检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Lu, Yuan de Ocáriz Borde, Haitz Sáez Liò, Pietro University of Cambridge Department of Engineering United Kingdom University of Oxford Oxford Robotics Institute United Kingdom University of Cambridge Department of Computer Science & Technology United Kingdom

In real-world scenarios, although data entities may possess inherent relationships, the specific graph illustrating their connections might not be directly accessible. Latent graph inference addresses this issue by enabling Graph Neural Networks (GNNs) to operate on point cloud data, dynamically learning the necessary graph structure. These graphs are often derived from a latent embedding space, which can be modeled using Euclidean, hyperbolic, spherical, or product spaces. However, currently, there is no principled differentiable method for determining the optimal embedding space. In this work, we introduce the Attentional Multi-Embedding Selection (AMES) framework, a differentiable method for selecting the best embedding space for latent graph inference through backpropagation, considering a downstream task. Our framework consistently achieves comparable or superior results compared to previous methods for latent graph inference across five benchmark datasets. Importantly, our approach eliminates the need for conducting multiple experiments to identify the optimal embedding space. Furthermore, we explore interpretability techniques that track the gradient contributions of different latent graphs, shedding light on how our attention-based, fully differentiable approach learns to choose the appropriate latent space. In line with previous works, our experiments emphasize the advantages of hyperbolic spaces in enhancing performance. More importantly, our interpretability framework provides a general approach for quantitatively comparing embedding spaces across different tasks based on their contributions, a dimension that has been overlooked in previous literature on latent graph inference. © 2023, CC BY.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

VFL+: Low-Coupling Vertical Federated Learning With Privileged Information Paradigm

引用

IEEE Transactions on Emerging Topics in Computational Intelligence 2025年

作者： Dai, Wei Cui, Teng Zhang, Tong Chen, Badong China University of Mining Technology School of Information and Control Engineering Xuzhou221116 China South China University of Technology School of Computer Science and Engineering Guangzhou510006 China Xi'an Jiaotong University Institute of Artificial Intelligence and Robotics Xi'an710049 China

Vertical Federated Learning (VFL) enables the construction of models by combining clients with different features without compromising privacy. Existing VFL methods exhibit tightly coupled participant parameters, resulting in substantial interdependencies among clients during the prediction phase, which significantly hampers the model's usability. To tackle these challenges, this paper studies a VFL approach with low coupling of parameters between clients. Drawing inspiration from federated cooperation and teacher-supervised learning, we propose a low-coupling vertical federated learning with privileged information paradigm (VFL+), allowing participants to make autonomous predictions. Specifically, VFL+ treats information from other clients as privileged data during the training phase rather than the testing phase, thereby achieving independence in individual model predictions. Subsequently, this paper further investigates three typical scenarios of vertical cooperation and designs corresponding cooperative frameworks. Systematic experiments on real data sets demonstrate the effectiveness of the proposed method. © 2017 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Robust Semi-Supervised Deep Nonnegative Matrix Factorization with Constraint Propagation for Data Representation

引用

IEEE Transactions on Big Data 2025年

作者： Peng, Siyuan Yin, Jingxing Yang, Zhijing Nie, Feiping Chen, Badong Guangdong University of Technology School of Information Engineering 510006 China Northwestern Polytechnical University School of Computer Science Center for OPTical IMagery Analysis and Learning Xi'an710072 China Xi'an Jiaotong University Institute of Artificial Intelligence and Robotics Xi'an710049 China

Deep nonnegative matrix factorization (DNMF) technique has attached much great attention in recent year, since it can effectively discover the underlying hierarchical structure of complex data. However, most existing unsupervised and semi-supervised DNMF approaches not only suffer from the noisy data seriously, but also fail to enhance the decomposition quality of DNMF obviously by using the obtained supervisory information. To overcome these drawbacks, a robust semi-supervised DNMF method, called the correntropy based semi-supervised DNMF with constraint propagation (CSDCP), is proposed in this paper for learning a compact and meaningful data representation from the original data. Particularly, instead of adopting the traditional Frobenius norm, CSDCP employs the nonlinear and local similarity measure (e.g., correntropy) as the loss function in DNMF to enhance the robustness of DNMF for the noisy data. In addition, the hypergraph based constraint propagation (HCP) algorithm is adopted in CSDCP to exploit the limited supervisory information fully for capturing good data representation. Moreover, algorithm analysis of CSDCP is presented in this paper, including convergence analysis, robustness analysis supervised information analysis, and computational complexity. Extensive experimental results have illustrated that, in comparison to the most related DNMF approaches, CSDCP usually has better clustering results on six nonnegative datasets in clustering tasks. © 2015 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Loss Distillation via Gradient Matching for Point Cloud Completion with Weighted Chamfer Distance

Loss Distillation via Gradient Matching for Point Cloud Comp...

引用

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

作者： Fangzhou Lin Haotian Liu Haoying Zhou Songlin Hou Kazunori D Yamada Gregory S. Fischer Yanhua Li Haichong K. Zhang Ziming Zhang Department of Robotics Engineering Worcester Polytechnic Institute Worcester MA USA Graduate School of Information Sciences Tohoku University Sendai Japan Dell Technologies Hopkinton MA USA Department of Computer Science Worcester Polytechnic Institute Worcester MA USA Department of Electrical & Computer Engineering Worcester Polytechnic Institute Worcester MA USA

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

3D point clouds enhanced the robot’s ability to perceive the geometrical information of the environments, making it possible for many downstream tasks such as grasp pose detection and scene understanding. The performance of these tasks, though, heavily relies on the quality of data input, as incomplete can lead to poor results and failure cases. Recent training loss functions designed for deep learning-based point cloud completion, such as Chamfer distance (CD) and its variants (e.g. HyperCD [1]), imply a good gradient weighting scheme can significantly boost performance. However, these CD-based loss functions usually require data-related parameter tuning, which can be time-consuming for data-extensive tasks. To address this issue, we aim to find a family of weighted training losses (weighted CD) that requires no parameter tuning. To this end, we propose a search scheme, Loss Distillation via Gradient Matching, to find good candidate loss functions by mimicking the learning behavior in backpropagation between HyperCD and weighted CD. Once this is done, we propose a novel bilevel optimization formula to train the backbone network based on the weighted CD loss. We observe that: (1) with proper weighted functions, the weighted CD can always achieve similar performance to HyperCD, and (2) the Landau weighted CD, namely Landau CD, can outperform HyperCD for point cloud completion and lead to new state-of-the-art results on several benchmark datasets. Our demo code is available at https://***/Zhang-VISLab/IROS2024-LossDistillationWeightedCD.

关键词： Point cloud compression Training Three-dimensional displays Laser radar Benchmark testing Iterative algorithms Tuning Optimization Intelligent robots Convergence

来源：评论

学校读者我要写书评

暂无评论

Weakly-Supervised Learning via Multi-Lateral Decoder Branching for Tool Segmentation in Robot-Assisted Cardiovascular Catheterization

arXiv

引用

arXiv 2024年

作者： Omisore, Olatunji Mumini Akinyemi, Toluwanimi Nguyen, Anh Wang, Lei Research Center for Medical Robotics and Minimally Invasive Surgical Devices Shenzhen Institute of Advanced Technology Chinese Academy of Sciences China Smart Robotic Lab Department of Computer Science University of Liverpool United Kingdom

Robot-assisted catheterization has garnered a good attention for its potentials in treating cardiovascular diseases. However, advancing surgeon-robot collaboration still requires further research, particularly on task-specific automation. For instance, automated tool segmentation can assist surgeons in visualizing and tracking endovascular tools during procedures. While learning-based models have demonstrated state-of-the-art segmentation performances, generating ground-truth labels for fully-supervised methods is labor-intensive, time consuming, and costly. In this study, we developed a weakly-supervised learning method that is based on multi-lateral pseudo labeling for tool segmentation in cardiovascular angiogram datasets. The method utilizes a modified U-Net architecture featuring one encoder and multiple laterally branched decoders. The decoders generate diverse pseudo labels under different perturbations to augment the available partial annotation for model training. A mixed loss function with shared consistency was adapted for this purpose. The weakly-supervised model was trained end-to-end and validated using partially annotated angiogram data from three cardiovascular catheterization procedures. Validation results show that the weakly-supervised model could perform closer to fully-supervised models. Furthermore, the proposed multi-lateral approach outperforms three well known weakly-supervised learning methods, offering the highest segmentation performance across the three angiogram datasets. Numerous ablation studies confirmed the model’s consistent performance under different settings. Finally, the model was applied for tool segmentation in a robot-assisted catheterization experiments. The model enhanced visualization with high connectivity indices for guidewire and catheter, and a mean segmentation time of 35.26±11.29 ms per frame. This study provides a fast, stable, and less expensive method for segmentation and visualization of endovascular tools in ro

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

N Observation Photon Counting Imaging With Preprocessing

N Observation Photon Counting Imaging With Preprocessing

引用

International Joint Conference on computer science and Software Engineering (JCSSE)

作者： Gilsu Yeo Hyun-Woo Kim Myungjin Cho Min-Chul Lee Graduate School of Computer Science and Systems Engineering Kyushu Institute of Technology Iizuka City Fukuoka School of ICT Robotics and Mechanical Engineering IITC Hankyoung National University Anseong Kyonggi-do Republic of Korea

ISBN: (数字)9798350381764

ISBN: (纸本)9798350381771

In this paper, we explain our method to enhance the conventional integral imaging method. The photon-counting imaging is used to obtain the image including objects or scene under photon-lacked environments. And the conventional $N$ observation photon counting imaging obtains three-dimensional (3D) image by repeating the estimation to obtain more accurate information of object or scene than conventional photon-counting imaging under almost photon-lacked environments. To enhance the visual quality and information of 3D objects in the conventional $\mathrm{N}$ observation photon counting imaging, the volumetric computational reconstruction (VCR) is utilized as preprocessing and combined $N$ observation photon counting integral imaging in this paper.

关键词： Measurement Visualization Three-dimensional displays Accuracy Imaging Lakes Video recording

来源：评论

学校读者我要写书评

暂无评论

Intelligent Accident Recognition and Notification System using Hybrid Deep Learning and IoT

Intelligent Accident Recognition and Notification System usi...

引用

Soft Computing for Security Applications (ICSCSA), International Conference on

作者： P. Sathish Kumar Ramesh Singh Rawat Manish Shrimali Swapnil Parikh Harshal Patil Ramya Maranan Department of Robotics & Automation United Institute of Technology Coimbatore Tamil Nadu India Department of Computer Science & Engineering Graphic Era Deemed to be University Dehradun Uttarakhand India Department of Computer Science and IT Janardan Rai Nagar Rajasthan Vidyapeeth (Deemed to be University) Udaipur Rajasthan India Department of Computer Science and Engineering Parul Institute of Engineering and Technology Parul University Gujarat India Computer Science and Engineering Symbiosis Institute of Technology Symbiosis International (Deemed University) Pune Maharashtra India Department of Research and Innovation Saveetha School of Engineering SIMATS Chennai Tamil Nadu India

ISBN: (数字)9798331515720

ISBN: (纸本)9798331515737

Ensuring the safety of individuals should be a top priority. Everyone wants to return home safely. Many riders continue to disregard safety constraints, increasing the chance of accidents that result in death. It is critical to incorporate the latest technology into road monitoring systems to make cities smarter and to ensure rider safety. For this research, Deep Learning (DL) and the Internet of Things (IoT) were chosen for effective road surveillance and alert systems. The primary goal of the study is to detect and inform riders about accidents that occur along their path and to provide details about the location of the detected accident. Additionally, the system provides the vehicle's speed. To identify automobile accidents in the footage, a hybrid DL model that includes Convolutional Neural Network - Bidirectional Long Short-Term Memory (CNN-Bi-LSTM) is suggested. For the model's training, both accident and non-accident data were collected. The model is evaluated using three metrics: accuracy, loss, and execution time. The next step is to upload the recommended model to the ThingSpeak cloud. A Graphical User Interface (GUI) is being created in the ThingSpeak cloud. The GUI displays the vehicle's speed, accident images, and the precise location of the accident scene using the Raspberry Pi, speed sensor, Pi-camera, and Global Positioning System (GPS) module. An LED is also integrated into the GUI to alert the user. A real-world test is conducted on the designed system. The proposed solution has many advantages and will ensure driver safety.

关键词： Deep learning Training Cloud computing Accuracy Roads Surveillance Feature extraction Safety Accidents Graphical user interfaces

来源：评论

学校读者我要写书评

暂无评论

POMDP-Guided Active Force-Based Search for Robotic Insertion

arXiv

引用

arXiv 2024年

作者： Wang, Chen Luo, Haoxiang Zhang, Kun Chen, Hua Pan, Jia Zhang, Wei School of System Design and Intelligent Manufacturing Southern University of Science and Technology Shenzhen China Department of Computer Science The University of Hong Kong Hong Kong Cheng Kar-Shun Robotics Institute Hong Kong University of Science and Technology Clear Water Bay Hong Kong

In robotic insertion tasks where the uncertainty exceeds the allowable tolerance, a good search strategy is essential for successful insertion and significantly influences efficiency. The commonly used blind search method is time-consuming and does not exploit the rich contact information. In this paper, we propose a novel search strategy that actively utilizes the information contained in the contact configuration and shows high efficiency. In particular, we formulate this problem as a Partially Observable Markov Decision Process (POMDP) with carefully designed primitives based on an in-depth analysis of the contact configuration's static stability. From the formulated POMDP, we can derive a novel search strategy. Thanks to its simplicity, this search strategy can be incorporated into a Finite-State-Machine (FSM) controller. The behaviors of the FSM controller are realized through a low-level Cartesian Impedance Controller. Our method is based purely on the robot's proprioceptive sensing and does not need visual or tactile sensors. To evaluate the effectiveness of our proposed strategy and control framework, we conduct extensive comparison experiments in simulation, where we compare our method with the baseline approach. The results demonstrate that our proposed method achieves a higher success rate with a shorter search time and search trajectory length compared to the baseline method. Additionally, we show that our method is robust to various initial displacement errors. Copyright © 2024, The Authors. All rights reserved.

关键词： robotics

来源：评论

学校读者我要写书评

暂无评论

Web Based Lidar Point Cloud Visualization and Teleoperation Tool for Robots

Web Based Lidar Point Cloud Visualization and Teleoperation ...

引用

International Conference on Computing and Networking Technology (ICCNT)

作者： Suraj Nukala Midori Sugaya Seenu Nagarajan Department of Mechatronics Engineering Hindustan Institute of Technology and Science Chennai Tamil Nadu India Department of Computer Science Shibaura Institute of Technology Tokyo Japan Department of Mechatronics Engineering Centre for Automation and Robotics (ANRO) Hindustan Institute of Technology and Science Chennai 603103 Tamil Nadu India

This paper presents the development of a teleoperation system designed for remote control of a ROS robot over the internet. While existing visualization tools like rvis are limited to the host system or local area network, this system aims to overcome those constraints. The system's primary objectives are remote motor control and lidar data visualization using point cloud and camera data, and it is compatible with any ROS system, tested with ROS2 *** system meets the following requirements:*** ability to work over the *** ability to visualize lidar and camera *** ability to control *** achieve this, the system relies heavily on ROSBridge, which is a ROS node that exposes ROS communication channels such as topics, services, and activities out to the internet using websockets. This enables any client to subscribe and publish data to and from the ROS communication *** user interface of envious incorporates various interactive elements, including the camera feed, motor controllers, and lidar data visualization. These components are implemented using roslibjs, react, and react three fiber, which leverages webgl and threejs libraries to create an abstraction layer for seamless integration with the web *** leveraging ROSBridge and modern web technologies, the proposed system offers the ability to control motors and visualize lidar and camera data remotely over the internet. It provides a user-friendly interface for interacting with the ROS system, facilitating teleoperation of robots from any location with an internet connection. This system expands the capabilities of ROS beyond local networks, opening up new possibilities for remote robotics applications and *** the capabilities of this system would opens up a world of exciting applications, one of which is a swarm mapping system that takes leverage of multiple interconnected robots to collaboratively map and explore an area

关键词：

来源：评论

学校读者我要写书评

暂无评论

HairDiffusion: Vivid Multi-Colored Hair Editing via Latent Diffusion

arXiv

引用

arXiv 2024年

作者： Zeng, Yu Zhang, Yang Liu, Jiachen Shen, Linlin Deng, Kaijun He, Weizhao Wang, Jinbao Computer Vision Institute School of Computer Science & Software Engineering Shenzhen University China Shenzhen Institute of Artificial Intelligence and Robotics for Society China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China Guangdong Provincial Key Laboratory of Intelligent Information Processing China

Hair editing is a critical image synthesis task that aims to edit hair color and hairstyle using text descriptions or reference images, while preserving irrelevant attributes (e.g., identity, background, cloth). Many existing methods are based on StyleGAN to address this task. However, due to the limited spatial distribution of StyleGAN, it struggles with multiple hair color editing and facial preservation. Considering the advancements in diffusion models, we utilize Latent Diffusion Models (LDMs) for hairstyle editing. Our approach introduces Multi-stage Hairstyle Blend (MHB), effectively separating control of hair color and hairstyle in diffusion latent space. Additionally, we train a warping module to align the hair color with the target region. To further enhance multi-color hairstyle editing, we fine-tuned a CLIP model using a multi-color hairstyle dataset. Our method not only tackles the complexity of multi-color hairstyles but also addresses the challenge of preserving original colors during diffusion editing. Extensive experiments showcase the superiority of our method in editing multi-color hairstyles while preserving facial attributes given textual descriptions and reference images. © 2024, CC BY.

关键词： Color image processing

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：