检索结果-内蒙古大学图书馆

SSRN 2023年

作者： Lin, Luojun Xie, Han Sun, Zhishu Chen, Weijie Liu, Wenxi Yu, Yuanlong Zhang, Lei College of Computer and Data Science Fuzhou University Fuzhou China College of Computer Science and Technology Zhejiang University Hangzhou China School of Microelectronics and Communication Engineering Chongqing University Chongqing China

Domain Generalization (DG) aims to generalize a model trained on multiple source domains to an unseen target domain. The source domains always require precise annotations, which can be cumbersome or even infeasible to obtain in practice due to the vast amount of data involved. Web data, however, offers an opportunity to access large amounts of unlabeled data with rich style information, which can be leveraged to improve DG. From this perspective, we introduce a novel paradigm of DG, termed as Semi-Supervised Domain Generalization (SSDG), to explore how the labeled and unlabeled source domains can interact, and establish two settings, including the close-set and open-set SSDG. The close-set SSDG is based on existing public DG datasets, while the open-set SSDG, built on the newly-collected web-crawled datasets, presents a novel yet realistic challenge that pushes the limits of current technologies. A natural approach of SSDG is to transfer knowledge from labeled data to unlabeled data via pseudo labeling, and train the model on both labeled and pseudo-labeled data for generalization. Since there are conflicting goals between domain-oriented pseudo labeling and out-of-domain generalization, we develop a pseudo labeling phase and a generalization phase independently for SSDG. Unfortunately, due to the large domain gap, the pseudo labels provided in the pseudo labeling phase inevitably contain noise, which has negative affect on the subsequent generalization phase. Therefore, to improve the quality of pseudo labels and further enhance generalizability, we propose a cyclic learning framework to encourage a positive feedback between these two phases, utilizing an evolving intermediate domain that bridges the labeled and unlabeled domains in a curriculum learning manner. Extensive experiments are conducted to validate the effectiveness of our method. It is worth highlighting that web-crawled data can promote domain generalization as demonstrated by the experimental results.

关键词： Web crawler

来源：评论

学校读者我要写书评

暂无评论

Early Neuron Alignment in Two-layer ReLU Networks with Small Initialization

arXiv

引用

arXiv 2023年

作者： Min, Hancheng Mallada, Enrique Vidal, René Center for Innovation in Data Engineering and Science University of Pennsylvania United States Electrical and Computer Engineering Johns Hopkins University United States

This paper studies the problem of training a two-layer ReLU network for binary classification using gradient flow with small initialization. We consider a training dataset with well-separated input vectors: Any pair of input data with the same label are positively correlated, and any pair with different labels are negatively correlated. Our analysis shows that, during the early phase of training, neurons in the first layer try to align with either the positive data or the negative data, depending on its corresponding weight on the second layer. A careful analysis of the neurons’ directional dynamics allows us to provide an O(log √µn ) upper bound on the time it takes for all neurons to achieve good alignment with the input data, where n is the number of data points and µ measures how well the data are separated. After the early alignment phase, the loss converges to zero at a O(1t ) rate, and the weight matrix on the first layer is approximately low-rank. Numerical experiments on the MNIST dataset illustrate our theoretical findings. Copyright © 2023, The Authors. All rights reserved.

关键词： Neurons

来源：评论

学校读者我要写书评

暂无评论

Transfer Function Based Feature Selection Using Harris Hawk Optimization for Biomedical Applications

Transfer Function Based Feature Selection Using Harris Hawk ...

引用

Smart Electronics and Communication Systems (ISENSE), International Conference on

作者： S. Jayachitra A. Prasanth Prasannakiruba G S Srichandana Abbineni Department of Electronics and Communication Engineering PSNA College of Engineering and Technology Tamilnadu India Department of Computer Science and Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai Tamilnadu India Department of Computer Technology Bannari Amman Institute of Technology Sathyamangalam Department of ET-CSE(Data Science) CVR College of Engineering Hyderabad

ISBN: (数字)9798331528126

ISBN: (纸本)9798331528133

Feature Selection plays key role to truncate the high dimensionality in the datasets through eradicating the unwanted and noisy attributes to improve the performance of classification. The Meta-heuristic technique is one of the most optimistic search techniques to travel the feature space to locate finest feature subset. The Harris Hawk Optimization (HHO) excited from hunting approach of hawk in nature. The cost effectiveness and simplicity formulates the algorithm prominent and superior in solving optimization problems. The binary version of the optimization is accountable for delineating continuous searching space to discrete feature space. Here, 6 transfer functions with S-Shaped and V-Shaped families were interposed and analyzed. Twelve benchmark datasets from UCI repository has been introduced to examine the transfer functions and choose the best feature pertaining to mitigate local minima and high speed of convergence. To analyze the efficacy of transfer function, the proposed method was compared over exiting algorithms and the proposed results attain higher classification accuracy in many of the datasets.

关键词： Costs Communication systems Metaheuristics Transfer functions Benchmark testing Feature extraction Space exploration Classification algorithms Noise measurement Convergence

来源：评论

学校读者我要写书评

暂无评论

Semi-Supervised Domain Generalization with Evolving Intermediate Domain

SSRN

引用

SSRN 2023年

关键词： Web crawler

来源：评论

学校读者我要写书评

暂无评论

An Uncertainty-Aware Deep Learning-Based Model for COVID-19 Diagnosis

An Uncertainty-Aware Deep Learning-Based Model for COVID-19 ...

引用

Mobile Networks and Wireless Communications (ICMNWC), IEEE International Conference on

作者： L Chandra Sekhar Reddy R Jayakarthik Ajmeera Kiran Nipun Sharma Swati Sharma Pundru Chandra Shaker Reddy Department of CSE(Data Science) CMR College of Engineering & Technology Hyderabad India Department of Computer Science Saveetha College of Liberal Arts and Sciences Chennai Tamil Nadu India Computer Science and Engineering MLR Institute of Technology Dundigal Hyderabad Telangana India Electronics and Communication Engineering Presidency University Bangalore Karnataka India School of Computer Science Engineering and Information Science Presidency University Bangalore Karnataka India

The application of deep-learning(DL) to the processing of medical images has been highly successful. A few groundbreaking DL-based works have achieved substantial progress in computerized screening of COVID-19 using chest X-ray( CXR) pictures in the wake of the current epidemic scenario caused by SARS-CoV-2. While DL models have shown promise, they currently lack a crucial component for use in medical image analysis: the ability to communicate uncertainty in the strategies prediction. Therefore, in this paper, we create a design for automatically detecting COVID19 from CXR images using an uncertainty-aware convolutional-neural-network(UACNN) and estimate the uncertainty in its predictions. In the suggested method, an EfficientNetB3 model is tuned using CXR pictures, and then the model is used in conjunction with Monte Carlo (MC) dropout. The posterior predictive distribution has been obtained after M forward passes of inference using MC dropout. The anticipation and design uncertainty are then determined by calculating the mean and entropy of the generated anticipative distribution. The COVID19CXr, XR-pictures, and Kaggle CXR datasets are used to test the suggested approach. Multi-class classification on the COVID19CXr dataset was completed with an accuracy of 99.81% using the proposed UACNN approach. For the purpose of diagnosing COVID-19 cases from CXR pictures, our suggested methodology demonstrates its superiority over the existing methodologies.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Reliability-Adaptive Consistency Regularization for Weakly-Supervised Point Cloud Segmentation

arXiv

引用

arXiv 2023年

作者： Wu, Zhonghua Wu, Yicheng Lin, Guosheng Cai, Jianfei School of Computer Science and Engineering Nanyang Technological University Singapore639798 Singapore Department of Data Science and AI Monash University MelbourneVIC3800 Australia

Weakly-supervised point cloud segmentation with extremely limited labels is highly desirable to alleviate the expensive costs of collecting densely annotated 3D points. This paper explores applying the consistency regularization that is commonly used in weakly-supervised learning, for its point cloud counterpart with multiple data-specific augmentations, which has not been well studied. We observe that the straightforward way of applying consistency constraints to weakly-supervised point cloud segmentation has two major limitations: noisy pseudo labels due to the conventional confidence-based selection and insufficient consistency constraints due to discarding unreliable pseudo labels. Therefore, we propose a novel Reliability-Adaptive Consistency Network (RAC-Net) to use both prediction confidence and model uncertainty to measure the reliability of pseudo labels and apply consistency training on all unlabeled points while with different consistency constraints for different points based on the reliability of corresponding pseudo labels. Experimental results on the S3DIS and ScanNet-v2 benchmark datasets show that our model achieves superior performance in weakly-supervised point cloud segmentation. The code will be released publicly at https://***/wu-zhonghua/RAC-Net. Copyright © 2023, The Authors. All rights reserved.

关键词： Reliability

来源：评论

学校读者我要写书评

暂无评论

Adaptive data-Free Quantization

Adaptive Data-Free Quantization

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Biao Qian Yang Wang Richang Hong Meng Wang Key Laboratory of Knowledge Engineering with Big Data Ministry of Education School of Computer Science and Information Engineering Hefei University of Technology China

data-free quantization (DFQ) recovers the performance of quantized network (Q) without the original data, but generates the fake sample via a generator (G) by learning from full-precision network (P), which, however, is totally independent of Q, overlooking the adaptability of the knowledge from generated samples, i.e., informative or not to the learning process of Q, resulting into the overflow of generalization error. Building on this, several critical questions — how to measure the sample adaptability to Q under varied bit-width scenarios? whether the largest adaptability is the best? how to generate the samples with adaptive adaptability to improve Q's generalization? To answer the above questions, in this paper, we propose an Adaptive data-Free Quantization (AdaDFQ) method, which revisits DFQ from a zero-sum game perspective upon the sample adaptability between two players — a generator and a quantized network. Following this viewpoint, we further define the disagreement and agreement samples to form two boundaries, where the margin between two boundaries is optimized to adaptively regulate the adaptability of generated samples to Q, so as to address the over-and-under fitting issues. Our AdaDFQ reveals: 1) the largest adaptability is NOT the best for sample generation to benefit Q's generalization; 2) the knowledge of the generated sample should not be informative to Q only, but also related to the category and distribution information of the training data for P. The theoretical and empirical analysis validate the advantages of AdaDFQ over the state-of-the-arts. Our code is available at https://***/hfutqian/AdaDFQ.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Generative Semantic Communication for Joint Image Transmission and Segmentation

arXiv

引用

arXiv 2024年

作者： Yuan, Weiwen Ren, Jinke Wang, Chongjie Zhang, Ruichen Wei, Jun Kim, Dong In Cui, Shuguang FNii-Shenzhen China SSE United Kingdom Shenzhen China College of Computing and Data Science Nanyang Technological University Singapore College of Computer Science and Software Engineering Shenzhen University Shenzhen China Department of Electrical and Computer Engineering Sungkyunkwan University Suwon Korea Republic of

Semantic communication has emerged as a promising technology for enhancing communication efficiency. However, most existing research emphasizes single-task reconstruction, neglecting model adaptability and generalization across multi-task systems. In this paper, we propose a novel generative semantic communication system that supports both image reconstruction and segmentation tasks. Our approach builds upon semantic knowledge bases (KBs) at both the transmitter and receiver, with each semantic KB comprising a source KB and a task KB. The source KB at the transmitter leverages a hierarchical Swin-Transformer, a generative AI scheme, to extract multi-level features from the input image. Concurrently, the counterpart source KB at the receiver utilizes hierarchical residual blocks to generate task-specific knowledge. Furthermore, the two task KBs adopt a semantic similarity model to map different task requirements into pre-defined task instructions, thereby facilitating the feature selection of the source KBs. Additionally, we develop a unified residual block-based joint source and channel (JSCC) encoder and two task-specific JSCC decoders to achieve the two image tasks. In particular, a generative diffusion model is adopted to construct the JSCC decoder for the image reconstruction task. Experimental results demonstrate that our multi-task generative semantic communication system outperforms previous single-task communication systems in terms of peak signal-to-noise ratio and segmentation accuracy. Copyright © 2024, The Authors. All rights reserved.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

A Joint Gradient and Loss Based Clustered Federated Learning Design

A Joint Gradient and Loss Based Clustered Federated Learning...

引用

IEEE Conference on Global Communications (GLOBECOM)

作者： Licheng Lin Zhaohui Yang Yusen Wu Yuchen Liu Mingzhe Chen Department of Electrical and Computer Engineering University of Miami Coral Gables FL USA College of Information Science and Electronic Engineering Zhejiang University Hangzhou China Frost Institute for Data Science and Computing University of Miami Coral Gables FL USA Department of Computer Science North Carolina State University Raleigh NC USA

ISBN: (数字)9798350351255

ISBN: (纸本)9798350351262

In this paper, a novel clustered FL framework that enables distributed edge devices with non-IID data to independently form several clusters in a distributed manner and implement FL training within each cluster is proposed. In particular, our designed clustered FL algorithm must overcome two challenges associated with FL training. First, the server has limited FL training information (i.e., the parameter server can only obtain the FL model information of each device) and limited computational power for finding the differences among a large amount of devices. Second, each device does not have the data information of other devices for device clustering and can only use global FL model parameters received from the server and its data information to determine its cluster identity, which will increase the difficulty of device clustering. To overcome these two challenges, we propose a joint gradient and loss based distributed clustering method in which each device determines its cluster identity considering the gradient similarity and training loss. The proposed clustering method not only considers how a local FL model of one device contributes to each cluster but also the direction of gradient descent thus improving clustering speed. By delegating clustering decisions to edge devices, each device can fully leverage its private data information to determine its own cluster identity, thereby reducing clustering overhead and improving overall clustering performance. Simulation results demonstrate that our proposed clustered FL algorithm can reduce clustering iterations by up to 99% compared to the existing baseline.

关键词： Training Performance evaluation Federated learning Clustering methods Computational modeling Simulation Clustering algorithms Distributed databases data models Servers

来源：评论

学校读者我要写书评

暂无评论

Enhanced Multi-Objective Optimization Approach for Low-Interference UAV Communication Based on Collaborative Beamforming

Enhanced Multi-Objective Optimization Approach for Low-Inter...

引用

Smart World Congress (SWC), IEEE

作者： Chao Zhang Hui Kang Geng Sun Jiahui Li Boxiong Wang Bo Xu College of Computer Science and Technology Jilin University Changchun China College of Computing and Data Science Nanyang Technological University Singapore Singapore College of Information and Communication Engineering Hainan University Haikou China

ISBN: (数字)9798331520861

ISBN: (纸本)9798331520878

Unmanned aerial vehicles (UAVs) are widely used in the field of wireless communications due to their inherent advantages such as easy deployment and low cost. Employing collaborative beamforming techniques to form a UAV-based virtual antenna array (UVAA) is a promising solution to achieve remote and low-cost communications. Owing to the nature of electromagnetic waves, UVAA may cause interference to unaffiliated users when deployed in densely populated areas. To address this issue, UAVs must identify the most suitable positions to achieve optimal beam patterns. However, considering their limited energy capacity and the increased power consumption associated with excessive flight, a multi-objective optimization analysis is necessary to balance these factors. Thus, we formulate a low-interference communication multi-objective problem (LIMOP), aiming to maximize transmission rate, minimize interference, and reduce energy consumption through the optimization of UAV positions, excitation currents, and the selection of target BS. Given the complexity of LIMOP, we introduce multiple improvement strategies to propose an improved swarm intelligence method. According to simulation results, the proposed IMOAHA is effective in addressing the formulated LIMOP and is superior to other algorithms.

关键词： Wireless communication Energy consumption Power demand Array signal processing Simulation Collaboration Interference Autonomous aerial vehicles Optimization Antenna arrays

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：