检索结果-内蒙古大学图书馆

Communication-efficient Vertical Federated Learning via Compressed Error Feedback

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Valdeira, Pedro Xavier, João Soares, Cláudia Chi, Yuejie CMU IST United States IST NOVA CMU United States Department of Electrical and Computer Engineering Carnegie Mellon University United States Institute for Systems and Robotics Instituto Superior Técnico Portugal Department of Computer Science NOVA School of Science and Technology

Communication overhead is a known bottleneck in federated learning (FL). To address this, lossy compression is commonly used on the information communicated between the server and clients during training. In horizontal FL, where each client holds a subset of the samples, such communication-compressed training methods have recently seen significant progress. However, in their vertical FL counterparts, where each client holds a subset of the features, our understanding remains limited. To address this, we propose an error feedback compressed vertical federated learning (EF-VFL) method to train split neural networks. In contrast to previous communication-compressed methods for vertical FL, EF-VFL does not require a vanishing compression error for the gradient norm to converge to zero for smooth nonconvex problems. By leveraging error feedback, our method can achieve a O(1/T) convergence rate for a sufficiently large batch size, improving over the state-of-the-art O(1/√T) rate under O(1/√T) compression error, and matching the rate of uncompressed methods. Further, when the objective function satisfies the Polyak-Lojasiewicz inequality, our method converges linearly. In addition to improving convergence, our method also supports the use of private labels. Numerical experiments show that EF-VFL significantly improves over the prior art, confirming our theoretical results. The code for this work can be found at https://***/Valdeira/EF-VFL. © 2024, CC BY.

关键词： Federated learning

Multi-Keypoint Affordance Representation for Functional Dexterous Grasping

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Yang, Fan Luo, Dongsheng Chen, Wenrui Lin, Jiacheng Cai, Junjie Yang, Kailun Li, Zhiyong Wang, Yaonan School of Robotics Hunan University China National Engineering Research Center of Robot Visual Perception and Control Technology Hunan University China College of Computer Science and Electronic Engineering Hunan University Changsha China

Functional dexterous grasping requires precise hand-object interaction, going beyond simple gripping. Existing affordance-based methods primarily predict coarse interaction regions and cannot directly constrain the grasping posture, leading to a disconnection between visual perception and manipulation. To address this issue, we propose a multi-keypoint affordance representation for functional dexterous grasping, which directly encodes task-driven grasp configurations by localizing functional contact points. Our method introduces Contact-guided Multi-Keypoint Affordance (CMKA), leveraging human grasping experience images for weak supervision combined with Large Vision Models for fine affordance feature extraction, achieving generalization while avoiding manual keypoint annotations. Additionally, we present a Keypoint-based Grasp matrix Transformation (KGT) method, ensuring spatial consistency between hand keypoints and object contact points, thus providing a direct link between visual perception and dexterous grasping actions. Experiments on public real-world FAH datasets, IsaacGym simulation, and challenging robotic tasks demonstrate that our method significantly improves affordance localization accuracy, grasp consistency, and generalization to unseen tools and tasks, bridging the gap between visual affordance learning and dexterous robotic manipulation. The source code and demo videos will be publicly available at https://***/PopeyePxx/MKA. Copyright © 2025, The Authors. All rights reserved.

关键词： Vision

Edge-SAN: An Edge-Prompted Foundation Model for Accurate Nuclei Instance Segmentation in Histology Images

学校读者我要写书评

暂无评论

Edge-SAN: An Edge-Prompted Foundation Model for Accurate Nuc...

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Xuening Wu Yiqing Shen Qing Zhao Yanlan Kang Ruiqi Hu Wenqiang Zhang Shanghai Engineering Research Center of AI & Robotics Academy for Engineering & Technology Fudan University Shanghai China Department of Computer Science Johns Hopkins University Baltimore MD USA Department of Applied Mathematics Hong Kong Polytechnic University Hong Kong Engineering Research Center of AI & Robotics Ministry of Education Academy for Engineering & Technology School of Computer Science Fudan University Shanghai China

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

Accurate nuclei segmentation is fundamental in histology image analysis, playing an essential role in cancer grading and diagnosis. However, this task remains challenging due to variations in staining protocols, heterogeneity among nuclei types, and the densely clustered nature of nuclei. While SAM exhibits zero-shot generalization capabilities in natural image segmentation, its performance degrades when applied to nuclei segmentation in histology images. Existing adaptations of SAM for medical imaging primarily focus on organ or lesion segmentation, which differs substantially from nuclei segmentation due to the unique characteristics of nuclei—specifically, their sparse distribution combined with dense clustering. To address these challenges, we propose Edge-SAN (Segment Any Nuclei with Edge Prompting), an interactive segmentation foundation model specifically designed for nuclei segmentation. Edge-SAN introduces a novel edge prompting method that enhances the delineation of nuclei boundaries, particularly among densely clustered nuclei, by leveraging edge information to improve segmentation accuracy. We evaluate Edge-SAN on 12 diverse datasets in both few-shot and zero-shot scenarios, demonstrating its effectiveness as a foundation model for nuclei segmentation, achieving 66.81% AJI and 73.13% DSC—improvements of 16.33% and 15.48% over SAM-Med2D, respectively. The code is available at https://***/deep-geo/Edge-SAN.

关键词： Instance segmentation Training Technological innovation Accuracy Histopathology Foundation models Image edge detection Biological system modeling Real-time systems Cancer

Autonomous Number Plate Detection System for Vehicle Identification and Tracking

学校读者我要写书评

暂无评论

Autonomous Number Plate Detection System for Vehicle Identif...

Recent Trends in Microelectronics, Automation, Computing and Communications Systems (ICMACC), International Conference on

作者： Neha Sri Nareddy Abhinaya Polneni Rekha Baithi Pratyusha Kunchamwar Sunil Kumar Suvarna Durgabhavani Battu Naveena Budda Vikas Agarwal Premchander Munimanda AI IoT and Robotics Lab (AIR Lab) AGVs Group Autonomous Robotics Systems Limited Hyderabad India Department of Information Technology Malla Reddy Engineering College for Women Hyderabad India Ideabytes Software India Private Limited Hyderabad India School of Computer Science Georgia Tech Atlanta USA School of Computer Science and Engineering Malla Reddy Engineering College for Women Hyderabad India

ISBN: (数字)9798350366570

ISBN: (纸本)9798350366587

The autonomous number plate detection system plays a crucial role in modern transportation, law enforcement, and security infrastructure. Technical approaches using artificial intelligence, machine learning, and computer vision are actively researched to achieve ease of maintenance through real-time vehicle detection. The recent development has drastically improved the accuracy of object detection and recognition systems in deep neural networks. Using these techniques, vehicle number plates can easily be detected autonomously for vehicle identification and tracking. Here, we have used a custom-trained TensorFlow-based number plate detection method to autonomously detect vehicles using images captured by a smartphone, or surveillance camera. It showed an impressive mAP @ 0.5 of 95%, and demonstrated limitations in long-distance detection, leading us to designate it as the optimal vehicle detection model for accuracy. We designed and developed an autonomous number plate detection system for vehicle identification and tracking, which includes web-based, android-based, and embedded-based applications. In addition, we evaluated the proposed autonomous number plate detection system with real-time images and videos. The proposed system achieved real-time vehicle detection and tracking, boasting a commendable 90% detection accuracy.

关键词： Visualization Accuracy Law enforcement System performance Transportation Artificial neural networks Real-time systems Security License plate recognition Videos

Three weak solutions for a (p, q)-Schrödinger-Kirchhoff type equation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Ahmed, Ahmed Ahmedatt, Taghi Aberqi, Ahmed University of Nouakchott Faculty of Science and Technology Mathematics and Computer Sciences Department Research Unit Geometry Algebra Analysis and Applications Nouakchott Mauritania National School of Applied Sciences Sidi Mohamed Ben Abdellah University Fez Morocco

In this manuscript, we investigate a (p, q)-Schrödinger-Kirchhoff equation involving a continuous positive potential that meets the del Pino-Felmer type conditions. Using Recceri’s classical variational approach...

关键词：

D2SP: Dynamic Dual-Stage Purification Framework for Dual Noise Mitigation in Vision-based Affective Recognition.

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wang, Haoran Mai, Xinji Tao, Zeng Tong, Xuan Lin, Junxiong Wang, Yan Yu, Jiawen Wang, Boyang Yan, Shaoqi Zhao, Qing Zhou, Ziheng Gao, Shuyong Zhang, Wenqiang Shanghai Engineering Research Center of AI & Robotics Academy for Engineering & Technology Fudan University Shanghai China School of Information Science and Technology Fudan University Shanghai China Fudan University Shanghai China Engineering Research Center of AI & Robotics Ministry of Education Academy for Engineering & Technology Fudan University Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University Shanghai China

The contemporary state-of-the-art of Dynamic Facial Expression Recognition (DFER) technology facilitates remarkable progress by deriving emotional mappings of facial expressions from video content, underpinned by training on voluminous datasets. Yet, the DFER datasets encompass a substantial volume of noise data. Noise arises from low-quality captures that defy logical labeling, and instances that suffer from mislabeling due to annotation bias, engendering two principal types of uncertainty: the uncertainty regarding data usability and the uncertainty concerning label reliability. Addressing the two types of uncertainty, we have meticulously crafted a two-stage framework aiming at Seeking Certain data In extensive Uncertain data (SCIU). This initiative aims to purge the DFER datasets of these uncertainties, thereby ensuring that only clean, verified data is employed in training processes. To mitigate the issue of low-quality samples, we introduce the Coarse-Grained Pruning (CGP) stage, which assesses sample weights and prunes those deemed unusable due to their low weight. For samples with incorrect annotations, the Fine-Grained Correction (FGC) stage evaluates prediction stability to rectify mislabeled data. Moreover, SCIU is conceived as a universally compatible, plug-and-play framework, tailored to integrate seamlessly with prevailing DFER methodologies. Rigorous experiments across prevalent DFER datasets and against numerous benchmark methods substantiates SCIU’s capacity to markedly elevate performance metrics. Copyright © 2024, The Authors. All rights reserved.

关键词： Face recognition

A Multi-modal Hybrid Robot with Enhanced Traversal Performance*

学校读者我要写书评

暂无评论

A Multi-modal Hybrid Robot with Enhanced Traversal Performan...

IEEE International Conference on robotics and Automation (ICRA)

作者： Zhipeng He Na Zhao Yudong Luo Sian Long Xi Luo Hongbin Deng School of Mechatronical Engineering Beijing Institute of Technology Beijing China Department of Computer Science and Technology Morphing Robotics Lab Dalian Maritime University Dalian China Yichang Testing Tech. Research Institution Yichang China

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

Current multi-modal hybrid robots with flight and wheeled modes have fallen into the dilemma that they can only avoid obstacles by re-taking off when encountering obstacles due to the poor performance of wheeled obstacle-crossing. To tackle this problem, this paper presents a novel multi-modal hybrid robot with the ability to actively adjust the wheel’s size, which is inspired by the behavior of the turtle’s legs when it encounters obstacles, to enhance the traversal performance. In detail, we describe the hardware design that allows the robot to achieve a modal switch between flight and wheeled modes through foldable structures and variable wheel diameters; then, we present the architecture to control these two morphing mechanisms. After that, we establish the theoretical kinematic models for both the foldable arm and variable wheel and carry out extensive experiments to test the performance of the foldable arm, the variable-diameter wheel, as well as the traversal performance of the robot. Experimental results show that the proposed multimodal robot can realize the function of a quadrotor, respond quickly with full-scale folding within 0.9 s, climb a maximum slope of 36°, and traverse narrow passageways, which exhibit superior mobility and environmental adaptability.

关键词： Legged locomotion Wheels Prototypes Manipulators Sensors Mobile robots Collision avoidance

学校读者我要写书评

暂无评论

无人飞行器在不确定扰动下的动态目标跟踪

Engineering 2024年第4期35卷 74-85页

作者： Yanjie Chen Yangning Wu Limin Lan Hang Zhong Zhiqiang Miao Hui Zhang Yaonan Wang School of Mechanical Engineering and Automation Fuzhou UniversityFuzhou 350108China Department of Computer Science Aberystwyth UniversityAberystwyth SY233DBUK School of Robotics Hunan UniversityChangsha 410082China College of Electrical and Information Engineering Hunan UniversityChangsha 410082China National Engineering Research Center of Robot Visual Perception and Control Technology Hunan UniversityChangsha 410082China

This study proposes an image-based visual servoing(IBVS)method based on a velocity observer for an unmanned aerial vehicle(UAV)for tracking a dynamic target in Global Positioning System(GPS)-denied *** proposed method derives the simplified and decoupled image dynamics of underactuated UAVs using a constructed virtual camera and then considers the uncertainties caused by the unpredictable rotations and velocities of the dynamic target.A novel image depth model that extends the IBVS method to track a rotating target with arbitrary orientations is *** depth model ensures image feature accuracy and image trajectory smoothness in rotating target *** relative velocities of the UAV and the dynamic target are estimated using the proposed velocity *** to the velocity observer,translational velocity measurements are not required,and the control chatter caused by noise-containing measurements is *** integral-based filter is proposed to compensate for unpredictable environmental disturbances in order to improve the antidisturbance *** stability of the velocity observer and IBVS controller is analyzed using the Lyapunov *** simulations and multistage experiments are conducted to illustrate the tracking stability,anti-disturbance ability,and tracking robustness of the proposed method with a dynamic rotating target.

关键词： Unmanned aerial vehicle Visual servoing Velocity observer Target tracking

DeTrack: In-model Latent Denoising Learning for Visual Object Tracking

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Zhou, Xinyu Li, Jinglun Hong, Lingyi Jiang, Kaixun Guo, Pinxue Ge, Weifeng Zhang, Wenqiang Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University Shanghai China Shanghai Engineering Research Center of AI & Robotics Academy for Engineering and Technology Fudan University Shanghai China

Previous visual object tracking methods employ image-feature regression models or coordinate autoregression models for bounding box prediction. Image-feature regression methods heavily depend on matching results and do not utilize positional prior, while the autoregressive approach can only be trained using bounding boxes available in the training set, potentially resulting in suboptimal performance during testing with unseen data. Inspired by the diffusion model, denoising learning enhances the model's robustness to unseen data. Therefore, We introduce noise to bounding boxes, generating noisy boxes for training, thus enhancing model robustness on testing data. We propose a new paradigm to formulate the visual object tracking problem as a denoising learning process. However, tracking algorithms are usually asked to run in real-time, directly applying the diffusion model to object tracking would severely impair tracking speed. Therefore, we decompose the denoising learning process into every denoising block within a model, not by running the model multiple times, and thus we summarize the proposed paradigm as an in-model latent denoising learning process. Specifically, we propose a denoising Vision Transformer (ViT), which is composed of multiple denoising blocks. In the denoising block, template and search embeddings are projected into every denoising block as conditions. A denoising block is responsible for removing the noise in a predicted bounding box, and multiple stacked denoising blocks cooperate to accomplish the whole denoising process. Subsequently, we utilize image features and trajectory information to refine the denoised bounding box. Besides, we also utilize trajectory memory and visual memory to improve tracking stability. Experimental results validate the effectiveness of our approach, achieving competitive performance on several challenging datasets. The proposed in-model latent denoising tracker achieve real-time speed, rendering denoising learning

关键词： Regression analysis