检索结果-内蒙古大学图书馆

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： He, Xilin Hu, Jingyu Lin, Qinliang Luo, Cheng Xie, Weicheng Song, Siyang Khan, Muhammad Haris Shen, Linlin Computer Vision Institute School of Computer Science & Software Engineering Shenzhen University China Shenzhen Institute of Artificial Intelligence and Robotics for Society China Guangdong Provincial Key Laboratory of Intelligent Information Processing China University of Exeter United Kingdom Mohamed bin Zayed University of Artificial Intelligence United Arab Emirates

Domain generalization methods aim to learn transferable knowledge from source domains that can generalize well to unseen target domains. Recent studies show that neural networks frequently suffer from a simplicity-biased learning behavior which leads to over-reliance on specific frequency sets, namely as frequency shortcuts, instead of semantic information, resulting in poor generalization performance. Despite previous data augmentation techniques successfully enhancing generalization performances, they intend to apply more frequency shortcuts, thereby causing hallucinations of generalization improvement. In this paper, we aim to prevent such learning behavior of applying frequency shortcuts from a data-driven perspective. Given the theoretical justification of models' biased learning behavior on different spatial frequency components, which is based on the dataset frequency properties, we argue that the learning behavior on various frequency components could be manipulated by changing the dataset statistical structure in the Fourier domain. Intuitively, as frequency shortcuts are hidden in the dominant and highly dependent frequencies of dataset structure, dynamically perturbating the over-reliance frequency components could prevent the application of frequency shortcuts. To this end, we propose two effective data augmentation modules designed to collaboratively and adaptively adjust the frequency characteristic of the dataset, aiming to dynamically influence the learning behavior of the model and ultimately serving as a strategy to mitigate shortcut learning. Code is available at AdvFrequency. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Control Synthesis Problem of Traffic Flow in Urban Network

Control Synthesis Problem of Traffic Flow in Urban Network

引用

International Conference on Control, Decision and Information Technologies (CoDIT)

作者： Elena Sofronova Askhat Diveev Department of Robotics Control Federal Research Center "Computer Science and Control" of the Russian Academy of Sciences Moscow Russia

ISBN: (数字)9798350373974

ISBN: (纸本)9798350373981

The paper deals with the problem of traffic flow control in the urban road networks. The control is performed by traffic lights at intersections. The statement of the optimal control problem is given. A model-based approach is applied. The mathematical model of traffic flow based on the theory of controlled networks is used. A quality criterion is set. It is pointed out that a feature of the control of this object is its cyclical nature. Control is repeated at a certain time interval, which is called a control cycle. The duration of traffic light phases is considered as control. The phases switch sequentially in a certain order. Additional constraints are given that must be taken into account when choosing phase duration. As a result of solution of the optimal control problem the coordination plan for traffic lights is obtained. Coordination plan is cyclically repeated. The control synthesis problem is formulated that accounts for change in initial state. It is proposed to solve the control synthesis problem as a problem of selecting an optimal coordination plan from a set of plans calculated in advance for various initial flow states and model parameters.

关键词： Roads Decision making Optimal control Machine learning Switches Mathematical models Information technology Optimization

来源：评论

学校读者我要写书评

暂无评论

Improving sharpness-aware minimization by lookahead 24

Improving sharpness-aware minimization by lookahead

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Runsheng Yu Youzhi Zhang James T. Kwok Department of Computer Science and Engineering The Hong Kong University of Science and Technology Centre for Artificial Intelligence and Robotics Hong Kong Institute of Science & Innovation CAS

Sharpness-Aware Minimization (SAM), which performs gradient descent on adversarially perturbed weights, can improve generalization by identifying flatter minima. However, recent studies have shown that SAM may suffer from convergence instability and oscillate around saddle points, resulting in slow convergence and inferior performance. To address this problem, we propose the use of a lookahead mechanism to gather more information about the landscape by looking further ahead, and thus find a better trajectory to converge. By examining the nature of SAM, we simplify the extrapolation procedure, resulting in a more efficient algorithm. Theoretical results show that the proposed method converges to a stationary point and is less prone to saddle points. Experiments on standard benchmark datasets also verify that the proposed method outperforms the SOTAs, and converge more effectively to flat minima.

关键词：

来源：评论

学校读者我要写书评

暂无评论

InteLiPlan: An Interactive Lightweight LLM-Based Planner for Domestic Robot Autonomy

arXiv

引用

arXiv 2024年

作者： Ly, Kim Tien Lu, Kai Havoutis, Ioannis Oxford Robotics Institute University of Oxford United Kingdom Department of Computer Science University of Oxford United Kingdom

We introduce an interactive LLM-based framework designed to enhance the autonomy and robustness of domestic robots, targeting embodied intelligence. Our approach reduces reliance on large-scale data and incorporates a robot-agnostic pipeline that embodies an LLM. Our framework, InteLiPlan, ensures that the LLM’s decision-making capabilities are effectively aligned with robotic functions, enhancing operational robustness and adaptability, while our human-in-the-loop mechanism allows for real-time human intervention when user instruction is required. We evaluate our method in both simulation and on the real Toyota Human Support Robot (HSR). Our method achieves a 93% success rate in the ‘fetch me’ task completion with failure recovery, highlighting its capability in both failure reasoning and task planning. InteLiPlan achieves comparable performance to state-of-the-art large-scale LLM-based robotics planners, while using only real-time onboard computing. More information about InteLiPlan can be found at the project website: https://***/InteLiPlan. Copyright © 2024, The Authors. All rights reserved.

关键词： Human robot interaction

来源：评论

学校读者我要写书评

暂无评论

The Field of Requirements Engineering Education 35

The Field of Requirements Engineering Education

引用

35th IEEE International Conference on Software Engineering Education and Training, CSEE and T 2023

作者： Daun, Marian Grubb, Alicia M. Stenkova, Viktoria Tenbergen, Bastian Technical University of Applied Sciences Würzburg-Schweinfurt Center for Robotics Schweinfurt Germany Smith College Dept. of Computer Science NorthamptonMA United States University of Duisburg-Essen Paluno Essen Germany State University of New York Dept. of Computer Science OswegoNY United States

ISBN: (纸本)9798350322026

Requirements engineering (RE) is an essential part of the software development process. Good RE, among others, is the basis for high quality software, considerably reduces the risk for software projects to fail entirely or with budget-overspending and is crucial for coordinating systems and software engineering. Thus, RE education is a vital part of software engineering curricula. However, a central concept of what RE education comprise and how to best teach RE is lacking. Therefore, we conducted a systematic literature review of the field and provide a systematic map describing the state of the RE education field. Results for key trends in RE instruction of the past decade include involvement of real or realistic stakeholders, teaching predominantly elicitation as an RE activity, and increasing student factors such as motivation or communication skills. © 2023 IEEE.

关键词： Requirements engineering

来源：评论

学校读者我要写书评

暂无评论

FaceEngine: A Tracking-Based Framework for Real-Time Face Recognition in Video Surveillance System

引用

SN computer science 2024年第5期5卷 1-20页

作者： Imran, Ahsan Ahmed, Riad Hasan, Md Mehedi Ahmed, M. Helal Uddin Azad, A.K.M. Alyami, Salem A. Department of Robotics and Mechatronics Engineering University of Dhaka Dhaka 1000 Bangladesh Department of Computer Science and Engineering BRAC University Dhaka 1212 Bangladesh Department of Management Information Systems University of Dhaka Dhaka 1000 Bangladesh Department of Mathematics and Statistics College of Science Imam Mohammad Ibn Saud Islamic University (IMSIU) Riyadh 11432 Saudi Arabia

The escalating concern over worldwide security and criminal activities has led to the emergence and significance of closed-circuit television video surveillance systems as an essential tool for diverse security purposes. These systems are extensively implemented and serve a crucial function in the surveillance and upkeep of security. The predominant purpose of video surveillance systems is to gather data primarily for evidentiary purposes subsequent to the occurrence of a criminal incident. The demand for video surveillance systems capable of autonomously monitoring and promptly identifying criminals or intruders in real-time is steadily increasing. Nevertheless, the existing facial recognition methods pose difficulties in reliably identifying individuals who are in motion within a video frame. Moreover, conventional approaches necessitate a substantial quantity of photographs in order to achieve precise recognition following the acquisition of an individual’s facial pattern. In order to tackle these concerns, we developed the implementation of input optimisation algorithms alongside a novel framework for real-time face recognition in the context of video surveillance. The input optimization algorithms, integrated with adaptive thresholding techniques, effectively reduce the need for manual outlier removal by actively identifying outliers for each specific case. The application of this optimisation strategy has demonstrated a substantial enhancement in both the efficiency and precision of our system in comparison to alternative baseline methodologies. Through the use of a reduced set of input image, our system is capable of attaining a heightened degree of improvements. Specifically, employing tracking and temporal voting techniques enables our system to accomplish a real-time face recognition accuracy of 90.91%. The findings of this study suggest that our approach has the potential to be a valuable tool in various applications that necessitate rapid and precise fac

关键词： computer vision Deep learning Face recognition Image processing Tracking Video surveillance

来源：评论

学校读者我要写书评

暂无评论

V3D-SLAM: Robust RGB-D SLAM in Dynamic Environments with 3D Semantic Geometry Voting

V3D-SLAM: Robust RGB-D SLAM in Dynamic Environments with 3D ...

引用

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

作者： Tuan Dang Khang Nguyen Manfred Huber Department of Computer Science and Engineering Learning and Adaptive Robotics Laboratory University of Texas at Arlington Arlington TX USA

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

Simultaneous localization and mapping (SLAM) in highly dynamic environments is challenging due to the correlation complexity between moving objects and the camera pose. Many methods have been proposed to deal with this problem; however, the moving properties of dynamic objects with a moving camera remain unclear. Therefore, to improve SLAM’s performance, minimizing disruptive events of moving objects with a physical understanding of 3D shapes and dynamics of objects is needed. In this paper, we propose a robust method, V3D-SLAM, to remove moving objects via two lightweight reevaluation stages, including identifying potentially moving and static objects using a spatial-reasoned Hough voting mechanism and refining static objects by detecting dynamic noise caused by intra-object motions using Chamfer distances as similarity measurements. Through our experiment on the TUM RGB-D benchmark on dynamic sequences with ground-truth camera trajectories, the results show that our methods outperform most other recent state-of-the-art SLAM methods. Our source code is available at https://***/tuantdang/v3d-slam.

关键词： Simultaneous localization and mapping Three-dimensional displays Source coding Dynamics Noise Benchmark testing Cameras Feature extraction Trajectory Object recognition

来源：评论

学校读者我要写书评

暂无评论

CoCap: Coordinated motion Capture for multi-actor scenes in outdoor environments

arXiv

引用

arXiv 2024年

作者： Rauniyar, Aditya Corah, Micah Scherer, Sebastian Robotics Institute School of Computer Science Carnegie Mellon University PittsburghPA United States Department of Computer Science The Colorado School of Mines GoldenCO United States

Motion capture has become increasingly important, not only in computer animation but also in emerging fields like the virtual reality, bioinformatics, and humanoid training. Capturing outdoor environments offers extended horizon scenes but introduces challenges with occlusions and obstacles. Recent approaches using multi-drone systems to capture multiple actor scenes often fail to account for multi-view consistency and reasoning across cameras in cluttered environments. Coordinated motion Capture (CoCap), inspired by Conflict-Based Search (CBS), addresses this issue by coordinating view planning to ensure multi-view reasoning during conflicts. In scenarios with high occlusions and obstacles, where the likelihood of inter-robot collisions increases, CoCap demonstrates performance that approaches the ideal outcomes of unconstrained planning, outperforming existing sequential planning methods. Additionally, CoCap offers a single-robot view search approach for real-time applications in dense environments. Copyright © 2024, The Authors. All rights reserved.

关键词： Robot programming

来源：评论

学校读者我要写书评

暂无评论

DRONECOM: Dynamic Relay Operations for Network Efficient Communication in Mines

DRONECOM: Dynamic Relay Operations for Network Efficient Com...

引用

International Conference on Control, Automation and Systems ( ICCAS)

作者： Akash Patel Scott Fredriksson Samuel Nordström Emanuele Pagliari Ilias Tevetzidis Christoforos Kanellakis George Nikolakopoulos Department of Computer Science Electrical and Space Engineering Robotics & AI Team Luleå University of Technology Luleå Sweden

ISBN: (数字)9788993215380

ISBN: (纸本)9798331517939

As the routine operations are starting to become highly automated, it is crucial to develop autonomous solutions that are infrastructure independent. Achieving this is challenging due to the ever-changing landscape of mines, which complicates infrastructure development. In response, this paper introduces a robust framework employing drones to gather data from hard-to-access areas in mines and deliver the data back to the base station for routine monitoring purposes. These tasks include gathering data from operational vehicles (mine trucks, loaders etc.), as well as various sensors (e.g. monitoring rock bolts) and relaying the data to the mine’s base station for monitoring purposes. The proposed framework is based on autonomous navigation using a known point cloud map of the mine, proximity detection via Ultra WideBand (UWB) radios and the data transfer is accomplished through the IEEE 802.15.4 communication standard, operating in the 868 MHz ISM band, with the aim to guarantee long range operation. On the mission level, the drones act as data mules capable of autonomously extracting data from operating vehicles, storing the data onboard and eventually delivering the data to the base station, which is enabled through a Point and Click (PAC) autonomy framework based on global planning, reactive navigation, communication link and behavior management. The efficacy of this framework has been demonstrated through real-world experiments conducted at a test mine in Sweden, validating the overall architecture of the proposed solution.

关键词： Base stations Automation Navigation Fasteners Rocks Sensors Data mining Monitoring Drones Videos

来源：评论

学校读者我要写书评

暂无评论

On the Faithfulness of Vision Transformer Explanations

arXiv

引用

arXiv 2024年

作者： Wu, Junyi Kang, Weitai Tang, Hao Hong, Yuan Yan, Yan Department of Computer Science Illinois Institute of Technology United States Robotics Institute Carnegie Mellon University United States Department of Computer Science University of Connecticut United States

To interpret Vision Transformers, post-hoc explanations assign salience scores to input pixels, providing human-understandable heatmaps. However, whether these interpretations reflect true rationales behind the model’s output is still underexplored. To address this gap, we study the faithfulness criterion of explanations: the assigned salience scores should represent the influence of the corresponding input pixels on the model’s predictions. To evaluate faithfulness, we introduce Salience-guided Faithfulness Coefficient (SaCo), a novel evaluation metric leveraging essential information of salience distribution. Specifically, we conduct pair-wise comparisons among distinct pixel groups and then aggregate the differences in their salience scores, resulting in a coefficient that indicates the explanation’s degree of faithfulness. Our explorations reveal that current metrics struggle to differentiate between advanced explanation methods and Random Attribution, thereby failing to capture the faithfulness property. In contrast, our proposed SaCo offers a reliable faithfulness measurement, establishing a robust metric for interpretations. Furthermore, our SaCo demonstrates that the use of gradient and multilayer aggregation can markedly enhance the faithfulness of attention-based explanation, shedding light on potential paths for advancing Vision Transformer explainability. Copyright © 2024, The Authors. All rights reserved.

关键词： Distribution transformers

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：