检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Wu, Xinrui Xu, Jianbo Hu, Puyuan Wang, Guangming Wang, Hesheng Department of Automation Key Laboratory of System Control and Information Processing of Ministry of Education Key Laboratory of Marine Intelligent Equipment and System of Ministry of Education Shanghai Engineering Research Center of Intelligent Control and Management Shanghai Jiao Tong University Shanghai200240 China Department of Engineering University of Cambridge CambridgeCB2 1PZ United Kingdom

— Localization using a monocular camera in the pre-built LiDAR point cloud map has drawn increasing attention in the field of autonomous driving and mobile robotics. However, there are still many challenges (e.g. difficulties of map storage, poor localization robustness in large scenes) in accurately and efficiently implementing cross-modal localization. To solve these problems, a novel pipeline termed LHMap-loc is proposed, which achieves accurate and efficient monocular localization in LiDAR maps. Firstly, feature encoding is carried out on the original LiDAR point cloud map by generating offline heat point clouds, by which the size of the original LiDAR map is compressed. Then, an end-to-end online pose regression network is designed based on optical flow estimation and spatial attention to achieve real-time monocular visual localization in a pre-built map. In addition, a series of experiments have been conducted to prove the effectiveness of the proposed method. Our code is available at: https://***/IRMVLab/LHMaploc. Copyright © 2024, The Authors. All rights reserved.

关键词： Optical radar

来源：评论

学校读者我要写书评

暂无评论

Differential Private Discrete Noise-Adding Mechanism: Conditions, Properties, and Optimization

Differential Private Discrete Noise-Adding Mechanism: Condit...

引用

作者： Qin, Shuying He, Jianping Fang, Chongrong Lam, James Shanghai Jiao Tong University Department of Automation Shanghai200240 China Key Laboratory of System Control and Information Processing Ministry of Education of China Beijing100816 China Shanghai Engineering Research Center of Intelligent Control and Management Shanghai200240 China Shenzhen Institute of Research and Innovation Shenzhen518055 China The University of Hong Kong Department of Mechanical Engineering Hong Kong999077 Hong Kong

Differential privacy is a widely used framework for evaluating privacy loss in data anonymization. While the continuous noise-adding mechanism has been extensively studied, there is a dearth of research on discrete random mechanisms for discretely distributed data. This study addresses this gap by examining the primary differential privacy conditions and properties for general discrete random mechanisms, and investigating the trade-off between data privacy and data utility. We establish sufficient and necessary conditions for discrete ϵ-differential privacy and sufficient conditions for discrete (ϵδ)-differential privacy, with closed-form expressions for differential privacy parameters. These conditions can be applied to evaluate the differential privacy properties of discrete noise-adding mechanisms with various types of noise. Moreover, we propose an optimal discrete ϵ-differential private noise-adding mechanism under the utility-maximization framework. Here, the utility is characterized by the similarity of the statistical properties between the mechanism's input and output. Our findings suggest that the optimal class of discrete noise probability distributions in the mechanism is staircase-shaped. © 1991-2012 IEEE.

关键词： Probability distributions

来源：评论

学校读者我要写书评

暂无评论

Binary system modes of matrix-coupled multidimensional Kuramoto oscillators

arXiv

引用

arXiv 2023年

作者： Wang, Chongzhi Shao, Haibin Li, Dewei Department of Automation Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai Engineering Research Center of Intelligent Control and Management Shanghai200240 China

Synchronization and desynchronization are the two ends on the spectrum of emergent phenomena that somehow often coexist in biological, neuronal, and physical networks. However, previous studies essentially regard their coexistence as a partition of the network units: those that are in relative synchrony and those that are not. In real-world systems, desynchrony bears subtler divisions because the interacting units are high-dimensional, like fish schooling with varying speeds in a circle, synchrony and desynchrony may occur to the different dimensions of the population. In this work, we show with an ensemble of multidimensional Kuramoto oscillators, that this property is generalizable to arbitrary dimensions: for a d dimensional population, there exist 2d system modes where each dimension is either synchronized or desynchronized, represented by a set of almost binary order parameters. Such phenomena are induced by a matrix coupling mechanism that goes beyond the conventional scalar-valued coupling by capturing the inter-dimensional dependence amongst multidimensional individuals, which arises naturally from physical, sociological and engineering systems. As verified by our theory, the property of the coupling matrix thoroughly affects the emergent system modes and the phase transitions toward them. By numerically demonstrating that these system modes are interchangeable through matrix manipulation, we also observe explosive synchronization/desynchronization that is induced without the conditions that are previously deemed essential. Our discovery provides theoretical analogy to the cerebral activity where the resting state and the activated state coexist unihemispherically, it also evokes a new possibility of information storage in oscillatory neural networks. Copyright © 2023, The Authors. All rights reserved.

关键词： Synchronization

来源：评论

学校读者我要写书评

暂无评论

Retinal Vessels Segmentation Based on Multi-scale Hybrid Convolutional Network 4th

Retinal Vessels Segmentation Based on Multi-scale Hybrid Con...

引用

4th International Conference on Smart Vehicular Technology, Transportation, Communication and Applications, VTCA 2021

作者： Li, Rui Li, Zuoyong Cao, Xinrong Teng, Shenghua College of Electronic and Information Engineering Shandong University of Science and Technology Qingdao266590 China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou350121 China Fuzhou Digital Healthcare Industry Technology Innovation Center Minjiang University Fuzhou350121 China

ISBN: (纸本)9789811640384

Retinal fundus image can reveal the information on the early symptoms of diabetes, hypertension, hyperlipidemia and other diseases. Accurate segmentation of retinal vessels can assist the detection and diagnosis of the related diseases. Due to the intricate characteristic information of retinal vessels images, traditional segmentation methods lead to inaccurate segmentation for small vessels and pathological segmentation errors. In this paper, we propose a new multi-scale hybrid convolution U-Net. Firstly, we take the hybrid convolution module by combining dilated convolution and standard convolution as the core structure for feature extraction to obtain more abundant semantic feature information, while expanding the receptive field. Then, we add a multi-scale fusion module to the network encoding and decoding connection part, which fuses the feature information of different layers to reduce the loss of information and enhance the representation ability of the network. We evaluate the performance of the proposed method on two public retinal datasets (DRIVE and CHASE_DB1). The results of quantitative and qualitative experiments show that the proposed model can improve good accuracy in retinal vessels segmentation. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Operator-Adapted Evolutionary Large-Scale Multiobjective Optimization for Voltage Transformer Ratio Error Estimation 11th

Operator-Adapted Evolutionary Large-Scale Multiobjective Opt...

引用

11th International Conference on Evolutionary Multi-Criterion Optimization, EMO 2021

作者： Huang, Changwu Li, Lianghao He, Cheng Cheng, Ran Yao, Xin Guangdong Provincial Key Laboratory of Brain-Inspired Intelligent Computation Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen518055 China Key Laboratory of Image Information Processing and Intelligent Control of Education Ministry of China School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China

ISBN: (纸本)9783030720612

Large-scale multiobjective optimization problems (LSMOPs) exist widely in real-world applications, and they are challenging for existing evolutionary algorithms due to their massive volume of search space. Despite that a number of large-scale multiobjective evolutionary algorithms (LSMOEAs) have been proposed in recent years, their effectiveness in solving LSMOPs remains unsatisfactory. One main reason is that most existing LSMOEAs may fail to balance convergence enhancement and diversity maintenance, especially for solving real-world problems. To address this issue, we propose to use a hybridized LSMOEA with adaptive operator selection (AOS) to handle real-world LSMOPs. Specifically, the proposed hybridized LSMOEA with AOS (AOS-LSMOEA) includes multiple different offspring generation and environmental selection strategies extracted from some existing LSMOEAs. Then it uses the AOS to adaptively determine the application rates of different offspring generation and environmental selection operators in an online manner. The proposed approach is capable of taking advantage of existing LSMOEAs, and the AOS enables the algorithm to choose suitable operators for solving different LSMOPs. In this study, the proposed algorithm is expected to solve the voltage transformer ratio error estimation (TREE) problems effectively. Experimental results show that AOS-LSMOEA achieves significant performance improvement due to the hybridization of different operators and the adoption of AOS method. © 2021, Springer Nature Switzerland AG.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

Preserving Topology of Network Systems: Metric, Analysis, and Optimal Design

arXiv

引用

arXiv 2023年

作者： Li, Yushan Wang, Zitong He, Jianping Chen, Cailian Guan, Xinping Dept. of Automation Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai Engineering Research Center of Intelligent Control and Management Shanghai China

Preserving the topology from being inferred by external adversaries has become a paramount security issue for network systems (NSs), and adding random noises to the nodal states provides a promising way. Nevertheless, recent works have revealed that the topology cannot be preserved under i.i.d. noises in the asymptotic sense. How to effectively characterize the non-asymptotic preservation performance still remains an open issue. Inspired by the deviation quantification of concentration inequalities, this paper proposes a novel metric named trace-based variance-expectation ratio. This metric effectively captures the decaying rate of the topology inference error, where a slower rate indicates better non-asymptotic preservation performance. We prove that the inference error will always decay to zero asymptotically, as long as the added noises are non-increasing and independent (milder than the i.i.d. condition). Then, the optimal noise design that produces the slowest decaying rate for the error is obtained. More importantly, we amend the noise design by introducing one-lag time dependence, achieving the zero state deviation and the non-zero topology inference error in the asymptotic sense simultaneously. Extensions to a general class of noises with multi-lag time dependence are provided. Comprehensive simulations verify the theoretical findings. Copyright © 2023, The Authors. All rights reserved.

关键词： Topology

来源：评论

学校读者我要写书评

暂无评论

Optimal Linear Attack in Cyber-Physical Systems with Periodic Detection

Optimal Linear Attack in Cyber-Physical Systems with Periodi...

引用

IEEE Conference on Decision and control

作者： Jia Qi Chongrong Fang Jianping He Dept. of Automation Key Laboratory of System Control and Information Processing Shanghai Jiao Tong University Ministry of Education of China and Shanghai Engineering Research Center of Intelligent Control and Management Shanghai China

Security issues are of significant importance for cyber-physical systems (CPS), where the attack design is a major concern. Most related studies on attack design implicitly consider that the control period and detection period are the same. However, the two periods could be different in practical systems with remote detection such as supervisory control and data acquisition (SCADA) systems, which could lead to new vulnerabilities for attackers. In this paper, we consider the design of innovation-based linear attack strategies for CPS when the control period and detection period are inconsistent. Specifically, we propose an attack framework that consists of attack strategies for detection and non-detection instants under the period discrepancy. On this basis, we design the optimal stealthy innovation-based linear attack strategies for state estimation and LQG control to maximize the estimation error or control cost, respectively. Simulations are given to demonstrate the effectiveness of the proposed attack strategies.

关键词：

来源：评论

学校读者我要写书评

暂无评论

3D Cinemagraphy from a Single image

arXiv

引用

arXiv 2023年

作者： Li, Xingyi Cao, Zhiguo Sun, Huiqiang Zhang, Jianming Xian, Ke Lin, Guosheng Key Laboratory of Image Processing and Intelligent Control Ministry of Education School of Artificial Intelligence and Automation Huazhong University of Science and Technology China Adobe Research S-Lab Nanyang Technological University Singapore

We present 3D Cinemagraphy, a new technique that marries 2D image animation with 3D photography. Given a single still image as input, our goal is to generate a video that contains both visual content animation and camera motion. We empirically find that naively combining existing 2D image animation and 3D photography methods leads to obvious artifacts or inconsistent animation. Our key insight is that representing and animating the scene in 3D space offers a natural solution to this task. To this end, we first convert the input image into feature-based layered depth images using predicted depth values, followed by unprojecting them to a feature point cloud. To animate the scene, we perform motion estimation and lift the 2D motion into the 3D scene flow. Finally, to resolve the problem of hole emergence as points move forward, we propose to bidirectionally displace the point cloud as per the scene flow and synthesize novel views by separately projecting them into target image planes and blending the results. Extensive experiments demonstrate the effectiveness of our method. A user study is also conducted to validate the compelling rendering results of our method. Copyright © 2023, The Authors. All rights reserved.

关键词： Animation

来源：评论

学校读者我要写书评

暂无评论

Hybrid Data-Free Knowledge Distillation 39

Hybrid Data-Free Knowledge Distillation

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Tang, Jialiang Chen, Shuo Gong, Chen School of Computer Science and Engineering Nanjing University of Science and Technology China Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education China Jiangsu Key Laboratory of Image and Video Understanding for Social Security China Center for Advanced Intelligence Project RIKEN Japan Department of Automation Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University China

ISBN: (纸本)157735897X

Data-free knowledge distillation aims to learn a compact student network from a pre-trained large teacher network without using the original training data of the teacher network. Existing collection-based and generation-based methods train student networks by collecting massive real examples and generating synthetic examples, respectively. However, they inevitably become weak in practical scenarios due to the difficulties in gathering or emulating sufficient real-world data. To solve this problem, we propose a novel method called Hybrid Data-Free Distillation (HiDFD), which leverages only a small amount of collected data as well as generates sufficient examples for training student networks. Our HiDFD comprises two primary modules, i.e., the teacher-guided generation and student distillation. The teacher-guided generation module guides a Generative Adversarial Network (GAN) by the teacher network to produce high-quality synthetic examples from very few real-world collected examples. Specifically, we design a feature integration mechanism to prevent the GAN from overfitting and facilitate the reliable representation learning from the teacher network. Meanwhile, we drive a category frequency smoothing technique via the teacher network to balance the generative training of each category. In the student distillation module, we explore a data inflation strategy to properly utilize a blend of real and synthetic data to train the student network via a classifier-sharing-based feature alignment technique. Intensive experiments across multiple benchmarks demonstrate that our HiDFD can achieve state-of-the-art performance using 120 times less collected data than existing methods. Copyright © 2025, Association for the Advancement of Artificia Intelligence (***). All rights reserved.

关键词： Personnel training

来源：评论

学校读者我要写书评

暂无评论

Manifold Learning Inspired Mating Restriction for Evolutionary Constrained Multiobjective Optimization 11th

Manifold Learning Inspired Mating Restriction for Evolutiona...

引用

11th International Conference on Evolutionary Multi-Criterion Optimization, EMO 2021

作者： Li, Lianghao He, Cheng Cheng, Ran Pan, Linqiang Key Laboratory of Image Information Processing and Intelligent Control of Education Ministry of China School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China Guangdong Provincial Key Laboratory of Brain-Inspired Intelligent Computation Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen518055 China

ISBN: (纸本)9783030720612

Mating restriction strategies are capable of restricting the distribution of parent solutions for effective offspring generation in evolutionary algorithms (EAs). Studies have shown the importance of these strategies in improving the performance of EAs for multiobjective optimization. Our previous study proposed a specific manifold learning inspired mating restriction (MLMR) strategy. It has shown promising capability of solving multiobjective optimization problems (MOPs) with complicated Pareto set shapes. However, the effect of mating restriction strategies in solving constrained MOPs is yet to be well studied. Here, we investigate the effectiveness of MLMR for solving constrained MOPs. The MLMR strategy is embedded into some representative multiobjective EAs and tested on various benchmark constrained MOPs. Experimental results indicate the encouraging performance of MLMR in constrained multiobjective optimization. © 2021, Springer Nature Switzerland AG.

关键词： Multiobjective optimization

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：