检索结果-内蒙古大学图书馆

Learning to Learn Transferable Generative Attack for Person Re-Identification

IEEE Transactions on image processing 2025年 PP卷 PP页

作者： Bian, Yuan Liu, Min Wang, Xueping Ma, Yunfeng Wang, Yaonan Hunan University National Engineering Research Center of Robot Visual Perception and Control Technology College of Electrical and Information Engineering Hunan Changsha China Hunan Normal University Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing College of Information Science and Engineering Hunan Changsha China

Deep learning-based person re-identification (reid) models are widely employed in surveillance systems and inevitably inherit the vulnerability of deep networks to adversarial attacks. Existing attacks merely consider cross-dataset and cross-model transferability, ignoring the cross-test capability to perturb models trained in different domains. To powerfully examine the robustness of real-world re-id models, the Meta Transferable Generative Attack (MTGA) method is proposed, which adopts meta-learning optimization to promote the generative attacker producing highly transferable adversarial examples by learning comprehensively simulated transfer-based crossmodel&dataset&test black-box meta attack tasks. Specifically, cross-model&dataset black-box attack tasks are first mimicked by selecting different re-id models and datasets for meta-train and meta-test attack processes. As different models may focus on different feature regions, the Perturbation Random Erasing module is further devised to prevent the attacker from learning to only corrupt model-specific features. To boost the attacker learning to possess cross-test transferability, the Normalization Mix strategy is introduced to imitate diverse feature embedding spaces by mixing multi-domain statistics of target models. Extensive experiments show the superiority of MTGA, especially in cross-model&dataset and cross-model&dataset&test attacks, our MTGA outperforms the SOTA methods by 20.0% and 11.3% on mean mAP drop rate, respectively. © 1992-2012 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Multi-objective capacity configuration optimization of a grid-connected SOFC/LB microgrid

Multi-objective capacity configuration optimization of a gri...

引用

Youth Academic Annual Conference of Chinese Association of Automation (YAC)

作者： Beibei Wang Zishan Yin Jingxuan Peng Shiwei Zeng Zhonghua Deng Xi Li School of Artificial Intelligence and Automation Key Laboratory of Imaging Processing and Intelligent Control of Education Ministry Huazhong University of Science and Technology Wuhan China Wuhan Huamao Automation Co. Ltd Huazhong University of Science and Technology Wuhan China

ISBN: (数字)9798350379228

ISBN: (纸本)9798350390780

The solid Oxide Fuel Cell (SOFC) technique with electric to gas technique is an investment-worthy way to enhance the consumption of renewable energy in microgrids. Moreover, SOFC’s high fuel adaptability and efficient cogeneration are ideal for stationary power generation. However, due to SOFC’s slow load response and high cost, the capacity configuration designation of microgrid with SOFC system is significant. To enhance energy utilization and reduce cost, in this paper, a microgrid connected with an upper grid, containing SOFC, wind turbine (WT), photovoltaics (PV), electrolyzer, a hydrogen storage system (HSS), and lithium battery (LB), is built. Considering the dynamic characteristics of SOFC’s load response, transient and steady-stage’s energy management strategies assisted by LB are proposed. Capacity configuration parameters of microgrid’s components are selected as decision variables and minimal life cycle cost (LCC) and minimal curtailment rate of wind and PV are selected as objective functions. Using proposed strategies to process microgrids, the NSGA-II algorithm is used to optimize. An actual case is studied and appropriate capacity configuration is solved, with 2112 120W PVs,315 500W WTs, 5 10kW • h LBs,5 SOFCs,98.73kW electrolyzer and 38.94kg *** reaches $4.268 × 10 5 and wind &PV’s curtailment rate reaches 5.71%. The result’s rationality is proved by analyzing the detailed cost and operation.

关键词： Photovoltaic systems Renewable energy sources Costs Power demand Fuel cells Microgrids Solids

来源：评论

学校读者我要写书评

暂无评论

Research of Microstructure,Phase,and Mechanical Properties of Aluminum-Dross-Based Porous Ceramics

引用

Journal of Renewable Materials 2023年第7期11卷 3057-3072页

作者： Liang Yu Yuan Liu Xiuling Cao Yulong Yan Chen Zhang Yanli Jiang Key Laboratory of New Processing Technology for Nonferrous Metals&Materials Guilin University of TechnologyGuilin541004China Guangxi Scientific Experiment Center of Mining Metallurgy and EnvironmentGuilin University of TechnologyGuilin541004China Collaborative Innovation Center for Exploration of Nonferrous Metal Deposits and Efficient Utilization of Resources Guilin University of TechnologyGuilin541004China Hebei Technology Innovation Center for Intelligent Development and Control of Underground Built Environment School of Exploration Technology and EngineeringHebei GEO UniversityShijiazhuang050031China

In this study,the effect of sintering temperature and the addition of kaolin,a sintering agent,on the microscopic,phase,and mechanical properties of ceramics were investigated using secondary aluminum dross(SAD)as the main component in the manufacturing of *** basic phases of the ceramics were Al_(2)O_(3),MgAl_(2)O_(4),NaAl_(11)O_(17),and SiO_(2)without the addition of *** diffraction peaks of MgAl_(2)O_(4),NaAl_(11)O_(17),and SiO_(2)kept decreasing while those of Al_(2)O_(3)kept increasing with an increase in *** addition,the increase in temperature promoted the growth of the *** grains were uniform in size and regular in distribution,with a shrinkage of 2.2%,porosity of 72.5%,bulk density of 1.076 g/cm^(3),and compressive strength of 1.12 *** the sintering temperature was 1450°C,the basic phases of the ceramic after the addition of kaolin were Al_(2)O_(3),MgAl_(2)O_(4),NaAl_(11)O_(17),and SiO_(2).With the increase of kaolin,the diffraction peaks of NaAl_(11)O_(17)and SiO_(2)decreased until they disappeared,while the diffraction peaks of Al_(2)O_(3)increased *** kaolin was added at 30 wt.%,the ceramics obtained had shrinkage of 18%,a porosity of 47.26%,a bulk density of 1.965 g/cm^(3),and compressive strength of 31.9 *** existed inside the ceramics without the addition of kaolin,while the addition of kaolin significantly changed this *** is shown that SAD can obtain porous ceramics with good properties at a sintering temperature of 1450°C and a kaolin addition of 30 wt.%.

关键词： Secondary aluminum dross porous ceramics microstrure phase mechanical properties

来源：评论

学校读者我要写书评

暂无评论

CondNet: Conditional classifier for scene segmentation

arXiv

引用

arXiv 2021年

作者： Yu, Changqian Shao, Yuanjie Gao, Changxin Sang, Nong Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China

—The fully convolutional network (FCN) has achieved tremendous success in dense visual recognition tasks, such as scene segmentation. The last layer of FCN is typically a global classifier (1×1 convolution) to recognize each pixel to a semantic label. We empirically show that this global classifier, ignoring the intra-class distinction, may lead to sub-optimal results. In this work, we present a conditional classifier to replace the traditional global classifier, where the kernels of the classifier are generated dynamically conditioned on the input. The main advantages of the new classifier consist of: (i) it attends on the intra-class distinction, leading to stronger dense recognition capability;(ii) the conditional classifier is simple and flexible to be integrated into almost arbitrary FCN architectures to improve the prediction. Extensive experiments demonstrate that the proposed classifier performs favourably against the traditional classifier on the FCN architecture. The framework equipped with the conditional classifier (called CondNet) achieves new state-of-the-art performances on two datasets. The code and models are available at https://***/CondNet. Copyright © 2021, The Authors. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Generating Natural Language adversarial examples through an improved beam search algorithm

arXiv

引用

arXiv 2021年

作者： Zhao, Tengfei Ge, Zhaocheng Hu, Hanping Shi, Dingmeng School of Artificial Intelligence and Automation Huazhong University of Science and Technology Key Laboratory of Image Information Processing and Intelligent Control Ministry of Education

The research of adversarial attacks in the text domain attracts many interests in the last few years, and many methods with a high attack success rate have been proposed. However, these attack methods are inefficient as they require lots of queries for the victim model when crafting text adversarial examples. In this paper, a novel attack model is proposed, its attack success rate surpasses the benchmark attack methods, but more importantly, its attack efficiency is much higher than the benchmark attack methods. The novel method is empirically evaluated by attacking WordCNN, LSTM, BiLSTM, and BERT on four benchmark datasets. For instance, it achieves a 100% attack success rate higher than the state-of-the-art method when attacking BERT and BiLSTM on IMDB, but the number of queries for the victim models only is 1/4 and 1/6.5 of the state-of-the-art method, respectively. Also, further experiments show the novel method has a good transferability on the generated adversarial examples. © 2021, CC BY.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Predictor-Based Active Anti-Disturbance control for Multi-Rate control Systems with Delayed Sampled-Data

Predictor-Based Active Anti-Disturbance Control for Multi-Ra...

引用

第40届中国控制会议

作者： Jiankun Sun Zhigang Zeng the School of Artificial Intelligence and Automation Huazhong University of Science and Technology the Key Laboratory of Image Processing and Intelligent Control of Education Ministry of China

In this paper, we consider the problem of sampleddata active anti-disturbance control design for multi-rate control system subject to delayed sampled-data output. The plant considered in this paper is equipped with a slow-rate sensor and a fastrate actuator. In the presence of non-vanishing disturbance, a new output predictor-based observer is first proposed by only using the delayed sampled-data output, so as to effectively estimate system state and disturbance in the inter-sample time interval.A new sampled-data controller that updates at a fast-rate is then designed with the help of active anti-disturbance *** to prediction and active anti-disturbance techniques, the proposed sampled-data control method can effectively reject the influence of non-vanishing disturbance despite slow-rate sampling and delay of sensor. Finally, the effectiveness of the proposed control method is demonstrated via simulation results of a practical example of the visual servoing control for an inertially stabilized platform.

关键词： Sample-data active anti-disturbance control output delay multi-rate control system

来源：评论

学校读者我要写书评

暂无评论

SMTC-CL: Continuous Learning via Selective Multi-Task Coordination for Adaptive Signal Classification

引用

IEEE Transactions on Cognitive Communications and Networking 2024年

作者： Hao, Xiaoyang Yang, Shuyuan Liu, Ruoyu Feng, Zhixi Peng, Tongqing Huang, Bincheng Xidian University Key Laboratory of Intelligent Perception and Image Understanding Ministry of Education School of Artificial Intelligence Xi'an710071 China Avic Xi'an Flight Automatic Control Research Institute China MeiTuan China China Electronics Technology Group Corporation Institute of Information Science and Technology China

Continuously adaptive signal classification in complex electromagnetic environments is a desired property of realistic intelligent systems. However, the limitation of most existing signal processing tasks and methods lies in their assumption of fixed categories and invariant distributions. In contrast, humans naturally acquire knowledge continuously from data streams, enhancing their capabilities through cross-task knowledge integration and learning from the past. Inspired by this, we propose a continuous learning (CL) method based on selective multi-task coordination (SMTC) to deal with ever-changing task categories and distributions in practical electromagnetic environments (denoted as SMTC-CL). Firstly, we propose a signal task distribution comparison (TDC) method that leverages intra-domain density and inter-domain divergence. TDC selectively activates multiple old tasks to collaboration with the current incremental new task. Secondly, we propose the SMTC method. By revisiting potential collaborative tasks from the past using TDC and formulating different selection strategies based on the context, continuous learners can achieve mutual benefits between past and current tasks in SMTC learning. SMTC can partially alleviate catastrophic forgetting and enable continuous learners to adapt to the changing electromagnetic environment. Based on the signal automatic modulation classification (AMC) and real-world specific emitter identification (SEI) datasets, extensive experimental results validate the effectiveness of our proposed method on a variety of CL scenarios, including varying signal task categories, distributions, and their combinations. © 2015 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Nonlinear Active Disturbance Rejection control for Vehicle Active Suspension System

Nonlinear Active Disturbance Rejection Control for Vehicle A...

引用

Electronic Information Engineering and Computer Science (EIECS), 2021 International Conference on

作者： Xianglian Dai Chunzhe Zhao Rong Xu School of Electronics and Information Engineering Chongqing Three Gorges University Wanzhou China Chongqing Engineering Research Center of Internet of Things and Intelligent Control Technology Key Laboratory of Intelligent Information Processing and Control of Chongqing Municipal Institutions of Higher Education Chongqing Three Gorges University Wanzhou China

Nonlinear active disturbance rejection control (ADRC) is designed for the suspension system of the quarter vehicle model with the two-degree freedom. It is compared with other active suspension systems based on PID and linear ADRC scheme. The variance of the errors reveals that the nonlinear ADRC suspension system promotes the vehicle acceleration, the suspension dynamic disturbance, and wheel dynamic load.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Active Landing Recovery Method for Quadrotor UAV: Localization, Tracking and Buffering Landing

引用

IFAC-PapersOnLine 2023年第2期56卷 3366-3372页

作者： Yongkang Xu Zhihua Chen Shoukun Wang Junzheng Wang National Key Lab of Autonomous Intelligent Unmanned Systems Beijing Institute of Technology Beijing CO 100081 P.R.China Key Laboratory of Jiangxi Province for Image Processing and Pattern Recognition and MOE Key Lab of Nondestructive Testing Technology School of Information Engineering Nanchang Hangkong University Nanchang CO 330063 P.R. China

This paper proposes a principle of fully autonomous ground mobile landing recovery of Unmanned Aerial Vehicles (UAV) for the problems of relatively fixed landing point, passive recovery, poor flexibility, and environmental adaptability, which mainly includes localization, landing point tracking, and buffering landing for quadrotor UAV. Firstly, aiming at the problem that it is difficult to accurately obtain the position of a UAV in dynamic mobile landing recovery, a target location method based on Asynchronous Multisensor Information Fusion(AMIF) and servo turntable focus tracking is proposed. Secondly, to achieve fast and high-precision tracking of UAVs, a tracking control strategy of an independently driven landing recovery system and a Stewart six-degree of freedom platform is proposed. Then, to solve the problems of large impact force and center of gravity instability in the landing process of UAV, a stationarity control algorithm based on model prediction and a compliance control algorithm based on adaptive variable impedance are designed to achieve active compliance control while adjusting the position and attitude of the receiving surface in real-time. Finally, a quadrotor unmanned landing and recovery experimental platform is built to verify the feasibility of the ground mobile landing and recovery strategy proposed in this paper and the effectiveness of the control algorithm.

关键词： Quadrotor UAV Mobile Autonomous recovery Target localization Falling point tracking Buffering landing

来源：评论

学校读者我要写书评

暂无评论

Missile-Target Situation Assessment Model Based on Reinorcement Learning

引用

Journal of Shanghai Jiaotong university(Science) 2020年第5期25卷 561-568页

作者： ZHANG Yun LU Runyan CAI Yunze Department of Automation Key Laboratory of System Control and Information Processing of Ministry of EducationKey Laboratory of Marine Intelligent Equipment and System of Ministry of EducationShanghai Jiao Tong UniversityShanghai 200240China

In situation assessment(SA)of missile versus target fighter,the traditional SA models generally have the characteristics of strong subjectivity and poor dynamic *** paper considers SA as an expectation of future returns and establishes a missile-target simulation battle *** actor-critic(AC)algorithm in reinforcement learning(RL)is used to train the evaluation network,and a missile-target SA model is established in simulation battle *** and comparative experiments show that the model can effectively estimate the expected effect of missile attack under the current situation,and it provides an effective basis for missile attack decision.

关键词： situation assessment(SA) battle model reinforcement learning(RL) actor-critic(AC)algorithm

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：