检索结果-内蒙古大学图书馆

Moment Centralization-Based Gradient Descent Optimizers for Convolutional Neural Networks 1

International Conference on computer Vision and Machine Intelligence, CVMI 2022

作者： Sadu, Sumanth Dubey, Shiv Ram Sreeja, S.R. Computer Vision Group Department of Computer Science and Engineering Indian Institute of Information Technology Andhra Pradesh Sri City India Computer Vision and Biometrics Laboratory Indian Institute of Information Technology Uttar Pradesh Allahabad India Department of Computer Science and Engineering Indian Institute of Information Technology Andhra Pradesh Sri City India

ISBN: (数字)9789811978678

ISBN: (纸本)9789811978661

Convolutional neural networks (CNNs) have shown very appealing performance for many computer vision applications. The training of CNNs is generally performed using stochastic gradient descent (SGD)-based optimization techniques. The adaptive momentum-based SGD optimizers are the recent trends. However, the existing optimizers are not able to maintain a zero mean in the first order moment and struggle with optimization. In this paper, we propose a moment centralization-based SGD optimizer for CNNs. Specifically, we impose the zero mean constraints on the first order moment explicitly. The proposed moment centralization is generic in nature and can be integrated with any of the existing adaptive momentum-based optimizers. The proposed idea is tested with three state-of-the-art optimization techniques, including Adam, Radam, and Adabelief on benchmark CIFAR10, CIFAR100, and TinyImageNet datasets for image classification. The performance of the existing optimizers is generally improved when integrated with the proposed moment centralization. Further, the results of the proposed moment centralization are also better than the existing gradient centralization. The analytical analysis using the toy example shows that the proposed method leads to a shorter and smoother optimization trajectory. The source code is made publicly available at https://***/sumanthsadhu/MC-optimizer. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

Explainable Facial Expression Recognition for People with Intellectual Disabilities

arXiv

引用

arXiv 2024年

作者： Guarinos, Silvia Ramis Yee, Cristina Manresa Buades-Rubio, Jose Maria Gaya-Morey, Francesc Xavier Group of Computer Graphics Computer Vision and IA Maths Computer Science Department Universitat de les Illes Balears Palma Illes Balears Spain

Facial expression recognition plays an important role in human behaviour, communication, and interaction. Recent neural networks have demonstrated to perform well at its automatic recognition, with different explainability techniques available to make them more transparent. In this work, we propose a facial expression recognition study for people with intellectual disabilities that would be integrated into a social robot. We train two well-known neural networks with five databases of facial expressions and test them with two databases containing people with and without intellectual disabilities. Finally, we study in which regions the models focus to perceive a particular expression using two different explainability techniques: LIME and RISE, assessing the differences when used on images containing disabled and non-disabled people. Copyright © 2024, The Authors. All rights reserved.

关键词： Human computer interaction

来源：评论

学校读者我要写书评

暂无评论

Segmentation of CAD models using hybrid representation

引用

虚拟现实与智能硬件(中英文) 2025年第2期7卷 188-202页

作者： Claude UWIMANA Shengdi ZHOU Limei YANG Zhuqing LI Norbelt MUTAGISHA Edouard NIYONGABO Bin ZHOU State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and EngineeringBeihang UniversityBeijing 100191China Peace-Bay Academy of Virtual Reality Shenyang 110004China China Aerospace Systems Engineering Corporation Beijing 100070China Department of Signal and Information Processing Beihang UniversityBeijing 100191China Department of Computer Science University of SherbrookeSherbrooke J1C0A1Canada

In this paper,we introduce an innovative method for computer-aided design(CAD)segmentation by concatenating meshes and CAD *** previous CAD segmentation methods have achieved impressive performance using single representations,such as meshes,CAD,and point ***,existing methods cannot effectively combine different three-dimensional model types for the direct conversion,alignment,and integrity maintenance of geometric and topological ***,we propose an integration approach that combines the geometric accuracy of CAD data with the flexibility of mesh representations,as well as introduce a unique hybrid representation that combines CAD and mesh models to enhance segmentation *** combine these two model types,our hybrid system utilizes advanced-neural-network techniques to convert CAD models into mesh *** complex CAD models,model segmentation is crucial for model retrieval and *** partial retrieval,it aims to segment a complex CAD model into several simple *** first component of our hybrid system involves advanced mesh-labeling algorithms that harness the digitization of CAD properties to mesh *** second component integrates labelled face features for CAD segmentation by leveraging the abundant multisemantic information embedded in CAD *** combination of mesh and CAD not only refines the accuracy of boundary delineation but also provides a comprehensive understanding of the underlying object *** study uses the Fusion 360 Gallery *** results indicate that our hybrid method can segment these models with higher accuracy than other methods that use single representations.

关键词： B-RepNet hybrid segmentation CAD models classification MeshCNN MeshCAD-Net

来源：评论

学校读者我要写书评

暂无评论

Cubature Kalman Fusion Filtering Under Amplify-and-Forward Relays With Randomly Varying Channel Parameters

引用

IEEE/CAA Journal of Automatica Sinica 2025年第2期12卷 356-368页

作者： Jiaxing Li Zidong Wang Jun Hu Hongli Dong Hongjian Liu the Department of Applied Mathematics Harbin University of Science and Technology IEEE the Department of Computer Science Brunel University London the School of Automation Harbin University of Science and Technology the Artificial Intelligence Energy Research Institute Northeast Petroleum University the Heilongjiang Provincial Key Laboratory of Networking and Intelligent Control Northeast Petroleum University the National Key Laboratory of Continental Shale Oil of China Northeast Petroleum University the Key Laboratory of Advanced Perception and Intelligent Control of High-End Equipment Ministry of Education Anhui Polytechnic University the School of Mathematics and Physics Anhui Polytechnic University

In this paper, the problem of cubature Kalman fusion filtering(CKFF) is addressed for multi-sensor systems under amplify-and-forward(AaF) relays. For the purpose of facilitating data transmission, AaF relays are utilized to regulate signal communication between sensors and filters. Here, the randomly varying channel parameters are represented by a set of stochastic variables whose occurring probabilities are permitted to exhibit bounded uncertainty. Employing the spherical-radial cubature principle, a local filter under AaF relays is initially constructed. This construction ensures and minimizes an upper bound of the filtering error covariance by designing an appropriate filter gain. Subsequently, the local filters are fused through the application of the covariance intersection fusion rule. Furthermore, the uniform boundedness of the filtering error covariance's upper bound is investigated through establishing certain sufficient conditions. The effectiveness of the proposed CKFF scheme is ultimately validated via a simulation experiment concentrating on a three-phase induction machine.

关键词： Amplify-and-forward (AaF) relays covariance intersection fusion cubature Kalman filtering multi-sensor systems uniform boundedness

来源：评论

学校读者我要写书评

暂无评论

Observations of data characteristics and irregularities through domain-oriented transformations of attributes

引用

Procedia computer science 2024年 246卷 2694-2703页

作者： Urszula Stańczyk Grzegorz Baron Department of Computer Graphics Vision and Digital Systems Faculty of Automatic Control Electronics and Computer Science Silesian University of Technology Akademicka 2A 44-100 Gliwice Poland

The paper presents research dedicated to observations of relations between attribute properties and discretisation. In the investigations described, the gradually increasing sets of features were discretised by selected approaches, and several variants of data were constructed. The continuous, partially discrete, and completely translated datasets were explored by the chosen classifiers and their performance studied in the context of a number of discretised attributes, discretisation procedures, and the way of processing of features and datasets. The stylometric problem of authorship attribution was the machine learning task under study. The experimental results enable to observe closer the specificity of style-markers employed as characteristic features, and indicate conditions for efficient recognition of authorship. They can be extended to other application domains with similar characteristics.

关键词： Attribute domain Discretisation Data representation Data irregularities Pattern recognition Stylometry Authorship attribution

来源：评论

学校读者我要写书评

暂无评论

Earning Extra Performance From Restrictive Feedbacks

引用

IEEE Transactions on Pattern Analysis and Machine Intelligence 2023年第10期45卷 11753-11765页

作者： Li, Jing Pan, Yuangang Lyu, Yueming Yao, Yinghua Sui, Yulei Tsang, Ivor W. 138632 Singapore University of Technology Sydney The Australian Artificial Intelligence Institute UltimoNSW2007 Australia Southern University of Science and Technology The Guangdong Key Laboratory of Brain-inspired Intelligent Computation Department of Computer Science and Engineering Shenzhen518055 China University of New South Wales The School of Computer Science and Engineering Sydney1466 Australia

Many machine learning applications encounter situations where model providers are required to further refine the previously trained model so as to gratify the specific need of local users. This problem is reduced to the standard model tuning paradigm if the target data is permissibly fed to the model. However, it is rather difficult in a wide range of practical cases where target data is not shared with model providers but commonly some evaluations about the model are accessible. In this paper, we formally set up a challenge named Earning eXtra PerformancE from restriCTive feEDdbacks (EXPECTED) to describe this form of model tuning problems. Concretely, EXPECTED admits a model provider to access the operational performance of the candidate model multiple times via feedback from a local user (or a group of users). The goal of the model provider is to eventually deliver a satisfactory model to the local user(s) by utilizing the feedbacks. Unlike existing model tuning methods where the target data is always ready for calculating model gradients, the model providers in EXPECTED only see some feedbacks which could be as simple as scalars, such as inference accuracy or usage rate. To enable tuning in this restrictive circumstance, we propose to characterize the geometry of the model performance with regard to model parameters through exploring the parameters' distribution. In particular, for deep models whose parameters distribute across multiple layers, a more query-efficient algorithm is further tailor-designed that conducts layerwise tuning with more attention to those layers which pay off better. Our theoretical analyses justify the proposed algorithms from the aspects of both efficacy and efficiency. Extensive experiments on different applications demonstrate that our work forges a sound solution to the EXPECTED problem, which establishes the foundation for future studies towards this direction. © 1979-2012 IEEE.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

Pneumonia Detection in X-Ray Chest Images Based on Convolutional Neural Networks and Data Augmentation Methods 11

Pneumonia Detection in X-Ray Chest Images Based on Convoluti...

引用

11th International Conference on Information and Communication Technologies for Ageing Well and e-Health, ICT4AWE 2025

作者： Dardouri, Samia Department of Computer Science College of Computing and Information Technology Shaqra University Saudi Arabia InnoV'COM Laboratory-Sup'Com University of Carthage Tunisia

ISBN: (纸本)9789897587436

Pneumonia, a widespread lung ailment, stands as a leading global cause of mortality, particularly affecting vulnerable demographics such as children under five, the elderly, and individuals with underlying health conditions. Accounting for a significant portion of childhood fatalities, at 18%, pneumonia remains a critical health concern. Despite advancements in imaging diagnostic methods, chest radiographs remain pivotal due to their cost-effectiveness and rapid results. The proposed model, trained on data sourced from a readily available Kaggle database, consists of two primary stages: image preprocessing and feature extraction/image classification. Utilizing a CNN model, the framework achieves remarkable performance metrics, with precision, recall, F1-score, and accuracy reaching 93%, 96%, 94%, and 96%, respectively. These results underscore the CNN model's effectiveness in pneumonia detection, showcasing superior consistency and accuracy compared to other pretrained deep learning models. Copyright © 2025 by SCITEPRESS - science and Technology Publications, Lda.

关键词： Adam Optimizer CNN Deep Learning Early Detection Feature Extraction Image Data Augmentation Pneumonia Infection

来源：评论

学校读者我要写书评

暂无评论

OFDM-structure based waveform designs for integrated sensing and communication

引用

science China(Information sciences) 2025年第5期68卷 267-284页

作者： Jiaqi LIU Ping YANG Ke JIANG Jiarong ZHAO Wei XIANG Jianping WEI Ruixiang DUAN Saviour ZAMMIT Tony Q.S.QUEK National Key Laboratory of Wireless Communications University of Electronic Science and Technology of China School of Computing Engineering and Mathematical Sciences La Trobe University Meituan Academy of Robotics Department of Communications and Computer Engineering University of Malta Information Systems Technology and Design Pillar Singapore University of Technology and Design

The future sixth-generation(6G) paradigm aims to seamlessly integrate communication and environmental sensing capabilities into a single radio signal, promising improved efficiency and cost-effectiveness through simultaneous data communications and environmental perception. At the core of this evolution, orthogonal frequency division multiplexing(OFDM) and its advanced waveforms emerge as pivotal for integrated sensing and communications(ISAC). This study introduces a concise and unified ISAC waveform design framework based on orthogonal multicarriers. This framework supports versatile applications of OFDM and its derivative waveforms within a generalized ISAC system, marking a significant leap in integrating communication and sensing capabilities. A distinguishing feature of this framework is its adaptability,allowing users to intelligently select modulation strategies based on their specific environmental needs. This adaptability optimizes performance across diverse scenarios. Central to our innovations is the proposal of discrete Fourier transformspread OFDM with index modulation(DFT-S-OFDM-IM). This framework is paired with newly proposed signal processing methods for single-input single-output and multiple-input multiple-output(MIMO) systems. Extensive evaluations highlight DFT-S-OFDM-IM's superiority, including dramatically reduced peak-to-average power ratios(PAPRs), competitive communication performance, and exceptional sensing capabilities, striking an elegant balance between communication capacity and environmental sensing precision.

关键词： DFT-S-OFDM-IM index modulation integrated sensing and communication OFDM

来源：评论

学校读者我要写书评

暂无评论

AdaPIP: Adaptive picture-in-picture guidance for 360° film watching

引用

Computational Visual Media 2024年第3期10卷 487-503页

作者： Yi-Xiao Li Guan Luo Yi-Ke Xu Yu He Fang-Lue Zhang Song-Hai Zhang Department of Computer Science and Technology Tsinghua UniversityBeijingChinaand Beijing National Research Center for Information Science and Technology(BNRist)Tsinghua UniversityBeijingChina Key Laboratory of Space Utilization Technology and Engineering Center for Space UtilizationChinese Academy of SciencesBeijingChina Victoria University of Wellington WellingtonNew Zealand

360°videos enable viewers to watch freely from different directions but inevitably prevent them from perceiving all the helpful *** mitigate this problem,picture-in-picture(PIP)guidance was proposed using preview windows to show regions of interest(ROIs)outside the current view *** identify several drawbacks of this representation and propose a new method for 360° film watching called *** enhances traditional PIP by adaptively arranging preview windows with changeable view ranges and *** addition,AdaPIP incorporates the advantage of arrow-based guidance by presenting circular windows with arrows attached to them to help users locate the corresponding ROIs more *** also adapted AdaPIP and Outside-In to HMD-based immersive virtual reality environments to demonstrate the usability of PIP-guided approaches beyond 2D *** user experiments on 2D screens,as well as in VR environments,indicate that AdaPIP is superior to alternative methods in terms of visual experiences while maintaining a comparable degree of immersion.

关键词： 360°videos picture-in-picture(PIP) virtual reality(VR) visual guidance

来源：评论

学校读者我要写书评

暂无评论

Effects of Initialization Methods on the Performance of Multi-Objective Evolutionary Algorithms

Effects of Initialization Methods on the Performance of Mult...

引用

2023 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2023

作者： Gong, Cheng Pang, Lie Meng Nan, Yang Ishibuchi, Hisao Zhang, Qingfu City University of Hong Kong Department of Computer Science Kowloon Tong Hong Kong Southern University of Science and Technology Guangdong Provincial Key Laboratory of Brain-inspired Intelligent Computation Department of Computer Science and Engineering Shenzhen518055 China

ISBN: (纸本)9798350337020

Population initialization is always needed in evolutionary multi-objective optimization (EMO) algorithms. Intuitively, a well-designed initialization method can help facilitate the evolutionary process and improve the performance of EMO algorithms. However, very few studies have investigated the effects of initialization methods on the performance of EMO algorithms. Many existing EMO algorithms randomly generate an initial population to start the evolutionary process. To fill this research gap and attract more attention from EMO researchers to this important yet under-explored issue, in this paper, we examine the effects of various initialization methods that may become promising alternatives to the commonly-used random initialization method. Each initialization method is evaluated through computational experiments on test problems of various sizes with 5-1000 decision variables. Experimental results clearly demonstrate the advantage of well-designed initialization methods over the random initialization method. This study provides useful insights into EMO algorithm design and motivates further research on population initialization. © 2023 IEEE.

关键词：

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：