检索结果-内蒙古大学图书馆

DomainAdaptor: A Novel Approach to Test-time Adaptation

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhang, Jian Qi, Lei Shi, Yinghuan Gao, Yang State Key Laboratory for Novel Software Technology Nanjing University China National Institute of Healthcare Data Science Nanjing University China School of Computer Science and Engineering Southeast University China

To deal with the domain shift between training and test samples, current methods have primarily focused on learning generalizable features during training and ignore the specificity of unseen samples that are also critical during the test. In this paper, we investigate a more challenging task that aims to adapt a trained CNN model to unseen domains during the test. To maximumly mine the information in the test data, we propose a unified method called DomainAdaptor for the test-time adaptation, which consists of an AdaMixBN module and a Generalized Entropy Minimization (GEM) loss. Specifically, AdaMixBN addresses the domain shift by adaptively fusing training and test statistics in the normalization layer via a dynamic mixture coefficient and a statistic transformation operation. To further enhance the adaptation ability of AdaMixBN, we design a GEM loss that extends the Entropy Minimization loss to better exploit the information in the test data. Extensive experiments show that DomainAdaptor consistently outperforms the state-of-the-art methods on four benchmarks. Furthermore, our method brings more remarkable improvement against existing methods on the few-data unseen domain. The code is available at https://***/koncle/DomainAdaptor. Copyright © 2023, The Authors. All rights reserved.

关键词： Entropy

An Efficient Medium Access Control Mechanism for Flying Ad-hoc Networks

学校读者我要写书评

暂无评论

computer systems science & engineering 2021年第7期38卷 47-63页

作者： Muhammad Asghar Khan Fazal Noor Insaf Ullah Sajjad ur Rehman Shibli Nisar Mohaira Ahmad Department of Electronic Engineering ISRA UniversityIslamabad44000Pakistan Department of Computer Science and Information Systems Islamic University of MadinahMadinah400411Saudi Arabia Hamdard Institute of Engineering&Technology Islamabad44000Pakistan Department of Electrical Engineering Namal InstituteMianwali42200Pakistan Department of Electrical Engineering National University of Sciences and Technology(NUST)Islamabad44000Pakistan

The Flying Ad-hoc Networks(FANETs)is characterized by the transition from a single large Unmanned Aerial Vehicle(UAV)to multiple small UAVs connected in an ad-hoc *** high mobility is the core feature of such networks,they are prone to route breaks within the *** issue of connectivity loss can be coped with,to some extent,by making use of omnidirectional *** modification,however,curtails Quality-of-Service(QoS)requirements of networks in terms of bandwidth,media access delay,coverage and ***,directional antennas have advantages over omnidirectional antennas such as improved transmission range,spatial reuse and high ***,its introduction raises location-dependent issues to the Medium Access Control(MAC)*** calls for an efficient MAC protocol that can cater to new directional antenna models and,at the same time,can counter the constraints associated with the dynamic ***,in this article,we consider a UAV interconnection mechanism that lets the UAVs execute the communication tasks using the directional MAC *** technique is advantageous as compared to the approach of utilizing the MAC protocol using omnidirectional *** scheme is being implemented as a case study for Industry 4.0 inventory and traceability applications in the *** modeling and simulation purposes,we use the Optimized Network engineering Tool(OPNET)and aim to seek an evaluation with respect to throughput,media access delay,retransmission attempts and data *** results obtained demonstrate the effectiveness of the proposed scheme.

关键词： FANETs QoS Industry 4.0 IEEE 802.11 MAC OPNET mobility models directional antenna

Which One is Better? Self-supervised Temporal Coherence Learning for Skeleton Based Action Recognition

学校读者我要写书评

暂无评论

Which One is Better? Self-supervised Temporal Coherence Lear...

IEEE International Joint Conference on Biometrics (IJCB)

作者： Bizhu Wu Mingyan Wu Haoqin Ji Linlin Shen Computer Vision Institute College of Computer Science and Software Engineering Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University China

ISBN: (纸本)9781665463959

Recently, researchers have achieved significant results in the skeleton based action recognition task. To better model the skeleton sequences, existing methods learned the feature representations in the self-supervised setting by solving pretext tasks, such as predicting the order of a shuffled skeleton sequence or verifying whether a given skeleton sequence is shuffled or not. However, these pretext tasks are either too challenging or too easy for the encoder to obtain a proper skeleton representation for action recognition. Therefore, we propose a novel self-pretraining pretext task, Which One Is Better (WOIB), to identify which one is more temporally coherent, given two shuffled skeleton sequences. Experiments on the NTU RGB+D, NTU RGB+D 120, and Kinetics-Skeleton datasets with different network architectures show significant improvements in recognition accuracy, demonstrating that such a well-designed pretext task is general and able to drive the encoder to learn more discriminative representations.

关键词： Biometrics (access control) Coherence Predictive models Network architecture Drives Benchmark testing Skeleton

Online Covariance Matrix Estimation in Sketched Newton Methods

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Kuang, Wei Anitescu, Mihai Na, Sen Department of Statistics The University of Chicago United States Mathematics and Computer Science Division Argonne National Laboratory United States School of Industrial and Systems Engineering Georgia Institute of Technology United States

Given the ubiquity of streaming data, online algorithms have been widely used for parameter estimation, with second-order methods particularly standing out for their efficiency and robustness. In this paper, we study an online sketched Newton method that leverages a randomized sketching technique to perform an approximate Newton step in each iteration, thereby eliminating the computational bottleneck of second-order methods. While existing studies have established the asymptotic normality of sketched Newton methods, a consistent estimator of the limiting covariance matrix remains an open problem. We propose a fully online covariance matrix estimator that is constructed entirely from the Newton iterates and requires no matrix factorization. Compared to covariance estimators for first-order online methods, our estimator for second-order methods is batch-free. We establish the consistency and convergence rate of our estimator, and coupled with asymptotic normality results, we can then perform online statistical inference for the model parameters based on sketched Newton methods. We also discuss the extension of our estimator to constrained problems, and demonstrate its superior performance on regression problems as well as benchmark problems in the CUTEst set. © 2025, CC BY.

关键词： Newton-Raphson method

Model predictive control for tracking using artificial references: Fundamentals, recent results and practical implementation

学校读者我要写书评

暂无评论

Model predictive control for tracking using artificial refer...

IEEE Conference on Decision and Control

作者： P. Krupa J. Köhler A. Ferramosca I. Alvarado M.N. Zeilinger T. Alamo D. Limon Computer Science Group Gran Sasso Science Institute (GSSI) L’Aquila Italy ETH Zürich Institute for Dynamic Systems and Control Zürich Switzerland Department of Management Information and Production Engineering University of Bergamo Via Marconi 5 Dalmine (BG) Italy Department of Systems Engineering and Automation Universidad de Sevilla Seville Spain

ISBN: (数字)9798350316339

ISBN: (纸本)9798350316346

This paper provides a comprehensive tutorial on a family of Model Predictive Control (MPC) formulations, known as MPC for tracking, which are characterized by including an artificial reference as part of the decision variables in the optimization problem. These formulations have several benefits with respect to the classical MPC formulations, including guaranteed recursive feasibility under online reference changes, as well as asymptotic stability and an increased domain of attraction. This tutorial paper introduces the concept of using an artificial reference in MPC, presenting the benefits and theoretical guarantees obtained by its use. We then provide a survey of the main advances and extensions of the original linear MPC for tracking, including its non-linear extension. Additionally, we discuss its application to learning-based MPC, and discuss optimization aspects related to its implementation.

关键词： Surveys Asymptotic stability Costs Tutorials Optimization Predictive control

Solving the Quadratic Assignment Problem using Deep Reinforcement Learning

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Bagga, Puneet S. Delarue, Arthur School of Computer Science Georgia Institute of Technology United States H. Milton Stewart School of Industrial and Systems Engineering Georgia Institute of Technology United States

The Quadratic Assignment Problem (QAP) is an NP-hard problem which has proven particularly challenging to solve: unlike other combinatorial problems like the traveling salesman problem (TSP), which can be solved to optimality for instances with hundreds or even thousands of locations using advanced integer programming techniques, no methods are known to exactly solve QAP instances of size greater than 30. Solving the QAP is nevertheless important because of its many critical applications, such as electronic wiring design and facility layout selection. We propose a method to solve the original Koopmans-Beckman formulation of the QAP using deep reinforcement learning. Our approach relies on a novel double pointer network, which alternates between selecting a location in which to place the next facility and a facility to place in the previous location. We train our model using A2C on a large dataset of synthetic instances, producing solutions with no instance-specific retraining necessary. Out of sample, our solutions are on average within 7.5% of a high-quality local search baseline, and even outperform it on 1.2% of instances. Copyright © 2023, The Authors. All rights reserved.

关键词： Location

Accelerating Fingerprint-based Person Identification through Computation Offloading in Edge and Cloud Environments

学校读者我要写书评

暂无评论

Accelerating Fingerprint-based Person Identification through...

IEEE International Conference on Cloud Networking (CLOUDNET)

作者： Renan A. Barbosa João P. B. Andrade Mauro R. C. Da Silva Fernando A. M. Trinta Paulo A. L. Rego Group of Computer Networks Software Engineering and Systems (GREat) Federal University of Ceará (UFC) Fortaleza Ceará Brazil Institute of Computing University of Campinas (Unicamp) São Paulo Brazil

The increasing popularity of smartphones has driven the development of advanced features, including access to users’ biometric data and a wide range of services via wireless connections. This provides developers with opportunities to create increasingly complex applications. However, the limited resources on mobile devices pose challenges when executing operations such as fingerprint-based person identification, especially with large datasets. Given these limitations, we propose and evaluate a software architecture to enable fingerprint identification on mobile devices. Our approach leverages computation offloading techniques to migrate application components to cloud and edge/cloudlet servers. Through our evaluation, we have observed that offloading the task to cloudlet or cloud servers significantly accelerates the identification process, even when multiple devices simultaneously offload to the remote environment. These findings highlight the potential benefits of leveraging offloading to enhance the performance of fingerprint identification on mobile devices.

关键词：

SCARF: Scalable Continual Learning Framework for Memory-efficient Multiple Neural Radiance Fields

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wang, Yuze Wang, Junyi Wang, Chen Duan, Wantong Bao, Yongtang Qi, Yue State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University China School of Computer Science and Technology Shandong University China School of Computer and Artificial Intelligence Beijing Technology and Business University China Jingdezhen Research Institute Beihang University China Shandong University of Science and Technology China

This paper introduces a novel continual learning framework for synthesising novel views of multiple scenes, learning multiple 3D scenes incrementally, and updating the network parameters only with the training data of the upcoming new scene. We build on Neural Radiance Fields (NeRF), which uses multi-layer perceptron to model the density and radiance field of a scene as the implicit function. While NeRF and its extensions have shown a powerful capability of rendering photo-realistic novel views in a single 3D scene, managing these growing 3D NeRF assets efficiently is a new scientific problem. Very few works focus on the efficient representation or continuous learning capability of multiple scenes, which is crucial for the practical applications of NeRF. To achieve these goals, our key idea is to represent multiple scenes as the linear combination of a cross-scene weight matrix and a set of scene-specific weight matrices generated from a global parameter generator. Furthermore, we propose an uncertain surface knowledge distillation strategy to transfer the radiance field knowledge of previous scenes to the new model. Representing multiple 3D scenes with such weight matrices significantly reduces memory requirements. At the same time, the uncertain surface distillation strategy greatly overcomes the catastrophic forgetting problem and maintains the photo-realistic rendering quality of previous scenes. Experiments show that the proposed approach achieves state-of-the-art rendering quality of continual learning NeRF on NeRF-Synthetic, LLFF, and TanksAndTemples datasets while preserving extra low storage cost. Copyright © 2024, The Authors. All rights reserved.

关键词： Rendering (computer graphics)

FedAccess: Federated Learning-Based Built Surface Recognition for Wheelchair Routing

学校读者我要写书评

暂无评论

FedAccess: Federated Learning-Based Built Surface Recognitio...

IEEE Annual International computer software and Applications Conference (COMPSAC)

作者： Rochishnu Banerjee Ethan Han Longze Li Haoxiang Yu Md Osman Gani Vaskar Raychoudhury Roger O. Smith Department of Computer Science & Software Engineering Miami University Oxford OH USA Department of Electrical and Computer Engineering University of Texas Austin Austin TX USA Department of Information Systems University of Maryland Baltimore County Baltimore MD USA Department of Rehabilitation Sciences & Technology University of Wisconsin Milwaukee WI USA

ISBN: (数字)9798350376968

ISBN: (纸本)9798350376975

Wheelchair and mobility aid users often face challenges in navigating the built environment due to uneven sidewalks, temporary barriers, steep inclines, and narrow lanes. To assist these users, accessible routing systems have been introduced that generate wheelchair-accessible paths to facilitate navigation in unfamiliar environments. In general, accessible routing systems rely on surface and path characteristics like surface type, incline, width, etc., and crowd-sourced information about barriers to provide the optimal route. Emerging routing systems even provide personalized routing to users that are catered to the user's specific needs and requirements. However, these types of systems collect crowd-sourced personal/identifiable information which introduces privacy and data heterogeneity concerns that are not addressed by them or elsewhere in the concerned domain. To address these two issues specifically, we propose the novel FedAccess system for accessible routing that utilizes the federated learning paradigm for surface recognition using vibration data. The surface-induced vibrations are captured through smartphone-embedded motion sensors (accelerometers and gyroscopes) from 23 manual wheelchair users during their regular navigation. We have covered 10 distinct surfaces from the USA. As a result, the distribution of the data is naturally non-IID. Empirical evaluation shows that the FedAccess system can protect user data and identity while dealing with non-IID data and still recognize heterogeneous surfaces with higher accuracy than the state-of-the-art.

关键词： Vibrations Navigation Federated learning Wheelchairs Face recognition Manuals Routing