检索结果-南通市图书馆

meta-learning Multi-Scale Radiology Medical Image Super-Resolution

Computers, Materials & Continua 2023年第5期75卷 2671-2684页

作者： Liwei Deng Yuanzhi Zhang Xin Yang Sijuan Huang Jing Wang Heilongjiang Provincial Key Laboratory of Complex Intelligent System and Integration School of AutomationHarbin University of Science and TechnologyHarbin150080HeilongjiangChina Department of Radiation Oncology Sun Yat-sen University Cancer CenterState Key Laboratory of Oncology in South ChinaCollaborative Innovation Center for Cancer MedicineGuangdong Key Laboratory of Nasopharyngeal Carcinoma Diagnosis and TherapyGuangzhou510060GuangdongChina Faculty of Rehabilitation Medicine Biofeedback LaboratoryGuangzhou Xinhua UniversityGuangzhou510520GuangdongChina

High-resolution medical images have important medical value,but are difficult to obtain *** by hardware equipment and patient’s physical condition,the resolution of directly acquired medical images is often not ***,many researchers have thought of using super-resolution algorithms for secondary processing to obtain high-resolution medical ***,current super-resolution algorithms only work on a single scale,and multiple networks need to be trained when super-resolution images of different scales are *** definitely raises the cost of acquiring high-resolution medical ***,we propose a multi-scale superresolution algorithm using *** algorithm combines a metalearning approach with an enhanced depth of residual super-resolution network to design a meta-upscale *** meta-upscale module utilizes the weight prediction property of meta-learning and is able to perform the super-resolution task of medical images at any ***,we design a non-integer mapping relation for super-resolution,which allows the network to be trained under non-integer magnification *** to the state-of-the-art single-image super-resolution algorithm on computed tomography images of the pelvic *** meta-learning multiscale superresolution algorithm obtained a surpassing of about 2%at a smaller model *** on different parts proves the high generalizability of our ***-scale super-resolution algorithms using meta-learning can compensate for hardware device defects and reduce secondary harm to patients while obtaining high-resolution medical *** can be of great use in imaging related fields.

关键词： Super resolution deep learning meta learning computed tomography

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Decision-Making Models Based on meta-Reinforcement learning for Intelligent Vehicles at Urban Intersections

引用

Journal of Beijing Institute of Technology 2022年第4期31卷 327-339页

作者： Xuemei Chen Jiahe Liu Zijia Wang Xintong Han Yufan Sun Xuelong Zheng School of Mechanical Engineering Beijing Institute of TechnologyBeijing 100081China

Behavioral decision-making at urban intersections is one of the primary difficulties currently impeding the development of intelligent vehicle *** problem is that existing decision-making algorithms cannot effectively deal with complex random scenarios at urban *** deal with this,a deep deterministic policy gradient(DDPG)decision-making algorithm(T-DDPG)based on a time-series Markov decision process(T-MDP)was developed,where the state was extended to collect observations from several consecutive *** found that T-DDPG performed better in terms of convergence and generalizability in complex intersection scenarios than a traditional DDPG ***,model-agnostic meta-learning(MAML)was incorporated into the T-DDPG algorithm to improve the training method,leading to a decision algorithm(T-MAML-DDPG)based on a secondary *** experiments of intersection scenarios were carried out on the Gym-Carla platform to verify and compare the decision *** results showed that T-MAML-DDPG was able to easily deal with the random states of complex intersection scenarios,which could improve traffic safety and *** above decision-making models based on meta-reinforcement learning are significant for enhancing the decision-making ability of intelligent vehicles at urban intersections.

关键词： decision-making intelligent vehicles meta learning reinforcement learning urban intersections

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

FMSA:a meta-learning framework-based fast model stealing attack technique against intelligent network intrusion detection systems

引用

Cybersecurity 2024年第1期7卷 110-121页

作者： Kaisheng Fan Weizhe Zhang Guangrui Liu Hui He School of Cyberspace Science Harbin Institute of TechnologyHarbin 150001China Department of New Networks Peng Cheng LaboratoryShenzhen 518055GuangdongChina

Intrusion detection systems are increasingly using machine *** machine learning has shown excellent performance in identifying malicious traffic,it may increase the risk of privacy *** paper focuses on imple-menting a model stealing attack on intrusion detection *** model stealing attacks are hard to imple-ment in practical network environments,as they either need private data of the victim dataset or frequent access to the victim *** this paper,we propose a novel solution called Fast Model Stealing Attack(FMSA)to address the problem in the field of model stealing *** also highlight the risks of using ML-NIDS in network ***,meta-learning frameworks are introduced into the model stealing algorithm to clone the victim model in a black-box ***,the number of accesses to the target model is used as an optimization term,resulting in minimal queries to achieve model ***,adversarial training is used to simulate the data distribution of the target model and achieve the recovery of privacy *** experiments on multiple public datasets,compared to existing state-of-the-art algorithms,FMSA reduces the number of accesses to the target model and improves the accuracy of the clone model on the test dataset to 88.9%and the similarity with the target model to 90.1%.We can demonstrate the successful execution of model stealing attacks on the ML-NIDS system even with protective measures in place to limit the number of anomalous queries.

关键词： AI security Model stealing attack Network intrusion detection meta learning

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Distilling base-and-meta network with contrastive learning for few-shot semantic segmentation

引用

Autonomous Intelligent Systems 2023年第1期3卷 1-11页

作者： Xinyue Chen Yueyi Wang Yingyue Xu Miaojing Shi Informatics King’s College LondonStrandLondonWC2R 2LSUnited Kingdom. College of Electronic and Information Engineering Tongji UniversityShanghai201804China

Current studies in few-shot semantic segmentation mostly utilize meta-learning frameworks to obtain models that can be generalized to new ***,these models trained on base classes with sufficient annotated samples are biased towards these base classes,which results in semantic confusion and ambiguity between base classes and new classes.A strategy is to use an additional base learner to recognize the objects of base classes and then refine the prediction results output by the meta *** this way,the interaction between these two learners and the way of combining results from the two learners are *** paper proposes a new model,namely Distilling Base and meta(DBAM)network by using self-attention mechanism and contrastive learning to enhance the few-shot segmentation ***,the self-attention-based ensemble module(SEM)is proposed to produce a more accurate adjustment factor for improving the fusion of two predictions of the two ***,the prototype feature optimization module(PFOM)is proposed to provide an interaction between the two learners,which enhances the ability to distinguish the base classes from the target class by introducing contrastive learning *** experiments have demonstrated that our method improves on the PASCAL-5i under 1-shot and 5-shot settings,respectively.

关键词： Semantic segmentation Few-shot learning meta learning Contrastive learning Self-attention

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Recent advances of few-shot learning methods and applications

引用

Science China(Technological Sciences) 2023年第4期66卷 920-944页

作者： WANG JianYuan LIU KeXin ZHANG YuCheng LENG Biao LU JinHu School of Automation Science and Electrical Engineering Beihang UniversityBeijing 100191China School of Computer Science and Engineering Beihang UniversityBeijing 100191China

The rapid development of deep learning provides great convenience for production and ***,the massive labels required for training models limits further ***-shot learning which can obtain a high-performance model by learning few samples in new tasks,providing a solution for many scenarios that lack *** paper summarizes few-shot learning algorithms in recent years and proposes a ***,we introduce the few-shot learning task and its ***,according to different implementation strategies,few-shot learning methods in recent years are divided into five categories,including data augmentation-based methods,metric learning-based methods,parameter optimization-based methods,external memory-based methods,and other ***,We investigate the application of few-shot learning methods and summarize them from three directions,including computer vision,human-machine language interaction,and robot ***,we analyze the existing few-shot learning methods by comparing evaluation results on mini Image Net,and summarize the whole paper.

关键词： few-shot learning deep learning meta learning data augmentation parameter optimization

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

A Robust Framework for Multimodal Sentiment Analysis with Noisy Labels Generated from Distributed Data Annotation

引用

Computer Modeling in Engineering & Sciences 2024年第6期139卷 2965-2984页

作者： Kai Jiang Bin Cao Jing Fan School of Computer Science and Technology Zhejiang University of TechnologyHangzhou310023China

Multimodal sentiment analysis utilizes multimodal data such as text,facial expressions and voice to detect people’s *** the advent of distributed data collection and annotation,we can easily obtain and share such multimodal ***,due to professional discrepancies among annotators and lax quality control,noisy labels might be *** research suggests that deep neural networks(DNNs)will overfit noisy labels,leading to the poor performance of the *** address this challenging problem,we present a Multimodal Robust meta learning framework(MRML)for multimodal sentiment analysis to resist noisy labels and correlate distinct modalities ***,we propose a two-layer fusion net to deeply fuse different modalities and improve the quality of the multimodal data features for label correction and network ***,a multiple meta-learner(label corrector)strategy is proposed to enhance the label correction approach and prevent models from overfitting to noisy *** conducted experiments on three popular multimodal datasets to verify the superiority of ourmethod by comparing it with four baselines.

关键词： Distributed data collection multimodal sentiment analysis meta learning learn with noisy labels

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

还原论抑或加工论：深度学习的根基反思与理论走向

引用

教育学 2021年第6期

作者：龙宝新李亚云

深度学习是学习者透过表象、超越知识、潜入心灵、全面领悟的一种知识学习现象、目标与状态，还原论与加工论是深度学习研究的两个理论原生点。问题、思维与意义是深度学习的三个关节点，回植情景、思维升级是深度学习创建的两大基本路... 详细信息

深度学习是学习者透过表象、超越知识、潜入心灵、全面领悟的一种知识学习现象、目标与状态，还原论与加工论是深度学习研究的两个理论原生点。问题、思维与意义是深度学习的三个关节点，回植情景、思维升级是深度学习创建的两大基本路径，贯通型深度学习理论是有机整合还原论与加工论的理念范型。面向未来，深度学习的理论走向是：构筑知识学习的立体世界，构建知识学习的生发链、生态环，建立学习力的系统提升机制。

关键词：还原论加工论深度学习知识学习问题思维意义高阶思维元学习 reductionism processing theory deep learning knowledge learning problem thinking meaning higher-order thinking meta learning

来源：人大复印报刊资料评论

在线全文

人大复印报刊资料

学校读者我要写书评

暂无评论

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

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：