检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Wang, Jingyao Guo, Huijie Qiang, Wenwen Li, Jiangmeng Zheng, Changwen Xiong, Hui Hua, Gang University of Chinese Academy of Sciences Beijing China National Key Laboratory of Space Integrated Information System Institute of Software Chinese Academy of Sciences Beijing China Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing China Thrust of Artificial Intelligence Hong Kong University of Science and Technology Guangzhou China Department of Computer Science and Engineering The Hong Kong University of Science and Technology Hong Kong Wormpex AI Research LLC BellevueWA98004 United States

Humans excel at adapting perceptions and actions to diverse environments, enabling efficient interaction with the external world. This adaptive capability relies on the biological nervous system (BNS), which activates different brain regions for distinct tasks. Meta-learning similarly trains machines to handle multiple tasks but relies on a fixed network structure, not as flexible as BNS. To investigate the role of flexible network structure (FNS) in meta-learning, we conduct extensive empirical and theoretical analyses, finding that model performance is tied to structure, with no universally optimal pattern across tasks. This reveals the crucial role of FNS in meta-learning, ensuring meta-learning to generate the optimal structure for each task, thereby maximizing the performance and learning efficiency of meta-learning. Motivated by this insight, we propose to define, measure, and model FNS in meta-learning. First, we define that an effective FNS should possess frugality, plasticity, and sensitivity. Then, to quantify FNS in practice, we present three measurements for these properties, collectively forming the structure constraint with theoretical supports. Building on this, we finally propose Neuromodulated Meta-Learning (NeuronML) to model FNS in meta-learning. It utilizes bi-level optimization to update both weights and structure with the structure constraint. Extensive theoretical and empirical evaluations demonstrate the effectiveness of NeuronML on various tasks. Code is publicly available at https://***/WangJingyao07/NeuronML. Copyright © 2024, The Authors. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Attributes guided feature learning for vehicle re-identification

arXiv

引用

arXiv 2019年

作者： Li, Hongchao Lin, Xianmin Zheng, Aihua Li, Chenglong Luo, Bin He, Ran Hussain, Amir School of Computer Science and Technology Anhui University Hefei230601 China Information Materials and Intelligent Sensing Laboratory of Anhui Province Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Artificial Intelligence Anhui University Hefei230601 China Institute of Automation Chinese Academy of Sciences Beijing100190 China Edinburgh Napier University School of Computing EdinburghEH10 5DT United Kingdom

Vehicle Re-ID has recently attracted enthusiastic attention due to its potential applications in smart city and urban surveillance. However, it suffers from large intra-class variation caused by view variations and illumination changes, and inter-class similarity especially for different identities with a similar appearance. To handle these issues, in this paper, we propose a novel deep network architecture, which guided by meaningful attributes including camera views, vehicle types and colors for vehicle Re-ID. In particular, our network is end-to-end trained and contains three subnetworks of deep features embedded by the corresponding attributes. For network training, we annotate the view labels on the VeRi-776 dataset. Note that one can directly adopt the pre-trained view (as well as type and color) subnetwork on the other datasets with only ID information, which demonstrates the generalization of our model. Extensive experiments on the benchmark datasets VeRi-776 and VehicleID suggest that the proposed approach achieves the promising performance and yields to a new state-of-the-art for vehicle Re-ID. Copyright © 2019, The Authors. All rights reserved.

关键词： Vehicles

来源：评论

学校读者我要写书评

暂无评论

GenFace: A Large-Scale Fine-Grained Face Forgery Benchmark and Cross Appearance-Edge Learning

arXiv

引用

arXiv 2024年

作者： Zhang, Yaning Yu, Zitong Wang, Tianyi Huang, Xiaobin Shen, Linlin Gao, Zan Ren, Jianfeng Computer Vision Institute College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China School of Computing and Information Technology Great Bay University Dongguan523000 China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen518060 China Nanyang Technological University 50 Nanyang Ave Block N 4 639798 Singapore Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen518129 China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University China Jinan250014 China Key Laboratory of Computer Vision and System Ministry of Education Tianjin University of Technology Tianjin300384 China School of Computer Science University of Nottingham Ningbo China

The rapid advancement of photorealistic generators has reached a critical juncture where the discrepancy between authentic and manipulated images is increasingly indistinguishable. Thus, benchmarking and advancing techniques detecting digital manipulation become an urgent issue. Although there have been a number of publicly available face forgery datasets, the forgery faces are mostly generated using GAN-based synthesis technology, which does not involve the most recent technologies like diffusion. The diversity and quality of images generated by diffusion models have been significantly improved and thus a much more challenging face forgery dataset shall be used to evaluate SOTA forgery detection literature. In this paper, we propose a large-scale, diverse, and fine-grained high-fidelity dataset, namely GenFace, to facilitate the advancement of deepfake detection, which contains a large number of forgery faces generated by advanced generators such as the diffusion-based model and more detailed labels about the manipulation approaches and adopted generators. In addition to evaluating SOTA approaches on our benchmark, we design an innovative Cross Appearance-Edge Learning (CAEL) detector to capture multi-grained appearance and edge global representations, and detect discriminative and general forgery traces. Moreover, we devise an Appearance-Edge Cross-Attention (AECA) module to explore the various integrations across two domains. Extensive experiment results and visualizations show that our detection model outperforms the state of the arts on different settings like cross-generator, cross-forgery, and cross-dataset evaluations. Code and datasets will be available at https://***/Jenine-321/GenFace. Copyright © 2024, The Authors. All rights reserved.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Efficient Image Super-Resolution with Feature Interaction Weighted Hybrid Network

arXiv

引用

arXiv 2022年

作者： Li, Wenjie Li, Juncheng Gao, Guangwei Deng, Weihong Yang, Jian Qi, Guo-Jun Lin, Chia-Wen Pattern Recognition and Intelligent System Laboratory School of Artificial Intelligence Beijing University of Posts and Telecommunications Beijing100080 China Intelligent Visual Information Perception Laboratory Institute of Advanced Technology Nanjing University of Posts and Telecommunications Nanjing210046 China Key Laboratory of Artificial Intelligence Ministry of Education Shanghai200240 China Provincial Key Laboratory for Computer Information Processing Technology Soochow University Suzhou215006 China School of Communication and Information Engineering Shanghai University Shanghai200444 China School of Computer Science and Technology Nanjing University of Science and Technology Nanjing210094 China Research Center for Industries of the Future the School of Engineering Westlake University Hangzhou310024 China OPPO Research SeattleWA98101 United States Department of Electrical Engineering National Tsing Hua University Hsinchu30013 Taiwan

Lightweight image super-resolution aims to reconstruct high-resolution images from low-resolution images using low computational costs. However, existing methods result in the loss of middle-layer features due to activation functions. To minimize the impact of intermediate feature loss on reconstruction quality, we propose a Feature Interaction Weighted Hybrid Network (FIWHN), which comprises a series of Wide-residual Distillation Interaction Block (WDIB) as the backbone. Every third WDIB forms a Feature Shuffle Weighted Group (FSWG) by applying mutual information shuffle and fusion. Moreover, to mitigate the negative effects of intermediate feature loss, we introduce Wide Residual Weighting units within WDIB. These units effectively fuse features of varying levels of detail through a Wide-residual Distillation Connection (WRDC) and a Self-Calibrating Fusion (SCF). To compensate for global feature deficiencies, we incorporate a Transformer and explore a novel architecture to combine CNN and Transformer. We show that our FIWHN achieves a favorable balance between performance and efficiency through extensive experiments on low-level and high-level tasks. Codes will be available at https://***/IVIPLab/FIWHN. Copyright © 2022, The Authors. All rights reserved.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

S4TP: Social-Suitable and Safety-Sensitive Trajectory Planning for Autonomous Vehicles

arXiv

引用

arXiv 2024年

作者： Wang, Xiao Tang, Ke Dai, Xingyuan Xu, Jintao Du, Quancheng Ai, Rui Wang, Yuxiao Gu, Weihao Engineering Research Center of Autonomous Unmanned System Technology Ministry of Education Anhui University Hefei230031 China Haomo Technology Co. Ltd. Beijing100192 China The State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China Qingdao Academy of Intelligent Industries Qingdao266114 China The School of Computer and Communication Engineering University of Science and Technology Beijing Beijing100083 China The School of Artificial Intelligence University of Chinese Academy of Sciences Beijing100049 China

In public roads, autonomous vehicles (AVs) face the challenge of frequent interactions with human-driven vehicles (HDVs), which render uncertain driving behavior due to varying social characteristics among humans. To effectively assess the risks prevailing in the vicinity of AVs in social interactive traffic scenarios and achieve safe autonomous driving, this article proposes a social-suitable and safety-sensitive trajectory planning (S4TP) framework. Specifically, S4TP integrates the Social-Aware Trajectory Prediction (SATP) and Social-Aware Driving Risk Field (SADRF) modules. SATP utilizes Transformers to effectively encode the driving scene and incorporates an AV’s planned trajectory during the prediction decoding process. SADRF assesses the expected surrounding risk degrees during AVs-HDVs interactions, each with different social characteristics, visualized as two-dimensional heat maps centered on the AV. SADRF models the driving intentions of the surrounding HDVs and predicts trajectories based on the representation of vehicular interactions. S4TP employs an optimization-based approach for motion planning, utilizing the predicted HDVs’ trajectories as input. With the integration of SADRF, S4TP executes real-time online optimization of the planned trajectory of AV within low-risk regions, thus improving the safety and the interpretability of the planned trajectory. We have conducted comprehensive tests of the proposed method using the SMARTS simulator. Experimental results in complex social scenarios, such as unprotected left-turn intersections, merging, cruising, and overtaking, validate the superiority of our proposed S4TP in terms of safety and rationality. S4TP achieves a pass rate of 100% across all scenarios, surpassing the current state-of-the-art methods Fanta of 98.25% and Predictive-Decision of 94.75%. Copyright © 2024, The Authors. All rights reserved.

关键词： Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

Improved adaptive buffer replacement algorithm used for second level buffer

引用

Jisuanji Yanjiu yu Fazhan/Computer Research and Development 2007年第8期44卷 1331-1338页

作者： Sun, Guozhong Yuan, Qingbo Chen, Mingyu Fan, Jianping National Research Center for Intelligent Computing Systems Institute of Computing Technology Chinese Acad. of Sci. Beijing 100080 China Graduate University Chinese Acad. of Sci. Beijing 100049 China Key Laboratory of Computer System and Architecture Chinese Acad. of Sci. Beijing 100080 China Institute of Computing Technology Chinese Acad. of Sci. Beijing 100080 China

In a cluster or a database server system, the performance of some data intensive applications will be degraded much because of the limited local memory and large amount of interactions with slow disk. In high speed network, utilizing remote memory of other nodes or customized memory server to be as second level buffer can decrease access numbers to disks and benefit application performance. With second level buffer mode, this paper made some improvements for a recently proposed buffer cache replacement algorithm-LIRS, and brings forward an adaptive algorithm-LIRS-A. LIRS-A can adaptively adjust itself according to application characteristic, thus the problem of not suiting for time locality of LIRS is avoided. In TPC-H benchmarks, LIRS-A could improve hit rate over LIRS by 7.2% at most. In a Groupby query with network stream analyzing database, LIRS-A could improve hit rate over LIRS by 31.2% at most. When compared with other algorithms, LIRS-A also show similar or better performance.

关键词： Buffer storage

来源：评论

学校读者我要写书评

暂无评论

Multi-robot Path Planning and Trajectory Smoothing

Multi-robot Path Planning and Trajectory Smoothing

引用

IEEE International Conference on Automation Science and Engineering (CASE)

作者： Hub Ali Gang Xiong Huaiyu Wu Bin Hu Zhen Shen Hongxing Bai School of Mechanical and Electrical Engineering University of Electronic Science and Technology of China State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China Guangdong Engineering Research Center of 3D Printing and Intelligent Manufacturing Cloud Computing Center Chinese Academy of Sciences Dongguan China Beijing Engineering Research Center of Intelligent Systems and Technology Institute of Automation Chinese Academy of Sciences China Hubei Jointown Technology Co. Ltd Artificial Intelligence Research Institute Wuhan China

ISBN: (数字)9781728169040

ISBN: (纸本)9781728169057

In this paper we consider a problem in task execution for multi-robot trajectory planning with collision avoidance in a shared working environment. Consider two or more robots generating trajectories towards their respective goal positions. The collision may occur if their trajectory coordinates are intersecting at a point or follow the same path segment simultaneously. The central planner is introduced to control robot motion in the collision state and to reduce the complexity of the multi-robot path planning system. The global path for every robot is generated by the $\mathrm{A}^{*}$ algorithm in a grid-based environment. The path has presented a sequence of optimal grid numbers and later transformed into Cartesian coordinates for smooth trajectory generation. The central planner takes an optimal grid sequence for every robot to analyze the collision state according to its cost value. It regenerates the trajectories to minimize the complexity cost value and replaces the previous trajectory based on minimum cost value. In the collision state, the central planner allows one robot at a time to pass along the conflict path segment and hold others in queue at a safety offset distance until the previous robot passes safely. The algorithm has been applied to robots working in a shared environment in complex maps and the simulations is performed with MATLAB to calculate the efficiency of this approach for handling collision states in a multi-robot path planning system.

关键词： Robot kinematics Trajectory Collision avoidance Task analysis Resource management

来源：评论

学校读者我要写书评

暂无评论

A lightweight soft exoskeleton in lower limb assistance

A lightweight soft exoskeleton in lower limb assistance

引用

Chinese Automation Congress (CAC)

作者： Yu Zhang Zhuo Wang Chunjie Chen Tao Fang Ruimei Sun Yanjie Li School of Mechanical Engineering and Automation Harbin Institute of Technology Shenzhen China Guangdong Provincial Key Lab of Robotics and Intelligent System Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen China CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institutes of Advanced Technology Shenzhen China ShenZhen College of Advanced Technology University of Chinese Academy of Sciences Shenzhen China BeiJing Aerospace Wanyuan Science Technology Co. Ltd. Beijing China

ISBN: (数字)9781728176871

ISBN: (纸本)9781728176888

The soft exoskeleton is a wearable robot which is functioned to improve the capacity of human walking or loading. The metabolic of human is increase with the additional load, one integrated design method is used to reduce this effect in this paper. Meanwhile, in order to enhance the convenience and decrease the disturbance to wearer, the wireless module is used to replace the signal line. The nonlinear characteristics and uncertainty of flexible material make the control of soft exoskeleton system be a challenge, a switching controller is proposed to deal with this problem in this paper. It consists of Iterative learning control (ILC) based stable controller and admittance control based unstable controller, functioned with wearers walking stable and not. An experiment of force tracking is conducted to verify the controller performance in this paper, and the result demonstrate that the tracking is well after 20 iteration. In order to evaluate the performance of assistance of soft exoskeleton, five health adult male take part in metabolic experiment By compare the metabolic rate between the wear soft exoskeleton and not wear, the metabolic rate are decrease 7.33%, 14.56% and 10.45% with the walking speed of 3km/h, 5km/h and 7km/h, which are corresponding absolute values decrease of 0.46W/kg, 1.60W/kg and 1.21W/kg respectively.

关键词： AC motors Mechanical cables Wireless communication Pulleys Microprocessors Micromechanical devices Germanium

来源：评论

学校读者我要写书评

暂无评论

Privacy-Preserving Federated Learning Framework with Resisting Source Inference Attacks in Smart Healthcare

SSRN

引用

SSRN 2024年

作者： Chenghe, Dong Xu, Guangquan Zhang, Jianhong Bai, Hongpeng Hao, Peng College of Intelligence and Computing Tianjin University Tianjin300354 China School of Big Data Qingdao Huanghai University Qingdao China Tianjin300350 China Department of Electrical and Computer Engineering North China University of Technology Beijing100144 China Key Laboratory of Intelligent Education Technology Application of Zhejiang Province School of Computer Science and Technology Zhejiang Normal University Jinhua321004 China

Federated Learning (FL) is a distributed machine learning technology that is extensive applications in smart healthcare, since it allows multiple medical institutions to jointly train medical diagnostic models without sharing their local sensitive dataset with others. Despite its benefits, FL is susceptible to source inference attacks and model poisoning. To avoid these issues, we propose a federated learning framework for smart healthcare that preserves privacy and employs certificateless ring signatures to counteract potential attacks. During the collaborative training process of the FL model, certificateless ring signatures are used to obscure the origin of parameter updates, ensuring the anonymity of the parameter sources. This approach has the advantage of being computationally efficient due to no complicated pairing operations. Furthermore, compared with the previous certificateless ring signature schemes, our proposed scheme is more effective in reducing the success rate of source inference attacks, and is efficient in terms of computation and communication overhead. © 2024, The Authors. All rights reserved.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Double Deep Q-learning for Anti-saturation Attack Problem of Warship Group

Double Deep Q-learning for Anti-saturation Attack Problem of...

引用

Digital Twins and Parallel intelligence (DTPI), IEEE International Conference on

作者： Wei Li Gang Xiong Hao Tao Yunjun Han Fang Wang Xisong Dong Zhen Shen State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences School of Artificial Intelligence University of Chinese Academy of Sciences Beijing Engineering Research Center of Intelligent Systems and Technology Institute of Automation Guangdong Engineering Research Center of 3D Printing and Intelligent Manufacturing Cloud Computing Center Chinese Academy of Sciences China China Ship Development and Design Center Wuhan China School of Control Science and Engineering (CSE) Shandong University Jinan China Guangdong Engineering Research Center of 3D Printing and Intelligent Manufacturing Cloud Computing Center Chinese Academy of Sciences Dongguan China

Anti-saturation attack (ASA) strategy is vital for the survival of a warship group, and attracts the focus of many researchers. In this paper, the dynamics of ASA is formulated as a Markov Decision Process (MDP) with an enhanced states space since those characters are involved, such as the formation and detection and interception areas of warship group. A reinforcement learning method (Double Deep Q-leaning, DDQN) is developed to solve the problem and deal with the curse of dimensionality whereby the cost-to-go value is calculated by a marine engagement simulation system. A heuristic defense algorithm guided by field expert knowledge is designed for comparison. The experimental results show that the DDQN method performs better in anti-saturation attack scenarios.

关键词： Industries Heuristic algorithms Digital twin Conferences Knowledge based systems Reinforcement learning Markov processes

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：