检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Liu, Jiaming Yang, Senqiao Jia, Peidong Zhang, Renrui Lu, Ming Guo, Yandong Xue, Wei Zhang, Shanghang National Key Laboratory for Multimedia Information Processing School of Computer Science Peking University China AI2Robotics China The Chinese University of Hong Kong Hong Kong Hong Kong University of Science and Technology Hong Kong

Since real-world machine systems are running in non-stationary environments, Continual Test-Time Adaptation (CTTA) task is proposed to adapt the pre-trained model to continually changing target domains. Recently, existing methods mainly focus on model-based adaptation, which aims to leverage a self-training manner to extract the target domain knowledge. However, pseudo labels can be noisy and the updated model parameters are unreliable under dynamic data distributions, leading to error accumulation and catastrophic forgetting in the continual adaptation process. To tackle these challenges and maintain the model plasticity, we design a Visual Domain Adapter (ViDA) for CTTA, explicitly handling both domain-specific and domain-shared knowledge. Specifically, we first comprehensively explore the different domain representations of the adapters with trainable high-rank or low-rank embedding spaces. Then we inject ViDAs into the pre-trained model, which leverages high-rank and low-rank features to adapt the current domain distribution and maintain the continual domain-shared knowledge, respectively. To exploit the low-rank and high-rank ViDAs more effectively, we further propose a Homeostatic Knowledge Allotment (HKA) strategy, which adaptively combines different knowledge from each ViDA. Extensive experiments conducted on four widely used benchmarks demonstrate that our proposed method achieves state-of-the-art performance in both classification and segmentation CTTA tasks. Note that, our method can be regarded as a novel transfer paradigm for large-scale models, delivering promising results in adaptation to continually changing distributions. Project page: https://***/view/iclr2024-vida/home Copyright © 2023, The Authors. All rights reserved.

关键词： Domain Knowledge

来源：评论

学校读者我要写书评

暂无评论

F2A2: flexible fully-decentralized approximate actor-critic for cooperative multi-agent reinforcement learning

The Journal of Machine Learning Research

引用

The Journal of Machine Learning Research 2023年第1期24卷 8447-8521页

作者： Wenhao Li Bo Jin Xiangfeng Wang Junchi Yan Hongyuan Zha School of Data Science The Chinese University of Hong Kong Shenzhen Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen China School of Software Engineering Shanghai Research Institute for Intelligent Autonomous Systems Tongji University Shanghai China School of Computer Science and Technology Key Laboratory of Mathematics and Engineering Applications Ministry of Education East China Normal University Shanghai China Department of Computer Science and Engineering Key Laboratory of Artificial Intelligence Ministry of Education Shanghai Jiao Tong University Shanghai China

Traditional centralized multi-agent reinforcement learning (MARL) algorithms are sometimes unpractical in complicated applications due to non-interactivity between agents, the curse of dimensionality, and computation complexity. Hence, several decentralized MARL algorithms are motivated. However, existing decentralized methods only handle the fully cooperative setting where massive information needs to be transmitted in training. The block coordinate gradient descent scheme they used for successive independent actor and critic steps can simplify the calculation, but it causes serious bias. This paper proposes a exible fully decentralized actor-critic MARL framework, which can combine most of the actor-critic methods and handle large-scale general cooperative multi-agent settings. A primal-dual hybrid gradient descent type algorithm framework is designed to learn individual agents separately for decentralization. From the perspective of each agent, policy improvement and value evaluation are jointly optimized, which can stabilize multi-agent policy learning. Furthermore, the proposed framework can achieve scalability and stability for the large-scale environment. This framework also reduces information transmission by the parameter sharing mechanism and novel modeling-other-agents methods based on theory-of-mind and online supervised learning. Sufficient experiments in cooperative Multi-agent Particle Environment and StarCraft II show that the proposed decentralized MARL instantiation algorithms perform competitively against conventional centralized and decentralized methods.

关键词： cooperative MARL decentralized actor-critic primal-dual method

来源：评论

学校读者我要写书评

暂无评论

SSPA: Split-and-Synthesize Prompting with Gated Alignments for Multi-Label Image Recognition

arXiv

引用

arXiv 2024年

作者： Tan, Hao Tan, Zichang Li, Jun Wan, Jun Lei, Zhen Li, Stan Z. Beijing100190 China Beijing100049 China The School of Computer Science and Engineering Macau University of Science and Technology China The Centre for Artificial Intelligence and Robotics Hong Kong Institute of Science & Innovation Chinese Academy of Sciences Hong Kong The Sangfor Technologies Inc China Chinese Academy of Sciences China The Westlake University China

Multi-label image recognition is a fundamental task in computer vision. Recently, Vision-Language Models (VLMs) have made notable advancements in this area. However, previous methods fail to effectively leverage the rich knowledge in language models and often incorporate label semantics into visual features unidirectionally. To overcome these problems, we propose a Split-and-Synthesize Prompting with Gated Alignments (SSPA) framework to amplify the potential of VLMs. Specifically, we develop an in-context learning approach to associate the inherent knowledge from LLMs. Then we propose a novel Split-and-Synthesize Prompting (SSP) strategy to first model the generic knowledge and downstream label semantics individually and then aggregate them carefully through the quaternion network. Moreover, we present Gated Dual-Modal Alignments (GDMA) to bidirectionally interact visual and linguistic modalities while eliminating redundant cross-modal information, enabling more efficient region-level alignments. Rather than making the final prediction by a sharp manner in previous works, we propose a soft aggregator to jointly consider results from all image regions. With the help of flexible prompting and gated alignments, SSPA is generalizable to specific domains. Extensive experiments on nine datasets from three domains (i.e., natural, pedestrian attributes and remote sensing) demonstrate the state-of-the-art performance of SSPA. Further analyses verify the effectiveness of SSP and the interpretability of GDMA. The code will be made public. Copyright © 2024, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Machine Learning based Detection of Cyber Crime Hub Analysis using Twitter Data 4

Machine Learning based Detection of Cyber Crime Hub Analysis...

引用

4th IEEE International Conference on Computing, Power and Communication Technologies, GUCON 2021

作者： Mahor, Vinod Rawat, Romil Telang, Shrikant Garg, Bhagwati Mukhopadhyay, Debajyoti Palimkar, Prajyot SVVV IPS College of Technology and Management Computer Science Gwalior India SVIIT SVVV Computer Science Indore India Information Technology SVIIT SVVV Indore India Union Bank of India Branch Gwalior India Bennett University Greater Dept of Computer Science Engineering Noida India The Neotia University School of Engineering Applied Sciences Robotics Engineering The Neotia University

ISBN: (纸本)9781728199511

Online Social Network Platform is the hub of criminal activities. Among them twitter is the most popular one containing millions of media contents and thus can be used for crime analysis. In this research, a system for detecting Cyber Crime Hub in India, specifically Jamtara, is created. The design shows the criminal alert zones based on the name of crime incident reported. The proposed approach employs sigmoid kernel, support vector machine (SVM) classification. According to this analysis, Rate of Accuracy is 97.12 Percent (libSVM), which is greater by 3.12 percent(mySVM) as evaluation results of the proposed system in comparison to Data collected from Government site for Cyber crime analytics the system shows the statistics of cyber crime cases. © 2021 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Value Stream Mapping for Smart Pharmaceutical Management in a Thai Hospital

引用

Procedia computer science 2025年 253卷 495-504页

作者： Ganda Boonsothonsatit Rardchawadee Silapunt Supachai Vongbunyong Kamol Kaemarungsi Wirachchaya Chanpuypetch Nilubon Chonsawat Graduate School of Management and Innovation King Mongkut’s University of technology Thonburi Thailand Electronic and Telecommunication Engineering King Mongkut’s University of Technology Thonburi Thailand Hospital Automation Research Center Institute of Field Robotics King Mongkut’s University of Technology Thonburi Thailand National Electronics and Computer Technology Center National Science and Technology Development Agency Thailand Faculty of Agro-Industry Chiang Mai University Thailand Department of Agricultural Economy and Developement Faculty of Agriculture Chiang Mai University Thailand

The evolution of healthcare systems worldwide necessitates continual improvement in hospital management practices, particularly pharmaceutical management. This paper explores transforming traditional pharmaceutical management systems in large and medium-sized hospitals in Thailand into smart systems using Value Stream Mapping (VSM) as a guiding tool. Traditional systems often face challenges such as inefficiencies and medication errors. VSM, rooted in lean management principles, offers a structured approach to visualize and optimize processes. Additionally, smart technologies like automated inventory systems and electronic health records enhance pharmaceutical management effectiveness. Through a comprehensive research methodology encompassing case studies, data collection, and VSM analysis, this study identifies inefficiencies and proposes evidence-based strategies for improvement. Results from a case study highlight the benefits of VSM implementation in enhancing pharmacy operations, emphasizing improved patient care and operational efficiency. The implementation of a smart medication dispensing system shows promising results in reducing workload and accommodating increased patient arrivals. Continued evaluation and refinement are crucial for maximizing benefits and addressing emerging challenges effectively.

关键词： lean management smart medication dispensing smart pharmaceutical smart technologies Value Stream Mapping

来源：评论

学校读者我要写书评

暂无评论

Graph-Based Visual-Kinematic Fusion and Monte Carlo Initialization for Fast-Deployable Cable-Driven Robots

Graph-Based Visual-Kinematic Fusion and Monte Carlo Initiali...

引用

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： R. Khorrambakht H. Damirchi M.R. Dindarloo A. Saki S.A. Khalilpour Hamid D. Taghirad Stephan Weiss Electrical & Computer Engineering Department Control/Robotics Research Laboratory Tandon School of Engineering New York University Brooklyn NY School of Computer Science University of Adelaide Australia Faculty of Electrical Engineering University of Technology Tehran Iran Department of Smart Systems Technologies University of Klagenfurt Austria

Ease of calibration and high-accuracy task-space state-estimation purely based on onboard sensors is a key requirement for enabling easily deployable cable robots in real-world applications. In this work, we incorporate the onboard camera and kinematic sensors to drive a statistical fusion framework that presents a unified localization and calibration system which requires no initial values for the kinematic parameters. This is achieved by formulating a Monte-Carlo algorithm that initializes a factor-graph representation of the calibration and localization problem. With this, we are able to jointly identify both the kinematic parameters and the visual odometry scale alongside their corresponding uncertainties. We demonstrate the practical applicability of the framework using our state-estimation dataset recorded with the ARAS-CAM suspended cable driven parallel robot, and published as part of this manuscript.

关键词：

来源：评论

学校读者我要写书评

暂无评论

DPER: Diffusion Prior Driven Neural Representation for Limited Angle and Sparse View CT Reconstruction

arXiv

引用

arXiv 2024年

作者： Du, Chenhe Lin, Xiyue Wu, Qing Tian, Xuanyu Su, Ying Luo, Zhe Zheng, Rui Chen, Yang Wei, Hongjiang Zhou, S. Kevin Yu, Jingyi Zhang, Yuyao The School of Information Science and Technology ShanghaiTech University Shanghai China The Department of Critical Care Medicine Zhongshan Hospital Fudan University Shanghai China The Laboratory of Image Science and Technology The School of Computer Science and Engineering The Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications Southeast University Ministry of Education Nanjing210096 China The School of Biomedical Engineering Institute of Medical Robotics Shanghai Jiao Tong University Shanghai China School of Biomedical Engineering Suzhou Institute for Advanced Research University of Science and Technology of China Suzhou215123 China Institute of Computing Technology CAS Beijing100190 China

Limited-angle and sparse-view computed tomography (LACT and SVCT) are crucial for expanding the scope of X-ray CT applications. However, they face challenges due to incomplete data acquisition, resulting in diverse artifacts in the reconstructed CT images. Emerging implicit neural representation (INR) techniques, such as NeRF, NeAT, and NeRP, have shown promise in under-determined CT imaging reconstruction tasks. However, the unsupervised nature of INR architecture imposes limited constraints on the solution space, particularly for the highly ill-posed reconstruction task posed by LACT and ultra-SVCT. In this study, we introduce the Diffusion Prior Driven Neural Representation (DPER), an advanced unsupervised framework designed to address the exceptionally ill-posed CT reconstruction inverse problems. DPER adopts the Half Quadratic Splitting (HQS) algorithm to decompose the inverse problem into data fidelity and distribution prior sub-problems. The two sub-problems are respectively addressed by INR reconstruction scheme and pre-trained score-based diffusion model. This combination first injects the implicit image local consistency prior from INR. Additionally, it effectively augments the feasibility of the solution space for the inverse problem through the generative diffusion model, resulting in increased stability and precision in the solutions. We conduct comprehensive experiments to evaluate the performance of DPER on LACT and ultra-SVCT reconstruction with two public datasets (AAPM and LIDC), an in-house clinical COVID-19 dataset and a public raw projection dataset created by Mayo Clinic. The results show that our method outperforms the state-of-the-art reconstruction methods on in-domain datasets, while achieving significant performance improvements on out-of-domain (OOD) datasets. Copyright © 2024, The Authors. All rights reserved.

关键词： Inverse problems

来源：评论

学校读者我要写书评

暂无评论

Debiased Distillation for Consistency Regularization 39

Debiased Distillation for Consistency Regularization

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Wang, Lu Xu, Liuchi Yang, Xiong Huang, Zhenhua Cheng, Jun School of Computer Science and Engineering Northeastern University Shenyang China Institute of Applied Artificial Intelligence of the Guangdong-Hong Kong-Macao Greater Bay Area Shenzhen Polytechnic University Shenzhen China School of Computer Science South China Normal University Guangzhou China Guangdong Provincial Key Laboratory of Robotics and Intelligent System Shenzhen Institute of Advanced Technology CAS China The Chinese University of Hong Kong Hong Kong

ISBN: (纸本)157735897X

Knowledge distillation transfers “dark knowledge” from a large teacher model to a smaller student model, yielding a highly efficient network. To improve the network's generalization ability, existing works use a larger temperature coefficient for knowledge distillation. Nevertheless, these methods may reduce the confidence of the target category and lead to ambiguous recognition of similar samples. To mitigate this issue, some studies introduce intra-batch distillation to reduce prediction discrepancy. However, these methods overlook the inconsistency between background information and the target category, which may increase prediction bias due to noise disturbance. Additionally, label imbalance from random sampling and batch size can undermine network generalization reliability. To tackle these challenges, we propose a simple yet effective Intra-class Knowledge Distillation (IKD) method that facilitates knowledge sharing within the same class to ensure consistent predictions. First, we initialize the matrix and the vector to store logits and class counts provided by the teacher, respectively. Then, in the first epoch, we calculate the sum of logits and sample counts per class and perform KD to prevent knowledge omission. Finally, in subsequent training, we update the matrix to obtain the average logits and compute the KL divergence between the student's output and the updated matrix according to the label index. This process ensures intra-class consistency and improves the student's performance. Furthermore, this method theoretically reduces prediction bias by ensuring intra-class consistency. Extensive experiments on the CIFAR-100, ImageNet-1K, and Tiny-ImageNet datasets validate the superiority of IKD. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Learning-Based Low-Latency Collaborative Inference for Multi-Branch Models in D2D-Assisted MEC

Learning-Based Low-Latency Collaborative Inference for Multi...

引用

2025 IEEE Wireless Communications and Networking Conference, WCNC 2025

作者： Guo, Kai Xiao, Yilin Lu, Xiaozhen Xiao, Liang Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen China School of Science and Engineering The Chinese University of HongKong Shenzhen China Peng Cheng Laboratory Shenzhen China College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing China Xiamen University Department of Information and Communication Engineering Xiamen China

ISBN: (纸本)9798350368369

Deploying high-complexity deep neural network (DNN) on mobile devices presents significant challenges, stemming from the conflict between their computationally intensive demands and the constrained computational resources. Device-to-device (D2D) assisted mobile edge computing (MEC) exploits sharing resources among devices to perform DNN inference collaboratively for higher efficiency. However, most existing collaborative inference schemes ignore the structure of DNN models, thus suffering from high latency under dynamic network conditions and computational loads. In this paper, we propose a learning-based low-latency collaborative inference scheme for multi-branch models, which schedules the computations of each DNN layer to optimize the alignment between the DNN structure's characteristics and the D2D network environments. Specifically, the computational task of each branch is assigned to nearby mobile devices or the edge server for efficient collaboration. In addition, we design proximal policy optimization with task-specific architecture to choose the computational scheduling policy, which contains a two-stream NN to extract features from the D2D network and the tasks at each layer, as well as a multi-head output to obtain the collaborative devices for all tasks in the layer. Simulation results show that the proposed scheme reduces the inference latency compared with benchmarks. © 2025 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Optimizing Transistor Selection Using AH-TOR for Low Noise Amplifier Design in Sensing Applications

Optimizing Transistor Selection Using AH-TOR for Low Noise A...

引用

International Conference on Sensing technology, ICST

作者： Dayarnab Baidya Karthick Thiyagarajan Mitradip Bhattacharjee Yang An Department of Electrical Engineering and Computer Science i-Lab Indian Institute of Science Education and Research Bhopal Bhopal Madhya Pradesh India Smart Sensing and Robotics Laboratory (SensR Lab) Centre for Advanced Manufacturing Technology School of Engineering Design and Built Environment Western Sydney University Penrith Australia

ISBN: (数字)9798350374827

ISBN: (纸本)9798350374834

The design of a wireless sensor network receiver requires an efficient Low Noise Amplifier (LNA), with the transistor being a critical component that influences its performance. Selecting an optimal transistor for LNA design is a complex and time-consuming process due to the conflicting criteria involved. This study utilizes the Analytic Hierarchy Trade-off Ranking Method (AH-TOR), an integrated Multi-Criteria Decision-Making (MCDM) approach, to facilitate the selection of a suitable transistor for LNA design. Four types of transistors were evaluated as alternatives based on four criteria, with the Pseudomorphic High Electron Mobility Transistor (PHEMT) emerging as the optimal choice. The weight of PHEMT was calculated to be 1.0787, and its performance was benchmarked against other existing methods. Further analysis demonstrated the robustness of the AH-TOR method across various scenarios, consistently identifying PHEMT as the most suitable option. These findings highlight the reliability of the AH-TOR method for transistor selection in diverse applications.

关键词： Low-noise amplifiers Wireless sensor networks PHEMTs Decision making Receivers Electron mobility Robustness Sensors Transistors Integrated circuit reliability

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：