检索结果-内蒙古大学图书馆

Exploring Token-Level Augmentation in Vision Transformer for Semi-Supervised Semantic Segmentation

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Zhang, Dengke Tang, Quan Liu, Fagui Mei, Haiqing Chen, C.L. Philip The School of Computer Science and Engineering South China University of Technology Guangzhou510006 China The Department of New Network Pengcheng Laboratory Shenzhen518000 China The China Tobacco Guangdong Industrial Corporation Guangzhou510385 China State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100080 China

Semi-supervised semantic segmentation has witnessed remarkable advancements in recent years. However, existing algorithms are based on convolutional neural networks and directly applying them to Vision Transformers poses certain limitations due to conceptual disparities. To this end, we propose TokenMix, a data augmentation technique specifically designed for semi-supervised semantic segmentation with Vision Transformers. TokenMix aligns well with the global attention mechanism by mixing images at the token level, enhancing learning capability for contextual information among image patches. We further incorporate image augmentation and feature augmentation to promote the diversity of augmentation. Moreover, to enhance consistency regularization, we propose a dual-branch framework where each branch applies image and feature augmentation to the input image. We conduct extensive experiments across multiple benchmark datasets, including Pascal VOC 2012, Cityscapes, and COCO. Results suggest that the proposed method outperforms state-of-the-art algorithms with notably observed accuracy improvement, especially under limited fine annotations. Copyright © 2025, The Authors. All rights reserved.

关键词：

Joining Edge-Enabled Metaverse Services with Network Externality: A Stackelberg Game Approach

学校读者我要写书评

暂无评论

Joining Edge-Enabled Metaverse Services with Network Externa...

2023 IEEE International Conference on Metaverse Computing, Networking and Applications, MetaCom 2023

作者： Jiang, Yuna Kang, Jiawen Niyato, Dusit Ge, Xiaohu Xiong, Zehui Xu, Minrui Deng, Ruilong Huazhong University of Science and Technology School of Electronic Information and Communications Wuhan China Guangdong University of Technology School of Automation Guangzhou China Nanyang Technological University School of Computer Science and Engineering Singapore Singapore University of Technology and Design Pillar of Information Systems Technology and Design Singapore Zhejiang University State Key Laboratory of Industrial Control Technology Hangzhou China Shenzhen Huazhong University of Science and Technology Research Institute China

ISBN: (纸本)9798350333336

The metaverse is defined as a three-dimensional virtual-real fusion network focused on social connection. Edge computing can empower the metaverse by providing computing resources to realize real-time motion tracking, visual or auditory rendering and virtual scene dynamic change at the edge of networks. Users enjoy the immersive experience provided by the Metaverse Service Provider (MSP), and interact through digital avatars in the virtual world by requesting metaverse services. In this paper, we formulate the edge computing resources pricing, metaverse service rendering bitrate pricing and request problem in the metaverse. Especially, we model the interactions among edge servers, the MSP and Metaverse Service Users (MSUs) as a hierarchical three-stage Stackelberg game. The problem of joining edge-enabled metaverse services is also studied with the consideration of network externality, including the network effect and congestion effect. Based on the backward induction method, we derive the optimal computing resources pricing of edge servers, rendering bitrate pricing of the MSP, and rendering bitrate requests of MSUs. We also prove the existence and uniqueness of the Stackelberg game equilibrium. Simulation results show that the network effect can bring more positive utilities to entities when the social tie coefficient among MSUs is higher. Besides, all entities in the edge-enabled metaverse are affected negatively by the congestion effect. © 2023 IEEE.

关键词： Edge computing

A System for Positioning an Optical Tunnel Measuring Transducer of a Microoptoelectromechanical Micro-g Accelerometer

学校读者我要写书评

暂无评论

A System for Positioning an Optical Tunnel Measuring Transdu...

Annual Siberian Russian Workshop on Electron Devices and Materials (EDM)

作者： Evgenij S. Barbin Tamara G. Nesterenko Aleksej N. Koleda Evgeniy V. Shesterikov Ivan V. Kulinich Andrey A. Kokolov Laboratory of Radiophotonics The Tomsk State University of Control Systems and Radioelectronics. Laboratory of Intelligent Computer Systems Institute of Optics and Atmosphere Siberian Branch of the Russian Academy of Sciences Tomsk Russia Laboratory of Radiophotonics The Tomsk State University of Control Systems and Radioelectronics. Division for Electronic Engineering National Research Tomsk Polytechnic University Tomsk Russia

ISBN: (数字)9781665498043

ISBN: (纸本)9781665498050

The paper investigates a microoptoelectromechanical accelerometer that implements optical measuring transducer built based on the optical tunneling effect. The optical transducer is a directional optical coupler that contains moving and fixed waveguides from Si 3 N 4 with dimensions of 0.3 ×1 μm. The treatise studies the normalized transmission at the directional coupler output depending on the gap and coupling length. Due to the positioning system, the optical measuring transducer can have several operating points with different optical sensitivity. For instance, for a set coupling length of 100 μm, the sensitivity of the directional coupler may reach 6.25 × 10 6 m -1 , 20 × 10 6 m -1 or 41.7 × 10 6 m -1 for initial gaps of 255, 120 and 70 nm, correspondingly. The comb-drive actuator has three independent stages with 600, 50 and 4 fingers. It allows setting a necessary gap (from 0 to 2.8 μm) between the waveguides. It also imitates microaccelerations (from 16 micro-g to 3 g) by using electrostatic forces. The study proposes a method for selecting parameters of the positioning system (electrode voltage, number of fingers, spring suspension stiffness and inertial mass).

关键词： Electrodes Transducers Optical feedback Fingers Optical variables measurement Position measurement Tunneling

Social Force Embedded Mixed Graph Convolutional Network for Multi-class Trajectory Prediction

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Du, Quancheng Wang, Xiao Yin, Shouguo Li, Lingxi Ning, Huansheng The School of Computer and Communication Engineering University of Science and Technology Beijing Beijing100083 China The School of Artificial Intelligence Anhui University Hefei230031 China The State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China The School of Electrical and Computer Engineering Indiana University Purdue University IndianapolisIN46202 United States

Accurate prediction of agent motion trajectories is crucial for autonomous driving, contributing to the reduction of collision risks in human-vehicle interactions and ensuring ample response time for other traffic participants. Current research predominantly focuses on traditional deep learning methods, including convolutional neural networks (CNNs) and recurrent neural networks (RNNs). These methods leverage relative distances to forecast the motion trajectories of a single class of agents. However, in complex traffic scenarios, the motion patterns of various types of traffic participants exhibit inherent randomness and uncertainty. Relying solely on relative distances may not adequately capture the nuanced interaction patterns between different classes of road users. In this paper, we propose a novel multi-class trajectory prediction method named the social force embedded mixed graph convolutional network (SFEM-GCN). The primary goal is to extract social interactions among agents more accurately. SFEM-GCN comprises three graph topologies: the semantic graph (SG), position graph (PG), and velocity graph (VG). These graphs encode various of social force relationships among different classes of agents in complex scenes. Specifically, SG utilizes one-hot encoding of agent-class information to guide the construction of graph adjacency matrices based on semantic information. PG and VG create adjacency matrices to capture motion interaction relationships between different classes agents. These graph structures are then integrated into a mixed graph, where learning is conducted using a spatio-temporal graph convolutional neural network (ST-GCNN). To further enhance prediction performance, we adopt temporal convolutional networks (TCNs) to generate the predicted trajectory with fewer parameters. Experimental results on publicly available datasets demonstrate that SFEM-GCN surpasses state-of-the-art methods in terms of accuracy and robustness. Copyright © 2024, The Authors.

关键词： Forecasting

Multi-feature Fusion Based Deep Forest for Hyperspectral Image Classification 16th

学校读者我要写书评

暂无评论

Multi-feature Fusion Based Deep Forest for Hyperspectral Ima...

16th International Conference on Bio-Inspired Computing: Theories and Applications, BIC-TA 2021

作者： Liu, Xiaobo Mohammad, Mostofa Zaman Zhang, Chaochao Gong, Xin Cai, Zhihua School of Automation China University of Geosciences Wuhan430074 China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan430074 China Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Wuhan430074 China School of Computer Science China University of Geosciences Wuhan430074 China

ISBN: (纸本)9789811912528

Multi-feature fusion is a useful way to improve the classification of hyperspectral image (HSI). But the multi-feature fusion is usually at the decision level of classifier, which causes less link between features or poor extensibility of feature. In this paper, we propose a multi-feature fusion based deep forest method for HSI classification, named mfdForest. In mfdForest, the morphological features, saliency features, and edge features are extracted, then the three deep multi-grained scanning branches in dgcForest (one of improved deep forest) are used to extract and fuse the extracted features deeply, and the fused features are sent into cascade forest in dgcForest for classification. Experimental results indicate that the proposed framework consumes less training time and has better performance on two HSI data sets. © 2022, Springer Nature Singapore Pte Ltd.

关键词： Spectroscopy

Vulnerability of Machine Learning Approaches Applied in IoT-based Smart Grid: A Review

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhang, Zhenyong Liu, Mengxiang Sun, Mingyang Deng, Ruilong Cheng, Peng Niyato, Dusit Chow, Mo-Yuen Chen, Jiming The State Key Laboratory of Public Big Data College of Computer Science and Technology Guizhou University Guiyang550000 China The Department of Automatic Control and Systems Engineering University of Sheffield SheffieldS10 2TN United Kingdom The State Key Laboratory of Industrial Control Technology the College of Control Science and Engineering Zhejiang University Hangzhou310027 China The School of Computer Science and Engineering Nanyang Technological University Singapore639798 Singapore The UM SJTU Joint Institute Shanghai Jiao Tong University Shanghai200240 China

Machine learning (ML) sees an increasing prevalence of being used in the internet-of-things (IoT)-based smart grid. However, the trustworthiness of ML is a severe issue that must be addressed to accommodate the trend of ML-based smart grid applications (MLsgAPPs). The adversarial distortion injected into the power signal will greatly affect the system’s normal control and operation. Therefore, it is imperative to conduct vulnerability assessment for MLsgAPPs applied in the context of safety-critical power systems. In this paper, we provide a comprehensive review of the recent progress in designing attack and defense methods for MLsgAPPs. Unlike the traditional survey about ML security, this is the first review work about the security of MLsgAPPs that focuses on the characteristics of power systems. We first highlight the specifics for constructing the adversarial attacks on MLsgAPPs. Then, the vulnerability of MLsgAPP is analyzed from both the aspects of the power system and ML model. Afterward, a comprehensive survey is conducted to review and compare existing studies about the adversarial attacks on MLsgAPPs in scenarios of generation, transmission, distribution, and consumption, and the countermeasures are reviewed according to the attacks that they defend against. Finally, the future research directions are discussed on the attacker’s and defender’s side, respectively. We also analyze the potential vulnerability of large language model-based (e.g., ChatGPT) power system applications. Overall, we encourage more researchers to contribute to investigating the adversarial issues of MLsgAPPs. Copyright © 2023, The Authors. All rights reserved.

关键词： Machine learning

Cooperative Global K-exponential Tracking control of Multiple Mobile Robots-Extended Version

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Xu, Liang Su, Youfeng Cai, He College of Computer and Data Science Fuzhou University Fuzhou350116 China Shenzhen Key Laboratory of Control Theory and Intelligent Systems Southern University of Science and Technology Shenzhen518055 China School of Automation Science and Engineering South China University of Technology Guangzhou510641 China

This paper studies the cooperative tracking control problem for multiple mobile robots over a directed communication network. First, it is shown that the closed-loop system is uniformly globally asymptotically stable under the proposed distributed continuous feedback control law, where an explicit strict Lyapunov function is constructed. Then, by investigating the convergence rate, it is further proven that the closed-loop system is globally K-exponentially stable. Moreover, to make the proposed control law more practical, the distributed continuous feedback control law is generalized to a distributed sampled-data feedback control law using the emulation approach, based on the strong integral input-to-state stable Lyapunov function. Numerical simulations are presented to validate the effectiveness of the proposed control methods. Copyright © 2024, The Authors. All rights reserved.

关键词： Lyapunov functions

Distributed Event-Triggered Bandit Convex Optimization With Time-Varying Constraints

学校读者我要写书评

暂无评论

IEEE Transactions on control of Network systems 2025年

作者： Zhang, Kunpeng Yi, Xinlei Wen, Guanghui Cao, Ming Johansson, Karl H. Chai, Tianyou Yang, Tao Northeastern University State Key Laboratory of Synthetical Automation for Process Industries Shenyang110819 China Ministry of Education Shanghai Institute of Intelligent Science and Technology National Key Laboratory of Autonomous Intelligent Unmanned Systems Frontiers Science Center for Intelligent Autonomous Systems Shanghai201210 China Southeast University School of Automation Nanjing210096 China University of Groningen Engineering and Technology Institute Groningen Faculty of Science and Engineering GroningenAG 9747 Netherlands KTH Royal Institute of Technology Division of Decision and Control Systems School of Electrical Engineering and Computer Science Stockholm10044 Sweden KTH Royal Institute of Technology Digital Futures Stockholm10044 Sweden

This paper considers the distributed bandit convex optimization problem with time-varying inequality constraints over a network of agents, where the goal is to minimize network regret and cumulative constraint violation. Existing distributed online algorithms solving this problem require that each agent broadcasts its decision to its neighbors at each iteration. However, communication resources are often limited. To better utilize communication resources, we propose a distributed event-triggered online primal-dual algorithm with two-point bandit feedback. Under several classes of appropriately chosen decreasing parameter sequences and non-increasing event-triggered threshold sequences, we establish dynamic network regret and network cumulative constraint violation bounds. These bounds are comparable to the results achieved by distributed event-triggered online algorithms with full-information feedback. Finally, a numerical example is provided to verify the theoretical results. © 2014 IEEE.

关键词： Optimization algorithms

Heterogeneous Graph Reinforcement Learning for Dependency-aware Multi-task Allocation in Spatial Crowdsourcing

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhao, Yong Zhu, Zhengqiu Gao, Chen Wang, En Huang, Jincai Wang, Fei-Yue College of Systems Engineering National University of Defense Technology Hunan Province Changsha410073 China BNRist Tsinghua University Beijing100084 China College of Computer Science and Technology Jilin University Changchun130012 China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun130012 China State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China

Spatial Crowdsourcing (SC) is gaining traction in both academia and industry, with tasks on SC platforms becoming increasingly complex and requiring collaboration among workers with diverse skills. Recent research works address complex tasks by dividing them into subtasks with dependencies and assigning them to suitable workers. However, the dependencies among subtasks and their heterogeneous skill requirements, as well as the need for efficient utilization of workers’ limited work time in the multi-task allocation mode, pose challenges in achieving an optimal task allocation scheme. Therefore, this paper formally investigates the problem of Dependency-aware Multi-task Allocation (DMA) and presents a well-designed framework to solve it, known as Heterogeneous Graph Reinforcement Learning-based Task Allocation (HGRL-TA). To address the challenges associated with representing and embedding diverse problem instances to ensure robust generalization, we propose a multi-relation graph model and a Compound-path-based Heterogeneous Graph Attention Network (CHANet) for effectively representing and capturing intricate relations among tasks and workers, as well as providing embedding of problem state. The task allocation decision is determined sequentially by a policy network, which undergoes simultaneous training with CHANet using the proximal policy optimization algorithm. Extensive experiment results demonstrate the effectiveness and generality of the proposed HGRL-TA in solving the DMA problem, leading to average profits that is 21.78% higher than those achieved using the metaheuristic methods. © 2024, CC BY-NC-ND.

关键词： Reinforcement learning