检索结果-内蒙古大学图书馆

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Pang, Chao Weng, Xingxing Wu, Jiang Li, Jiayu Liu, Yi Sun, Jiaxing Li, Weijia Wang, Shuai Feng, Litong Xia, Gui-Song He, Conghui School of Artificial Intelligence Wuhan University China Shanghai Artificial Intelligence Laboratory China School of Computer Science Wuhan University China Sun Yat-Sen University China Sensetime Research China State Key Lab. of LIESMARS Wuhan University China Institue for Math and AI Wuhan University China

ISBN: (纸本)157735897X

This paper develops a Versatile and Honest vision language Model (VHM) for remote sensing image analysis. VHM is built on a large-scale remote sensing image-text dataset with rich-content captions (VersaD), and an honest instruction dataset comprising both factual and deceptive questions (HnstD). Unlike prevailing remote sensing image-text datasets, in which image captions focus on a few prominent objects and their relationships, VersaD captions provide detailed information about image properties, object attributes, and the overall scene. This comprehensive captioning enables VHM to thoroughly understand remote sensing images and perform diverse remote sensing tasks. Moreover, different from existing remote sensing instruction datasets that only include factual questions, HnstD contains additional deceptive questions stemming from the non-existence of objects. This feature prevents VHM from producing affirmative answers to nonsense queries, thereby ensuring its honesty. In our experiments, VHM significantly outperforms various vision language models on common tasks of scene classification, visual question answering, and visual grounding. Additionally, VHM achieves competent performance on several unexplored tasks, such as building vectorizing, multi-label classification and honest question answering. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Photointerpretation

来源：评论

学校读者我要写书评

暂无评论

Advswap: Covert Adversarial Perturbation with High Frequency Info-Swapping for Autonomous Driving Perception

Advswap: Covert Adversarial Perturbation with High Frequency...

引用

International Conference on Intelligent Transportation

作者： Yuanhao Huang Qinfan Zhang Jiandong Xing Mengyue Cheng Haiyang Yu Yilong Ren Xiao Xiong School of Transportation Science and Engineering Beihang University Beijing P.R.China State Key Lab of Intelligent Transportation System Beijing P.R.China Zhongguancun Laboratory Beijing P.R.China Department of Electrical and Computer Engineering University of Alberta Edmonton Canada

ISBN: (数字)9798331505929

ISBN: (纸本)9798331505936

Perception module of Autonomous vehicles (AVs) are increasingly susceptible to be attacked, which exploit vulnerabilities in neural networks through adversarial inputs, thereby compromising the AI safety. Some researches focus on creating covert adversarial samples, but existing global noise techniques are detectable and difficult to deceive the human visual system. This paper introduces a novel adversarial attack method, AdvSwap, which creatively utilizes wavelet-based highfrequency information swapping to generate covert adversarial samples and fool the camera. AdvSwap employs invertible neural network for selective high-frequency information swapping, preserving both forward propagation and data integrity. The scheme effectively removes the original label data and incorporates the guidance image data, producing concealed and robust adversarial samples. Experimental evaluations and comparisons on the GTSRB and nuScenes datasets demonstrate that AdvSwap can make concealed attacks on common traffic targets. The generates adversarial samples are also difficult to perceive by humans and algorithms. Meanwhile, the method has strong attacking robustness and attacking transferability.

关键词： Wavelet transforms Training Neural networks Noise Visual systems Robustness Classification algorithms Data mining Information exchange Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

Beyond Model Scale Limits: End-Edge-Cloud Federated Learning with Self-Rectified Knowledge Agglomeration

arXiv

引用

arXiv 2024年

作者： Wu, Zhiyuan Sun, Sheng Wang, Yuwei Liu, Min Xu, Ke Pan, Quyang Gao, Bo Wen, Tian The State Key Lab of Processers Institute of Computing Technology Chinese Academy of Sciences Beijing China The University of Chinese Academy of Sciences Beijing China The Zhongguancun Laboratory Beijing China The Department of Computer Science and Technology Tsinghua University Beijing China The School of Computer Science and Technology The Engineering Research Center of Network Management Technology for High-Speed Railway of Ministry of Education Beijing Jiaotong University Beijing China

The rise of End-Edge-Cloud Collaboration (EECC) offers a promising paradigm for Artificial Intelligence (AI) model training across end devices, edge servers, and cloud data centers, providing enhanced reliability and reduced latency. Hierarchical Federated Learning (HFL) can benefit from this paradigm by enabling multi-tier model aggregation across distributed computing nodes. However, the potential of HFL is significantly constrained by the inherent heterogeneity and dynamic characteristics of EECC environments. Specifically, the uniform model structure bounded by the least powerful end device across all computing nodes imposes a performance bottleneck. Meanwhile, coupled heterogeneity in data distributions and resource capabilities across tiers disrupts hierarchical knowledge transfer, leading to biased updates and degraded performance. Furthermore, the mobility and fluctuating connectivity of computing nodes in EECC environments introduce complexities in dynamic node migration, further compromising the robustness of the training process. To address multiple challenges within a unified framework, we propose End-Edge-Cloud Federated Learning with Self-Rectified Knowledge Agglomeration (FedEEC), which is a novel EECC-empowered FL framework that allows the trained models from end, edge, to cloud to grow larger in size and stronger in generalization ability. FedEEC introduces two key innovations: (1) Bridge Sample Based Online Distillation Protocol (BSBODP), which enables knowledge transfer between neighboring nodes through generated bridge samples, and (2) Self-Knowledge Rectification (SKR), which refines the transferred knowledge to prevent suboptimal cloud model optimization. The proposed framework effectively handles both cross-tier resource heterogeneity and effective knowledge transfer between neighboring nodes, while satisfying the migration-resilient requirements of EECC. Extensive experiments on three datasets demonstrate that FedEEC achieves significantly hi

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Insulin-resistance and depression cohort data mining to identify nutraceutical related DNA methylation biomarker for type 2 diabetes

引用

Genes & Diseases 2021年第5期8卷 669-676页

作者： Fengji Liang Yuan Quan Andong Wu Ying Chen Ruifeng Xu Yuexing Zhu Jianghui Xiong Lab of Epigenetics and Advanced Health Technology SPACEnter Space Science and Technology InstituteShenzhenGuangdong Province518117PR China State Key Laboratory of Space Medicine Fundamentals and Application China Astronaut Research and Training CenterBeijing100094PR China School of Computer Science and Technology Harbin Institute of Technology Shenzhen Graduate SchoolShenzhenGuangdong Province518055PR China

Insulin-resistance(IR)is one of the most important precursors of type 2 diabetes(T2D).Recent evidence suggests an association of depression with the onset of ***-lating evidence shows that depression and T2D share common biological origins,and DNA methylation examination might reveal the link between lifestyle,disease risk,and potential therapeutic targets for *** we hypothesize that integrative mining of IR and depression cohort data will facilitate predictive biomarkers identification for *** utilized a newly proposed method to extract gene-level information from probe level data on genome-wide DNA methylation *** identified a set of genes associated with IR and depression in clin-ical *** overlapping the IR-related nutraceutical-gene network with depression net-works,we identified a common subnetwork centered with Vitamin D Receptor(VDR)*** clinical validation of gene methylation set in a small cohort of T2D patients and controls was established using the Sequenome matrix-assisted laser desorption ionization-time flight mass spectrometry.A set of sites in the promoter regions of VDR showed a signifi-cant difference between T2D patients and *** a logistic regression model,the optimal prediction performance of these sites was AUC Z 0.902,and an odds ratio Z ***,monitoring the methylation status of specific VDR promoter region might help stratify the high-risk individuals who could potentially benefit from vitamin D dietary *** results highlight the link between IR and depression,and the DNA methyl-ation analysis might facilitate the search for their shared mechanisms in the etiology of T2D.

关键词： Depression DNA methylation Insulin resistance Nutraceuticals Type 2 Diabetes Vitamin D receptor

来源：评论

学校读者我要写书评

暂无评论

High-Throughput GPU Implementation of Dilithium Post-Quantum Digital Signature

arXiv

引用

arXiv 2022年

作者： Shen, Shiyu Yang, Hao Dai, Wangchen Zhang, Hong Liu, Zhe Zhao, Yunlei School of Computer Science Fudan University Shanghai China College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing China Research Institute of Basic Theories Zhejiang lab Hangzhou China State Key Laboratory of Cryptology Beijing China

Digital signatures are fundamental building blocks in various protocols to provide integrity and authenticity. The development of the quantum computing has raised concerns about the security guarantees afforded by classical signature schemes. CRYSTALS-Dilithium is an efficient post-quantum digital signature scheme based on lattice cryptography and has been selected as the primary algorithm for standardization by the National Institute of Standards and Technology. In this work, we present a high-throughput GPU implementation of Dilithium. For individual operations, we employ a range of computational and memory optimizations to overcome sequential constraints, reduce memory usage and IO latency, address bank conflicts, and mitigate pipeline stalls. This results in high and balanced compute throughput and memory throughput for each operation. In terms of concurrent task processing, we leverage task-level batching to fully utilize parallelism and implement a memory pool mechanism for rapid memory access. Considering the impact of varying repetition numbers in Dilithium on the overall execution time and hardware utilization, we propose a dynamic task scheduling mechanism to improve multiprocessor occupancy and significantly reduce execution time. Furthermore, we apply asynchronous computing and launch multiple streams to hide data transfer latencies and maximize the computing capabilities of both CPU and GPU. For Dilithium2, our implementation demonstrates throughputs of 575k and 1409k operations per second for signing and verification procedures, respectively, on an A100 GPU, corresponding to 111× and 69× speedups over a single-thread CPU implementation. Across all three security levels, our GPU implementation can concurrently compute ten thousand tasks in less than 32 miliseconds for signing and 15 miliseconds for verification on both commercial and server-grade GPUs. This achieves microsecond-level amortized execution times for each task, offering a high-throughput an

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

Contour detection in Cassini ISS images based on Hierarchical Extreme Learning Machine and Dense Conditional Random Field

引用

Research in Astronomy and Astrophysics 2020年第1期20卷 83-92页

作者： Xi-Qi Yang Qing-Feng Zhang Zhan Li Department of Computer Science Jinan UniversityGuangzhou 510632China State Key Lab of CAD&CG Zhejiang UniversityHangzhou 310000China Sino-French Joint Laboratory for Astrometry Dynamics and Space ScienceJinan UniversityGuangzhou 510632China

In Cassini ISS(Imaging science Subsystem)images,contour detection is often performed on disk-resolved objects to accurately locate their ***,contour detection is a key *** edge detection methods,such as Canny and Roberts,often extract the contour with too much interior details and *** the deep convolutional neural network has been applied successfully in many image tasks,such as classification and object detection,it needs more time and computer *** this paper,a contour detection algorithm based on H-ELM(Hierarchical Extreme Learning Machine)and Dense CRF(Dense Conditional Random Field)is proposed for Cassini ISS *** experimental results show that this algorithm’s performance is better than both traditional machine learning methods,such as Support Vector Machine,Extreme Learning Machine and even deep Convolutional Neural *** extracted contour is closer to the actual ***,it can be trained and tested quickly on the general configuration of PC,and thus can be applied to contour detection for Cassini ISS images.

关键词： techniques:image processing methods:data analysis astrometry

来源：评论

学校读者我要写书评

暂无评论

DRL-Based Optimization for AoI and Energy Consumption in C-V2X Enabled IoV

IEEE Transactions on Green Communications and Networking

引用

IEEE Transactions on Green Communications and Networking 2025年

作者： Zhang, Zheng Wu, Qiong Fan, Pingyi Cheng, Nan Chen, Wen Letaief, Khaled B. Jiangnan University School of Internet of Things Engineering Wuxi214122 China Tsinghua University Beijing National Research Center for Information Science and Technology Department of Electronic Engineering State Key laboratory of Space Network and Communications Tsinghua University Beijing100084 China Xidian University State Key Lab. of ISN School of Telecom-munications Engineering Xi'an710071 China Shanghai Jiao Tong University Department of Electronic Engineering Shanghai200240 China Department of Electrical and Computer Engineer-ing Hong Kong

To address communication latency issues, the Third Generation Partnership Project (3GPP) has defined Cellular-Vehicle to Everything (C-V2X) technology, which includes Vehicle-to-Vehicle (V2V) communication for direct vehicle-to-vehicle communication. However, this method requires vehicles to autonomously select communication resources based on the Semi-Persistent Scheduling (SPS) protocol, which may lead to collisions due to different vehicles sharing the same communication resources, thereby affecting communication effectiveness. Non-Orthogonal Multiple Access (NOMA) is considered a potential solution for handling large-scale vehicle communication, as it can enhance the Signal-to-Interference-plus-Noise Ratio (SINR) by employing Successive Interference Cancellation (SIC), thereby reducing the negative impact of communication collisions. When evaluating vehicle communication performance, traditional metrics such as reliability and transmission delay present certain contradictions. Introducing the new metric Age of Information (AoI) provides a more comprehensive evaluation of communication system. Additionally, to ensure service quality, user terminals need to possess high computational capabilities, which may lead to increased energy consumption, necessitating a trade-off between communication energy consumption and effectiveness. Given the complexity and dynamics of communication systems, Deep Reinforcement Learning (DRL) serves as an intelligent learning method capable of learning optimal strategies in dynamic environments. Therefore, this paper analyzes the effects of multi-priority queues and NOMA on AoI in the C-V2X vehicular communication system and proposes an energy consumption and AoI optimization method based on DRL. Finally, through comparative simulations with baseline methods, the proposed approach demonstrates its advances in terms of energy consumption and AoI. © 2017 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

VIPeR: Visual Incremental Place Recognition with Adaptive Mining and Continual Learning

arXiv

引用

arXiv 2024年

作者： Ming, Yuhang Xu, Minyang Yang, Xingrui Ye, Weicai Wang, Weihan Peng, Yong Dai, Weichen Kong, Wanzeng School of Computer Science Hangzhou Dianzi University Key Laboratory of Brain Machine Collaborative Intelligence of Zhejiang Province Hangzhou310018 China High-speed Aerodynamics Institute CARDC Mianyang621000 China State Key Lab of CAD&CG Zhejiang University Hangzhou310058 China Stevens Institute of Technology HobokenNJ07030 United States

Visual place recognition (VPR) is essential to many autonomous systems. Existing VPR methods demonstrate attractive performance at the cost of limited generalizability. When deployed in unseen environments, these methods exhibit significant performance drops. Targeting this issue, we present VIPeR, a novel approach for visual incremental place recognition with the ability to adapt to new environments while retaining the performance of previous ones. We first introduce an adaptive mining strategy that balances the performance within a single environment and the generalizability across multiple environments. Then, to prevent catastrophic forgetting in continual learning, we design a novel multi-stage memory bank for explicit rehearsal. Additionally, we propose a probabilistic knowledge distillation to explicitly safeguard the previously learned knowledge. We evaluate our proposed VIPeR on three large-scale datasets—Oxford Robotcar, Nordland, and TartanAir. For comparison, we first set a baseline performance with naive finetuning. Then, several more recent continual learning methods are compared. Our VIPeR achieves better performance in almost all aspects with the biggest improvement of 13.85% in average performance. 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

Distributed Online Convex Optimization with Time-Varying Constraints: Tighter Cumulative Constraint Violation Bounds under Slater's Condition

引用

IEEE Transactions on Automatic Control 2025年

作者： Yi, Xinlei Li, Xiuxian Yang, Tao Xie, Lihua Hong, Yiguang Chai, Tianyou Johansson, Karl H. National Key Laboratory of Autonomous Intelligent Unmanned Systems Shanghai Institute of Intelligent Science and Technology China Ministry of Education Frontiers Science Center for Intelligent Autonomous Systems China Massachusetts Institute of Technology Lab for Information & Decision Systems CambridgeMA02139 United States Northeastern University State Key Laboratory of Synthetical Automation for Process Industries Shenyang110819 China Nanyang Technological University School of Electrical and Electronic Engineering 50 Nanyang Avenue 639798 Singapore Kth Royal Institute of Technology Division of Decision and Control Systems School of Electrical Engineering and Computer Science Sweden Digital Futures Stockholm10044 Sweden

This paper considers distributed online convex optimization with time-varying constraints. In this setting, a network of agents makes decisions at each round, and then only a portion of the loss function and a coordinate block of the constraint function are privately revealed to each agent. The loss and constraint functions are convex and can vary arbitrarily across rounds. The agents collaborate to minimize static network regret and network cumulative constraint violation. A novel distributed online algorithm with a vanishing stepsize is proposed and it achieves an O(Tmax {c,1-c}) static network regret bound and an O(T1-c/2) network cumulative constraint violation bound, where T is the number of rounds and c∈ (0,1) is a user-defined trade-off parameter. When Slater's condition holds (i.e, there is a point that strictly satisfies the inequality constraints), the network cumulative constraint violation bound is reduced to O(T1-c). Moreover, if the loss functions are strongly convex, then static network regret bound is reduced to O(log (T)), and the network cumulative constraint violation bound is reduced to O(√log (T)T) and O(log (T)) without and with Slater's condition, respectively. To the best of our knowledge, this paper is the first to achieve tighter (network) cumulative constraint violation bounds for (distributed) online convex optimization with time-varying constraints under Slater's condition. Finally, the theoretical results are verified through numerical simulations. © 1963-2012 IEEE.

关键词： Convex optimization

来源：评论

学校读者我要写书评

暂无评论

Devils in the Clouds: An Evolutionary Study of Telnet Bot Loaders

Devils in the Clouds: An Evolutionary Study of Telnet Bot Lo...

引用

IEEE International Conference on Communications (ICC)

作者： Yuhui Zhu Zhenxiang Chen Qiben Yan Shanshan Wang Alberto Giaretta Enlong Li Lizhi Peng Chuan Zhao Mauro Conti Shandong Provincial Key Laboratory of Network Based Intelligent Computing University of Jinan China School of Information Science and Engineering University of Jinan China Department of Computer Science and Engineering Michigan State University USA AASS MPI Lab Örebro University Sweden Department of Mathematics University of Padua Italy

One of the innovations brought by Mirai and its derived malware is the adoption of self-contained loaders for infecting IoT devices and recruiting them in botnets. Functionally decoupled from other botnet components and not embedded in the payload, loaders cannot be analysed using conventional approaches that rely on honeypots for capturing samples. Different approaches are necessary for studying the loaders evolution and defining a genealogy. To address the insufficient knowledge about loaders' lineage in existing studies, in this paper, we propose a semantic-aware method to measure, categorize, and compare different loader servers, with the goal of highlighting their evolution, independent from the payload evolution. Leveraging behavior-based metrics, we cluster the discovered loaders and define eight families to determine the genealogy and draw a homology map. Our study shows that the source code of Mirai is evolving and spawning new botnets with new capabilities, both on the client side and the server side. In turn, shedding light on the infection loaders can help the cybersecurity community to improve detection and prevention tools.

关键词：

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：