aims to solve the problem of significant performance degradation when target domain data collected from the Out-Of-Distribution (O.O.D). Previous efforts try to exploit invariant features in the source domain through CNN networks. However, inspired by causal mechanisms, we find that the complex spurious-invariant information is still hidden in this view invariant features, and the impact of domain and class discrepancies on extracting invariance has not been effectively mitigated. To alleviate these issues, we propose a self-weighted multi-view mining invariance domain generalization framework (SMIDG). On the one hand, to make up for the insufficiency of traditional single-view convolutional feature extraction networks, we propose to mine features from another frequency view and use the self-adaptive adversarial masks to eliminate some spurious correlations, ensuring causal invariance in the coarse-grained generalization. However, due to inconsistencies in discriminative information between interdomain and intra-domain samples, as well as inter-class and intra-class samples, the coarse-grained elimination of spurious associations does not fully resolve this issue. On the other hand, we also consider the fine-grained generalization from two aspects. Firstly, to better tackle the domain discrepancies, we propose a novel progressive contrastive learning strategy that learns the underlying specific features of samples while gradually mitigating domain discrepancies, thereby ensuring domain invariance in fine-grained generalization. Secondly, due to the issue of feature inconsistency, we adopt a self-adaptive hard sample mining method with information gain to ensure that the model pays more attention on hard disentangled samples, thus maintaining feature invariance. Extensive experiments on five benchmark datasets demonstrate that our method outperforms state-of-the-art approaches. © 1992-2012 IEEE.

关键词： Contrastive learning Feature extraction Frequency-domain analysis Training Data models Data mining Correlation Data augmentation Convolutional neural networks computer science

来源：评论

学校读者我要写书评

暂无评论

From Head to Tail: Efficient Black-box Model Inversion Attack via Long-tailed Learning

arXiv

引用

arXiv 2025年

作者： Li, Ziang Zhang, Hongguang Wang, Juan Chen, Meihui Hu, Hongxin Yi, Wenzhe Xu, Xiaoyang Yang, Mengda Ma, Chenjun Key Laboratory of Aerospace Information Security and Trusted Computing Ministry of Education School of Cyber Science and Engineering Wuhan University China Shanghai Innovation Institute China Ant Group China Department of Computer Science and Engineering University at Buffalo SUNY United States

Model Inversion Attacks (MIAs) aim to reconstruct private training data from models, leading to privacy leakage, particularly in facial recognition systems. Although many studies have enhanced the effectiveness of white-box MIAs, less attention has been paid to improving efficiency and utility under limited attacker capabilities. Existing black-box MIAs necessitate an impractical number of queries, incurring significant overhead. Therefore, we analyze the limitations of existing MIAs and introduce Surrogate Model-based Inversion with Long-tailed Enhancement (SMILE), a high-resolution oriented and query-efficient MIA for the black-box setting. We begin by analyzing the initialization of MIAs from a data distribution perspective and propose a long-tailed surrogate training method to obtain high-quality initial points. We then enhance the attack’s effectiveness by employing the gradient-free black-box optimization algorithm selected by NGOpt. Our experiments show that SMILE outperforms existing state-of-the-art black-box MIAs while requiring only about 5% of the query overhead. Our code is available at https://***/L1ziang/SMILE. Copyright © 2025, The Authors. All rights reserved.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Organic-inorganic hybrid piezotronic bipolar junction transistor for pressure sensing

引用

Microsystems & Nanoengineering 2024年第3期10卷 229-244页

作者： Emad Iranmanesh Zihao Liang Weiwei Li Congwei Liao Shunyu Jin Chuan Liu Kai Wang Shengdong Zhang Charalampos Doumanidis Gehan A.J.Amaratunga Hang Zhou Guangdong Provincial Key Laboratory of In-Memory Computing Chips School of Electronic and Computer EngineeringPeking University Shenzhen Graduate SchoolShenzhen 518055P.R.China School of Mechanical Engineering Guangdong Technion-Israel Institute of TechnologyShantou 515063P.R.China State Key Laboratory of Microelectronics Device and Integrated Technology Institute of MicroelectronicsChinese Academy of SciencesBeijing 100029P.R.China Hefei National Research Center for Physical Sciences at the Microscale University of Science and Technology of ChinaHefei 23000PR China School of Electronics and Information Technology Sun Yat-sen UniversityNo.132 East Waihuan RoadGuangzhou 510006P.R.China Department of Mechanical Aerospaceand Biomedical EngineeringUniversity of South AlabamaShelby Hall3128MobileAL 36688USA Electrical Engineering Division Department of EngineeringUniversity of Cambridge9 JJ Thomson AvenueCambridge CB30FAUnited Kingdom Zhejiang University International CampusHainingChina

With the rapid development of the Internet of Things(IoTs),wearable sensors are playing an increasingly important role in daily monitoring of personal health and *** signal-to-noise-ratio has become the most critical performance factor to *** enhance it,on the one hand,good sensing materials/devices have been employed;on the other hand,signal amplification and noise reduction circuits have been ***,most of these devices and circuits work in an active sampling mode,requiring frequent data acquisition and hence,entailing high-power *** this scenario,a flexible and wearable event-triggered sensor with embedded signal amplification without an external power supply is of great ***,we report a flexible two-terminal piezotronic n-p-n bipolar junction transistor(PBJT)that acts as an autonomous and highly sensitive,current-and/or voltage-mediated pressure *** PBJT is formed by two back-to-back piezotronic diodes which are defined as emitter-base and collectorbase *** force exertion on the emitter side,as a result of the piezoelectric effect,the emitter-base diode is forward biased while the collector-base diode is reverse *** to the inherent BJT amplification effect,the PBJT achieves record-high sensitivities of 139.7 kPa^(-1)(current-based)and 88.66 kPa^(-1)(voltage-based)in sensing *** PBJT also has a fast response time of<110 ms under exertion of dynamic stimuli ranging from a flying butterfly to a gentle finger ***,the PBJT advances the state of the art not only in terms of sensitivity but also in regard to being self-driven and autonomous,making it promising for pressure sensing and other IoT applications.

关键词： bipolar transistor IoT

来源：评论

学校读者我要写书评

暂无评论

Towards a Deep Learning Pain-Level Detection Deployment at UAE for Patient-Centric-Pain Management and Diagnosis Support: Framework and Performance Evaluation

引用

Procedia computer science 2023年 220卷 339-347页

作者： Leila Ismail Muhammad Danish Waseem Clouds and Distributed Computing and Systems (CLOUDS) Lab School of Computing and Information Systems Faculty of Engineering and Information Technology The University of Melbourne Australia. Intelligent Distributed Computing and Systems (INDUCE) Research Laboratory Department of Computer Science and Software Engineering College of Information Technology United Arab Emirates University UAE. National Water and Energy Center United Arab Emirates University UAE.

The outbreak of the COVID-19 pandemic revealed the criticality of timely intervention in a situation exacerbated by a shortage in medical staff and equipment. Pain-level screening is the initial step toward identifying the severity of patient conditions. Automatic recognition of state and feelings help in identifying patient symptoms to take immediate adequate action and providing a patient-centric medical plan tailored to a patient's state. In this paper, we propose a framework for pain-level detection for deployment in the United Arab Emirates and assess its performance using the most used approaches in the literature. Our results show that a deployment of a pain-level deep learning detection framework is promising in identifying the pain level accurately.

关键词： computer Vision Deep Learning Image Processing Machine Learning Pain Detection Patient-Centric Smart healthcare eHealth

来源：评论

学校读者我要写书评

暂无评论

Retraction Note: High performance reconciliation for practical quantum key distribution systems

引用

Optical and Quantum Electronics 2024年第12期56卷 1-2页

作者： Mao, ao-Kun Li, Qiong Hao, Peng-Lei Abd-El-Atty, Bassem Iliyasu, Abdullah M. Department of Computer Science and Technology Harbin Institute of Technology Harbin China CAS Key Laboratory of Quantum Information University of Science and Technology of China Hefei China CAS Center for Excellence in Quantum Information and Quantum Physics University of Science and Technology of China Hefei China Department of Computer Science Faculty of Computers and Information Luxor University Luxor Egypt Electrical Engineering Department College of Engineering Prince Sattam Bin Abdulaziz University Al- Kharj Saudi Arabia School of Computing Tokyo Institute of Technology Yokohama Japan School of Computer Science and Technology Changchun University of Science and Technology Changchun China

来源：评论

学校读者我要写书评

暂无评论

Entirety of Quantum Uncertainty and Its Experimental Verification

引用

Chinese Physics Letters 2021年第7期38卷 11-16页

作者： Jie Xie Li Zhou Aonan Zhang Huichao Xu Man-Hong Yung Ping Xu Nengkun Yu Lijian Zhang National Laboratory of Solid State Microstructures College of Engineering and Applied Sciences and School of PhysicsNanjing UniversityNanjing 210093China Collaborative Innovation Center of Advanced Microstructures Nanjing UniversityNanjing 210093China Department of Computer Science and Technology Tsinghua UniversityBeijing 100084China Shenzhen Institute for Quantum Science and Engineering and Department of Physics Southern University of Science and TechnologyShenzhen 518055China Shenzhen Key Laboratory of Quantum Science and Engineering Southern University of Science and TechnologyShenzhen 518055China Institute for Quantum Information&State Key Laboratory of High Performance Computing College of ComputerNational University of Defense TechnologyChangsha 410073China Centre for Quantum Software and Information School of SoftwareFaculty of Engineering and Information TechnologyUniversity of Technology SydneyNSWAustralia

As a foundation of quantum physics,uncertainty relations describe ultimate limit for the measurement uncertainty of incompatible ***,uncertainty relations are formulated by mathematical bounds for a specific *** we present a method for geometrically characterizing uncertainty relations as an entire area of variances of the observables,ranging over all possible input *** find that for the pair of position and momentum operators,Heisenberg's uncertainty principle points exactly to the attainable area of the variances of position and ***,for finite-dimensional systems,we prove that the corresponding area is necessarily semialgebraic;in other words,this set can be represented via finite polynomial equations and inequalities,or any finite union of such *** particular,we give the analytical characterization of the areas of variances of(a)a pair of one-qubit observables and(b)a pair of projective observables for arbitrary dimension,and give the first experimental observation of such areas in a photonic system.

关键词： observable union operators

来源：评论

学校读者我要写书评

暂无评论

CSCL-DTI: predicting drug-target interaction through cross-view and self-supervised contrastive learning

CSCL-DTI: predicting drug-target interaction through cross-v...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Xuan Lin Xi Zhang Zu-Guo Yu Yahui Long Xiangxiang Zeng Philip S. Yu College of Computer Science Xiangtan University China Key Laboratory of Intelligent Computing and Information Processing of Ministry of Education Xiangtan University China Singapore Immunology Network (SIgN) Agency for Science Technology and Research (A*STAR) Singapore College of Information Science and Engineering Hunan University China Department of Computer Science University of Illinois Chicago USA

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

Accurately predicting drug-target interactions (DTI) is a critical step in drug discovery. Existing methods of DTI prediction primarily employ Simplified Molecular-Input Line-Entry System (SMILES) sequences or molecular graphs to learn drug representations. However, the features learned by such single-view approach is prone to incomplete. While some multiview methods that consider the views of both SMILES sequences and molecular graphs have been developed, these methods often fall in short in capturing potential interactions between views. In this work, we propose a novel dual contrastive learning framework CSCL-DTI for DTI prediction. First, we design a contrastive-enhanced cross-view representation learning (CVRL) to learn representations for drugs. In this module, Transformer-based and graph convolutional network (GCN)-based encoders are separately adopted to learn view-specific representations, followed by contrastive learning to enrich the representations by accounting for the potential interplay between local chemical context and topological structure. Second, we combine Transformer with self-supervised contrastive learning (SSCL) to learn representations for targets by modelling protein amino acids sequences. The scheme allows to effectively preserve the intrinsic characteristics of the sequences. Finally, we introduce a bilinear attention network to obtain an integrated representation by adaptively incorporating drug and target representations. Benchmarking experiments on two datasets demonstrated that CSCL-DTI 1 outperforms six state-of-the-art methods.

关键词： Drugs Proteins Representation learning Protein engineering Adaptation models Contrastive learning Predictive models Transformers Amino acids Diffusion tensor imaging

来源：评论

学校读者我要写书评

暂无评论

Like an Ophthalmologist: Dynamic Selection Driven Multi-View Learning for Diabetic Retinopathy Grading 39

Like an Ophthalmologist: Dynamic Selection Driven Multi-View...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Luo, Xiaoling Xu, Qihao Wu, Huisi Liu, Chengliang Lai, Zhihui Shen, Linlin Computer Vision Institute College of Computer Science and Software Engineering Shenzhen University Shenzhen China Shenzhen Key Laboratory of Visual Object Detection and Recognition Harbin Institute of Technology Shenzhen China Department of Computer Science and Engineering Hong Kong University of Science and Technology Hong Kong National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China Guangdong Provincial Key Laboratory of Intelligent Information Processing China

ISBN: (纸本)157735897X

Diabetic retinopathy (DR), with its large patient population, has become a formidable threat to human visual health. In the clinical diagnosis of DR, multi-view fundus images are considered to be more suitable for DR diagnosis because of the wide coverage of the field of view. Therefore, different from the previous single-view DR grading methods, we design a dynamic selection-driven multi-view DR grading method to fit clinical scenarios better. Since lesion information plays a key role in DR diagnosis, previous methods usually boost the model performance by enhancing the lesion feature. However, during the actual diagnosis, ophthalmologists not only focus on the crucial parts, but also exclude irrelevant features to ensure the accuracy of judgment. To this end, we introduce the idea of dynamic selection and design a series of selection mechanisms from fine granularity to coarse granularity. In this work, we first introduce an Ophthalmic Image Reader (OIR) agent to provide the model with pixel-level prompts of suspected lesion areas. Moreover, we design a Multi-View Token Selection Module (MVTSM) that prunes redundant feature tokens and dynamically selects key information. In the final decision stage, we dynamically fuse multi-view features through the novel Multi-View Mixture of Experts Module (MVMoEM), to enhance key views and reduce the impact of conflicting views. Extensive experiments on a large multi-view fundus image dataset with 34,452 images prove that our method performs favorably against state-of-the-art models. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Ophthalmology

来源：评论

学校读者我要写书评

暂无评论

Diff9D: Diffusion-Based Domain-Generalized Category-Level 9-DoF Object Pose Estimation

引用

IEEE Transactions on Pattern Analysis and Machine Intelligence 2025年第7期47卷 5520-5537页

作者： Jian Liu Wei Sun Hui Yang Pengchao Deng Chongpei Liu Nicu Sebe Hossein Rahmani Ajmal Mian National Engineering Research Center for Robot Visual Perception and Control Technology College of Electrical and Information Engineering School of Robotics and the State Key Laboratory of Advanced Design and Manufacturing for Vehicle Body Hunan University Changsha China Institute of Artificial Intelligence and Robotics Xi’an Jiaotong University Xi’an China Department of Information Engineering and Computer Science University of Trento Trento Italy School of Computing and Communications Lancaster University Lancaster U.K. Department of Computer Science The University of Western Australia Crawley WA Australia

Nine-degrees-of-freedom (9-DoF) object pose and size estimation is crucial for enabling augmented reality and robotic manipulation. Category-level methods have received extensive research attention due to their potential for generalization to intra-class unknown objects. However, these methods require manual collection and labeling of large-scale real-world training data. To address this problem, we introduce a diffusion-based paradigm for domain-generalized category-level 9-DoF object pose estimation. Our motivation is to leverage the latent generalization ability of the diffusion model to address the domain generalization challenge in object pose estimation. This entails training the model exclusively on rendered synthetic data to achieve generalization to real-world scenes. We propose an effective diffusion model to redefine 9-DoF object pose estimation from a generative perspective. Our model does not require any 3D shape priors during training or inference. By employing the Denoising Diffusion Implicit Model, we demonstrate that the reverse diffusion process can be executed in as few as 3 steps, achieving near real-time performance. Finally, we design a robotic grasping system comprising both hardware and software components. Through comprehensive experiments on two benchmark datasets and the real-world robotic system, we show that our method achieves state-of-the-art domain generalization performance.

关键词： Shape Solid modeling Three-dimensional displays Pose estimation Training Robots Grasping Diffusion models Real-time systems Point cloud compression

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

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

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：