检索结果-内蒙古大学图书馆

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Pei Zhang Dong Wang Chanyue Wu Jing Yang Lei Kang Zongwen Bai Ying Li Qiang Shen School of Computer Science Northwestern Polytechnical University Xi’an China Shaanxi Key Laboratory of Intelligent Processing for Big Energy Data Yan’an University Yan’an China School of Automation and Software Engineering Shanxi University Taiyuan China Qingdao Topscomm Communication Co. Ltd Qingdao China Department of Computer Science Aberystwyth University UK

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Hyperspectral Image (HSI) cross-scene classification is a challenging task in remote sensing, particularly when real-time processing of Target Domain (TD) HSI is required, and data cannot be reused for training. While deep learning methods have shown promising results, the generalization ability of HSI representations remains limited, mainly due to class label imbalance. This paper introduces a dual-stage learning framework based on transfer learning to enhance classification accuracy in the TD. The framework includes a self-supervised learning stage and a supervised fine-tuning stage. The self-supervised stage focuses on learning robust representations by leveraging inherent structures within HSI data, while the fine-tuning stage uses training labels to extract semantic information. A masked diffusion model predicts masked tokens from unmasked ones, capturing both high-level structures and fine details in HSI data. An efficient spatiospectral Transformer, which removes self-attention from the decoder, is proposed to enhance the self-supervised process. This design allows mask tokens to obtain information from visible tokens without interacting with each other, reducing sequence length and computational costs. By decoding each mask token conditionally independently, only a subset of masked tokens is processed. Extensive experiments on two public HSI datasets demonstrate that the proposed method outperforms state-of-the-art techniques.

关键词： Training Transfer learning Self-supervised learning Transformers Diffusion models Real-time systems Decoding Computational efficiency Speech processing Hyperspectral imaging

来源：评论

学校读者我要写书评

暂无评论

Explaining Model Overfitting in CNNs via GMM Clustering

arXiv

引用

arXiv 2024年

作者： Dou, Hui Mu, Xinyu Yi, Mengjun Han, Feng Zhao, Jian Shen, Furao State Key Laboratory for Novel Software Technology China Department of Computer Science and Technology Nanjing University Nanjing210023 China School of Electronic Science and Engineering Nanjing University Nanjing210023 China School of Artificial Intelligence Nanjing University Nanjing210023 China

Convolutional Neural Networks (CNNs) have demonstrated remarkable prowess in the field of computer vision. However, their opaque decision-making processes pose significant challenges for practical applications. In this study, we provide quantitative metrics for assessing CNN filters by clustering the feature maps corresponding to individual filters in the model via Gaussian Mixture Model (GMM). By analyzing the clustering results, we screen out some anomaly filters associated with outlier samples. We further analyze the relationship between the anomaly filters and model overfitting, proposing three hypotheses. This method is universally applicable across diverse CNN architectures without modifications, as evidenced by its successful application to models like AlexNet and LeNet-5. We present three meticulously designed experiments demonstrating our hypotheses from the perspectives of model behavior, dataset characteristics, and filter impacts. Through this work, we offer a novel perspective for evaluating the CNN performance and gain new insights into the operational behavior of model overfitting. Copyright © 2024, The Authors. All rights reserved.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Self-Supervised Learning Using Noisy-Latent Augmentation

Self-Supervised Learning Using Noisy-Latent Augmentation

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Rasa Khosrowshahli Shahryar Rahnamayan Azam Asilian Bidgoli Masoud Makrehchi Department of Electrical Computer and Software Engineering Nature-Inspired Computational Intelligence (NICI) Lab Ontario Tech University Oshawa ON Canada Engineering Department Nature-Inspired Computational Intelligence (NICI) Lab Brock University St. Catharines ON Canada Nature-Inspired Computational Intelligence (NICI) Lab Faculty of Science Wilfrid Laurier University Waterloo ON Canada Department of Electrical Computer and Software Engineering Ontario Tech University Oshawa ON Canada

Generally speaking, labeled data is difficult and expensive to provide for applications in machine learning and data mining. One of the earliest approaches to tackle this problem is semi-supervised self-training to take advantages of labeled and unlabeled data to create pseudo-labeled data. However, reaching a high level of confidence to predict the unseen data by a classifier with a limited number of labeled samples is a challenging task. Generating pseudo-labeled data can collaboratively improve the self-training to increase its confidence for further predictions. This paper proposes a collaborative framework between augmentation and self-training to accurately train a model with very limited labeled data. Our framework includes two components where the first component is an unsupervised technique to augment labeled data and feed to the second component which is self-training. The first component uses a custom variational autoencoder architecture (VAE) to generate new samples by adding randomly generated noise to encoded latent representation. As a result, the augmentation component can generate the unique and unexplored images with respect to limited input data distribution. We evaluated the proposed framework on handwritten MNIST image dataset. The conducted experiment shows that the generative component can be helpful in overcoming the problem of inaccurate self-training prediction when sufficient labeled data is not accessible.

关键词：

来源：评论

学校读者我要写书评

暂无评论

The Rise of Cloud Computing: Data Protection, Privacy, and Open Research Challenges - A Systematic Literature Review (SLR)

引用

Computational Intelligence and Neuroscience 2022年第0期2022卷 8303504页

作者： Hassan, Junaid Shehzad, Danish Habib, Usman Aftab, Muhammad Umar Ahmad, Muhammad Kuleev, Ramil Mazzara, Manuel Department of Computer Science National University of Computer and Emerging Sciences Islamabad Chiniot-Faisalabad Campus Chiniot35400 Pakistan Department of Computer Science Superior University Lahore54000 Pakistan Faculty of Computer Sciences and Engineering GIK Institute of Engineering Sciences and Technology Topi Swabi Khyber Pakhtunkhwa23640 Pakistan Institute of Software Development and Engineering Innopolis University Innopolis420500 Russia

Cloud computing is a long-standing dream of computing as a utility, where users can store their data remotely in the cloud to enjoy on-demand services and high-quality applications from a shared pool of configurable computing resources. Thus, the privacy and security of data are of utmost importance to all of its users regardless of the nature of the data being stored. In cloud computing environments, it is especially critical because data is stored in various locations, even around the world, and users do not have any physical access to their sensitive data. Therefore, we need certain data protection techniques to protect the sensitive data that is outsourced over the cloud. In this paper, we conduct a systematic literature review (SLR) to illustrate all the data protection techniques that protect sensitive data outsourced over cloud storage. Therefore, the main objective of this research is to synthesize, classify, and identify important studies in the field of study. Accordingly, an evidence-based approach is used in this study. Preliminary results are based on answers to four research questions. Out of 493 research articles, 52 studies were selected. 52 papers use different data protection techniques, which can be divided into two main categories, namely noncryptographic techniques and cryptographic techniques. Noncryptographic techniques consist of data splitting, data anonymization, and steganographic techniques, whereas cryptographic techniques consist of encryption, searchable encryption, homomorphic encryption, and signcryption. In this work, we compare all of these techniques in terms of data protection accuracy, overhead, and operations on masked data. Finally, we discuss the future research challenges facing the implementation of these techniques. © 2022 Junaid Hassan et al.

关键词： Sensitive data

来源：评论

学校读者我要写书评

暂无评论

CommGPT: A Graph and Retrieval-Augmented Multimodal Communication Foundation Model

arXiv

引用

arXiv 2025年

作者： Jiang, Feibo Zhu, Wanyun Dong, Li Wang, Kezhi Yang, Kun Pan, Cunhua Dobre, Octavia A. Hunan Normal University China Hunan University of Technology and Business China Department of Computer Science Brunel University London United Kingdom School of Intelligent Software and Engineering Nanjing University China Southeast University China Memorial University Canada

Large Language Models (LLMs) possess human-level cognitive and decision-making capabilities, making them a key technology for 6G. However, applying LLMs to the communication domain faces three major challenges: 1) Inadequate communication data;2) Restricted input modalities;and 3) Difficulty in knowledge retrieval. To overcome these issues, we propose CommGPT, a multimodal foundation model designed specifically for communications. First, we create high-quality pretraining and fine-tuning datasets tailored in communication, enabling the LLM to engage in further pretraining and fine-tuning with communication concepts and knowledge. Then, we design a multimodal encoder to understand and process information from various input modalities. Next, we construct a Graph and Retrieval-Augmented Generation (GRG) framework, efficiently coupling Knowledge Graph (KG) with Retrieval-Augmented Generation (RAG) for multi-scale learning. Finally, we demonstrate the feasibility and effectiveness of the CommGPT through experimental validation. Copyright © 2025, The Authors. All rights reserved.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Data-Driven Estimation of Effectiveness of COVID-19 Non-pharmaceutical Intervention Policies

Data-Driven Estimation of Effectiveness of COVID-19 Non-phar...

引用

IEEE International Conference on Big Data

作者： Yash Mahajan Sheikh Rabiul Islam Mohammad Ruhul Amin Shubhra Kanti Karmaker Santu Computer Science and Software Engineering Auburn University Auburn USA Department of Computing Sciences University of Hartford Connecticut USA Computer and Information Science Fordham University New York USA

ISBN: (纸本)9781665480468

Non-pharmaceutical Interventions (NPIs), such as Stay-at-Home, and Face-Mask-Mandate, are essential components of the public health response to contain an outbreak like COVID-19. However, it is very challenging to quantify the individual or joint effectiveness of NPIs and their impact on people from different racial and ethnic groups or communities in general. Therefore, in this paper, we study the following two research questions: 1) How can we quantitatively estimate the effectiveness of different NPI policies pertaining to the COVID-19 pandemic?; and 2) Do these policies have considerably different effects on communities from different races and ethnicity? To answer these questions, we model the impact of an NPI as a joint function of stringency and effectiveness over a duration of time. Consequently, we propose a novel stringency function that can provide an estimate of how strictly an NPI was implemented on a particular day. Next, we applied two popular tree-based discriminative classifiers, considering the change in daily COVID cases and death counts as binary target variables, while using stringency values of different policies as independent features. Finally, we interpreted the learned feature weights as the effectiveness of COVID-19 NPIs. Our experimental results suggest that, at the country level, restaurant closures and stay-at-home policies were most effective in restricting the COVID-19 confirmed cases and death cases respectively; and overall, restaurant closing was most effective in hold-down of COVID-19 cases at individual community levels such as Asian, White, Black, AIAN and, NHPI. Additionally, we also performed a comparative analysis between race-specific effectiveness and country-level effectiveness to see whether different communities were impacted differently. Our findings suggest that the different policies impacted communities (race and ethnicity) differently.

关键词： COVID-19 Pandemics Estimation Big Data Vaccines Public healthcare Business

来源：评论

学校读者我要写书评

暂无评论

Explaining Model Overfitting in CNNS Via GMM Clustering

SSRN

引用

SSRN 2024年

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Deep Feature Rotation for Multimodal Image Style Transfer

arXiv

引用

arXiv 2022年

作者： Nguyen, Son Truong Tuyen, Nguyen Quang Phuc, Nguyen Hong School of Mechanical Engineering Hanoi University of Science and Technology Viet Nam School of Computer Science and Engineering University of Aizu Japan Department of Software Engineering Eastern International University Viet Nam

Recently, style transfer is a research area that attracts a lot of attention, which transfers the style of an image onto a content target. Extensive research on style transfer has aimed at speeding up processing or generating high-quality stylized images. Most approaches only produce an output from a content and style image pair, while a few others use complex architectures and can only produce a certain number of outputs. In this paper, we propose a simple method for representing style features in many ways called Deep Feature Rotation (DFR), while not only producing diverse outputs but also still achieving effective stylization compared to more complex methods. Our approach is representative of the many ways of augmentation for intermediate feature embedding without consuming too much computational expense. We also analyze our method by visualizing output in different rotation weights. © 2022, CC BY.

关键词： Rotation

来源：评论

学校读者我要写书评

暂无评论

See Blue Sky: Deep Image Dehaze Using Paired and Unpaired Training Images

arXiv

引用

arXiv 2022年

作者： Zhang, Xiaoyan Tang, Gaoyang Zhu, Yingying Tian, Qi The College of Computer Science and Software Engineering Shenzhen University Guang Dong Shenzhen518060 China Department of Computer Science The Univerisity of Texas San AntonioTX78249 United States

The issue of image haze removal has attracted wide attention in recent years. However, most existing haze removal methods cannot restore the scene with clear blue sky, since the color and texture information of the object in the original haze image is insufficient. To remedy this, we propose a cycle generative adversarial network to construct a novel end-to-end image dehaze model. We adopt outdoor image datasets to train our model, which includes a set of real-world unpaired image dataset and a set of paired image dataset to ensure that the generated images are close to the real scene. Based on the cycle structure, our model adds four different kinds of loss function to constrain the effect including adversarial loss, cycle consistency loss, photorealism loss and paired L1 loss. These four constraints can improve the overall quality of such degraded images for better visual appeal and ensure reconstruction of images to keep from distortion. The proposed model could remove the haze of images and also restore the sky of images to be clean and blue (like captured in a sunny weather). Copyright © 2022, The Authors. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of Pneumatic Soft Gripper with Suction and Grasp Composite Structure 5th

Design and Implementation of Pneumatic Soft Gripper with Suc...

引用

5th International Conference on Cognitive Systems and Signal Processing, ICCSIP 2020

作者： Huang, Haiming Liang, Xiaotao Zhuo, Yufan Wu, Linyuan Wen, Zhenkun Sun, Fuchun College of Electronic and Information Engineering Shenzhen University Shenzhen518060 China Peng Cheng Lab Shenzhen GD518055 China College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China Department of Computer Science and Technology Tsinghua University Beijing100084 China

ISBN: (纸本)9789811623356

Robot gripper is used in many different places at present, but traditional gripper is difficult to grasp and sort soft and fragile fruits and vegetables effectively. Based on manipulator technology, this paper presents a design scheme of pneumatic multi-fingered gripper. This design combines the vacuum chunk and soft fingers to make the gripper precisely grasp the target object without damaging the surface of the object. The flexible fingers can be made quickly by using a compound injection molding method. Combined with the STM32 microcontroller and the Universal Robots 5 (UR Arm), the operation system of the soft gripper is realized, and the man-machine interaction presents a good performance. Through the grasping experiment, it is proved that the prototype can grasp, transport, and place soft and fragile objects stably and accurately. Overall, this design implements the combination of pneumatic unit and soft gripper, and provides a new orientation to the research of soft robot. © 2021, Springer Nature Singapore Pte Ltd.

关键词： Grippers

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：