检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Li, Jiangmeng Qiang, Wenwen Zheng, Changwen Su, Bing Razzak, Farid Wen, Ji-Rong Xiong, Hui The University of Chinese Academy of Sciences Beijing China The Science & Technology on Integrated Information System Laboratory Institute of Software Chinese Academy of Sciences Beijing China The New York University Columbia University New York United States The Beijing Key Laboratory of Big Data Management and Analysis Methods Gaoling School of Artificial Intelligence Renmin University of China Beijing100872 China Guangzhou China Department of Computer Science & Engineering The Hong Kong University of Science and Technology Hong Kong

While self-supervised learning techniques are often used to mine hidden knowledge from unlabeled data via modeling multiple views, it is unclear how to perform effective representation learning in a complex and inconsistent context. To this end, we propose a new multi-view self-supervised learning method, namely consistency and complementarity network (CoCoNet), to comprehensively learn global inter-view consistent and local cross-view complementarity-preserving representations from multiple views. To capture crucial common knowledge which is implicitly shared among views, CoCoNet employs a global consistency module that aligns the probabilistic distribution of views by utilizing an efficient discrepancy metric based on the generalized sliced Wasserstein distance. To incorporate cross-view complementary information, CoCoNet proposes a heuristic complementarity-aware contrastive learning approach, which extracts a complementarity-factor jointing cross-view discriminative knowledge and uses it as the contrast to guide the learning of view-specific encoders. Theoretically, the superiority of CoCoNet is verified by our information-theoretical-based analyses. Empirically, our thorough experimental results show that CoCoNet outperforms the state-of-the-art self-supervised methods by a significant margin, for instance, CoCoNet beats the best benchmark method by an average margin of 1.1% on ImageNet. Copyright © 2022, The Authors. All rights reserved.

关键词： Supervised learning

来源：评论

学校读者我要写书评

暂无评论

Value Function Dynamic Estimation in Reinforcement Learning based on data Adequacy 20

Value Function Dynamic Estimation in Reinforcement Learning ...

引用

4th High Performance Computing and Cluster Technologies Conference, HPCCT 2020 and the 3rd International Conference on Big data and Artificial Intelligence, BDAI 2020

作者： Gao, Huifan Pan, Yinghui Tang, Jing Zeng, Yifeng Chai, Peihua Cao, Langcai Xiamen Key Laboratory of Big Data Intelligent Analysis and Decision Department of Automation Xiamen University Xiamen China College of Computer Science and Software Engineering Shenzhen University China Newcastle Business School Northumbria University United Kingdom Department of Computer and Information Sciences Northumbria University United Kingdom

ISBN: (纸本)9781450375603

In recent years, reinforcement learning has played an important role in the study of decision problem in computer games. To solve the problem of how to better estimate the value function with limited computational resources, this paper proposes a dynamic estimation method of value function based on data adequacy. In consideration of the varying complexity of each state in the MDP model, we propose a dynamic value function estimation method which is different from the fixed value function estimation method in traditional methods. Based on the PigChase challenge of the Malmo project launched by Microsoft in 2017, we compare the new method with the existing techniques. Experimental results show that the performance of the proposed algorithm is better than traditional algorithms. © 2020 ACM.

关键词： Dynamic programming

来源：评论

学校读者我要写书评

暂无评论

SODU2-NET: a novel deep learning-based approach for salient object detection utilizing U-NET

引用

PeerJ Computer science 2025年 11卷 e2623-e2623页

作者： Abbas, Hyder Ren, Shen Bing Asim, Muhammad Hassan, Syeda Iqra El-Latif, Ahmed A. Abd State Key Laboratory of Public Big Data College of Computer Science and Technology Institute for Artificial Intelligence Guizhou University Guizhou Guiyang China School of Computer Science and Engineering Central South University Changsha China EIAS Data Science and Blockchain Laboratory College of Computer and Information Sciences Prince Sultan University Riyadh Saudi Arabia School of Computer Science and Technology Guangdong University of Technology Guangzhou China Department of Electrical and Electronic Engineering British Malaysian Institute Universiti of Kuala Lumpur Kuala Lumpur Malaysia Software Engineering Department Sir Syed University of Engineering and Technology Karachi Pakistan Department of Mathematics and Computer Science Faculty of Science Menoufia University Shebin El-Koom Egypt

Detecting and segmenting salient objects from natural scenes, often referred to as salient object detection, has attracted great interest in computer vision. To address this challenge posed by complex backgrounds in salient object detection is crucial for advancing the field. This article proposes a novel deep learning-based architecture called SODU2-NET (Salient object detection U2-Net) for salient object detection that utilizes the U-NET base structure. This model addresses a gap in previous work that focused primarily on complex backgrounds by employing a densely supervised encoder-decoder network. The proposed SODU2-NET employs sophisticated background subtraction techniques and utilizes advanced deep learning architectures that can discern relevant foreground information when dealing with complex backgrounds. Firstly, an enriched encoder block with full feature fusion (FFF) with atrous spatial pyramid pooling (ASPP) varying dilation rates to efficiently capture multi-scale contextual information, improving salient object detection in complex backgrounds and reducing the loss of information during down-sampling. Secondly the block includes an attention module that refines the decoder, is constructed to enhances the detection of salient objects in complex backgrounds by selectively focusing attention on relevant features. This allows the model to reconstruct detailed and contextually relevant information, which is essential to determining salient objects accurately. Finally, the architecture has been improved by adding a residual block at the encoder end, which is responsible for both saliency prediction and map refinement. The proposed network is designed to learn the transformation between input images and ground truth, enabling accurate segmentation of salient object regions with clear borders and accurate prediction of fine structures. SODU2-NET is demonstrated to have superior performance in five public datasets, including DUTS, SOD, DUT OMRON, HKU-IS, PASCA

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Transformers in Medical Image Analysis: A Review

arXiv

引用

arXiv 2022年

作者： He, Kelei Gan, Chen Li, Zhuoyuan Rekik, Islem Yin, Zihao Ji, Wen Gao, Yang Wang, Qian Zhang, Junfeng Shen, Dinggang Medical School of Nanjing University Nanjing China National Institute of Healthcare Data Science Nanjing University Nanjing China State Key Laboratory for Novel Software Technology Nanjing University Nanjing China BASIRA Lab Faculty of Computer and Informatics Engineering Istanbul Technical University Istanbul Turkey School of Science and Engineering Computing University of Dundee United Kingdom School of Biomedical Engineering ShanghaiTech University Shanghai China Department of Research and Development Shanghai United Imaging Intelligence Co. Ltd. Shanghai China

Transformers have dominated the field of natural language processing, and recently impacted the computer vision area. In the field of medical image analysis, Transformers have also been successfully applied to full-stack clinical applications, including image synthesis/reconstruction, registration, segmentation, detection, and diagnosis. Our paper aims to promote awareness and application of Transformers in the field of medical image analysis. Specifically, we first overview the core concepts of the attention mechanism built into Transformers and other basic components. Second, we review various Transformer architectures tailored for medical image applications and discuss their limitations. Within this review, we investigate key challenges revolving around the use of Transformers in different learning paradigms, improving the model efficiency, and their coupling with other techniques. We hope this review can give a comprehensive picture of Transformers to the readers in the field of medical image analysis. © 2022, CC BY-SA.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

Dynamic slimmable denoising network

arXiv

引用

arXiv 2021年

作者： Jiang, Zutao Li, Changlin Chang, Xiaojun Zhu, Jihua Yang, Yi School of Software Engineering Xi'an Jiaotong Universiy China Department of Data Science and Ai Monash Univeristy School of Computing Technologies Rmit University Australia Australian Artificial Intelligence Institute University of Technology Sydney UltimoNSW2007 Australia

Recently, tremendous human-designed and automatically searched neural networks have been applied to image denoising. However, previous works intend to handle all noisy images in a pre-defined static network architecture, which inevitably leads to high computational complexity for good denoising quality. Here, we present dynamic slimmable denoising network (DDS-Net), a general method to achieve good denoising quality with less computational complexity, via dynamically adjusting the channel configurations of networks at test time with respect to different noisy images. Our DDS-Net is empowered with the ability of dynamic inference by a dynamic gate, which can predictively adjust the channel configuration of networks with negligible extra computation cost. To ensure the performance of each candidate sub-network and the fairness of the dynamic gate, we propose a three-stage optimization scheme. In the first stage, we train a weight-shared slimmable super network. In the second stage, we evaluate the trained slimmable super network in an iterative way and progressively tailor the channel numbers of each layer with minimal denoising quality drop. By a single pass, we can obtain several sub-networks with good performance under different channel configurations. In the last stage, we identify easy and hard samples in an online way and train a dynamic gate to predictively select the corresponding sub-network with respect to different noisy images. Extensive experiments demonstrate our DDS-Net consistently outperforms the state-of-the-art individually trained static denoising networks. © 2021, CC BY.

关键词： Computational complexity

来源：评论

学校读者我要写书评

暂无评论

A Geometric Strategy Algorithm for Orthogonal Pro jection onto a Parametric Surface

引用

Journal of Computer science & Technology 2019年第6期34卷 1279-1293页

作者： Xiaowu Li Zhinan Wu Feng Pan Juan Liang Jiafeng Zhang Linke Hou College of Data Science and Information Engineering Guizhou Minzu UniversityGuiyang 550025China School of Mathematics and Computer Science Yichun UniversityYichun 336000China School of Software Engineering South China University of TechnologyGuangzhou 510006China Department of Science Taiyuan Institute of TechnologyTaiyuan 030008China Center for Economic Research Shandong UniversityJinan 250100China

In this paper, we investigate how to compute the minimum distance between a point and a parametric surface, and then to return the nearest point (foot point) on the surface as well as its corresponding parameter, which is also called the point projection problem of a parametric surface. The geometric strategy algorithm (hereafter GSA) presented consists of two parts as follows. The normal curvature to a given parametric surface is used to find the corresponding foot point firstly, and then the Taylor's expansion of the parametric surface is employed to compute parameter increments and to get the iteration formula to calculate the orthogonal projection point of test point to the parametric surface. Our geometric strategy algorithm is essentially dependent on the geometric property of the normal curvature, and performs better than existing methods in two ways. Firstly, GSA converges faster than existing methods, such as the method to turn the problem into a root-finding of nonlinear system, subdividing methods, clipping methods, geometric methods (tangent vector and geometric curvature) and hybrid second-order method, etc. Specially, it converges faster than the classical Newton's iterative method. Secondly, GSA is independent of the initial iterative value, which we prove in Theorem 1. Many numerical examples confirm GSA's robustness and efficiency.

关键词： point projection problem point inversion problem normal curvature normal curvature sphere convergence analysis

来源：评论

学校读者我要写书评

暂无评论

VSRQ: Quantitative Assessment Method for Safety Risk of Vehicle Intelligent Connected System

arXiv

引用

arXiv 2023年

作者： Zhang, Tian Guan, Wenshan Miao, Hao Huang, Xiujie Liu, Zhiquan Wang, Chaonan Guan, Quanlong Fang, Liangda Duan, Zhifei Department of Cyberspace Security College of Information Science and Technology Jinan University Guangzhou511486 China Department of Computer Science College of Information Science and Technology Jinan University Guangzhou510632 China College of Information Science and Technology Jinan University Guangdong Institution of Smart Education Jinan University Guangzhou510632 China College of Cyber Security Jinan University Guangzhou510632 China Guangdong Gene Data Processing and Analysis Engineering Research Center China Pazhou Laboratory Guangzhou510330 China Guangxi Key Laboratory of Trusted Software Guilin University of Electronic Technology Guilin541004 China Guangzhou XPeng Motors Technology Co. Ltd No.8 Songgang Road Changxing Street Cencun Tianhe District Guangzhou China

The field of intelligent connected in modern vehicles continues to expand, and the functions of vehicles become more and more complex with the development of the times. This has also led to an increasing number of vehicle vulnerabilities and many safety issues. Therefore, it is particularly important to identify high-risk vehicle intelligent connected systems, because it can inform security personnel which systems are most vulnerable to attacks, allowing them to conduct more thorough inspections and tests. In this paper, we develop a new model for vehicle risk assessment by combining I-FAHP with FCA clustering: VSRQ model. We extract important indicators related to vehicle safety, use fuzzy cluster analys (FCA) combined with fuzzy analytic hierarchy process (FAHP) to mine the vulnerable components of the vehicle intelligent connected system, and conduct priority testing on vulnerable components to reduce risks and ensure vehicle safety. We evaluate the model on OpenPilot and experimentally demonstrate the effectiveness of the VSRQ model in identifying the safety of vehicle intelligent connected systems. The experiment fully complies with ISO 26262 and ISO/SAE 21434 standards, and our model has a higher accuracy rate than other models. These results provide a promising new research direction for predicting the security risks of vehicle intelligent connected systems and provide typical application tasks for VSRQ. The experimental results show that the accuracy rate is 94.36%, and the recall rate is 73.43%, which is at least 14.63% higher than all other known indicators. Copyright © 2023, The Authors. All rights reserved.

关键词： Vehicle safety

来源：评论

学校读者我要写书评

暂无评论

A Secure Federated data-Driven Evolutionary Multi-objective Optimization Algorithm

arXiv

引用

arXiv 2022年

作者： Liu, Qiqi Yan, Yuping Ligeti, Péter Jin, Yaochu Trustworthy and General AI Lab School of Engineering Westlake University China Faculty of Technology Bielefeld University Bielefeld33619 Germany Faculty of Informatics Department of Computeralgebra Eötvös Loránd University Hungary Smart Data Group E-Group ICT Software Zrt Hungary Department of Computer Science University of Surrey Surrey GuildfordGU2 7XH United Kingdom

data-driven evolutionary algorithms usually aim to exploit the information behind a limited amount of data to perform optimization, which have proved to be successful in solving many complex real-world optimization problems. However, most data-driven evolutionary algorithms are centralized, causing privacy and security concerns. Existing federated Bayesian optimization algorithms and data-driven evolutionary algorithms mainly protect the raw data on each client. To address this issue, this paper proposes a secure federated data-driven evolutionary multiobjective optimization algorithm to protect both the raw data and the newly infilled solutions obtained by optimizing the acquisition function conducted on the server. We select the query points on a randomly selected client at each round of surrogate update by calculating the acquisition function values of the unobserved points on this client, thereby reducing the risk of leaking the information about the solution to be sampled. In addition, since the predicted objective values of each client may contain sensitive information, we mask the objective values with Diffie-Hellman-based noise, and then send only the masked objective values of other clients to the selected client via the server. Since the calculation of the acquisition function also requires both the predicted objective value and the uncertainty of the prediction, the predicted mean objective and uncertainty are normalized to reduce the influence of noise. Experimental results on a set of widely used multi-objective optimization benchmarks show that the proposed algorithm can protect privacy and enhance security with only negligible sacrifice in the performance of federated data-driven evolutionary optimization. Copyright © 2022, The Authors. All rights reserved.

关键词： Evolutionary algorithms

来源：评论

学校读者我要写书评

暂无评论

An advanced algorithm for discrimination prevention in data mining

An advanced algorithm for discrimination prevention in data ...

引用

Telecommunications, Optics and Computer science (TOCS), IEEE Conference on

作者： Shuoyu Wang Jie Ren Hao Fang Jun Pan Xin Hu Tingyun Zhao College of Information Science and Technology Tibet University Lhasa China Department of Computer Science and Technology Lyuliang University Lvliang China College of Foreign Languages Liaoning University of Traditional Chinese Medicine Shenyang China School of Electronic and Information Engineering Beihang University Beijing China School of Mathematics and Statistics Yangtze Normal University Chongqing China School of Software and Big Data Changzhou College of Information Technology Changzhou China

ISBN: (纸本)9781665470544

data mining has been effectively utilized in huge expanded application areas. Associations overall go with significant business choices in light of mining of data. Discrimination in navigation and preservation of protection of data are a couple of significant difficulties in data mining. Discrimination is of two sorts, Direct Discrimination and Indirect Discrimination. Discrimination prevention includes two significant angles disclosure of direct and additionally roundabout discrimination and data transformation as alteration of separating rules without influencing data quality. Existing strategies for discrimination prevention utilize one of the three methodologies, in particular, the pre-process, in-process or post-process approach. Tests for the exhibition assessment of all calculations by fluctuating these info boundaries, each in turn to review and break down impact of these boundaries.

关键词： Computer science Navigation data integrity Computational modeling Optics Minimization data models

来源：评论

学校读者我要写书评

暂无评论

Multivariate Time Series Forecasting with Transfer Entropy Graph

arXiv

引用

arXiv 2020年

作者： Duan, Ziheng Xu, Haoyan Huang, Yida Feng, Jie Wang, Yueyang The School of Big Data and Software Engineering Chongqing University Chongqing401331 China The Department of Control Science and Engineering Zhejiang University Hangzhou310027 China

Multivariate time series (MTS) forecasting is an essential problem in many fields. Accurate forecasting results can effectively help decision-making. To date, many MTS forecasting methods have been proposed and widely applied. However, these methods assume that the predicted value of a single variable is affected by all other variables, which ignores the causal relationship among variables. To address the above issue, we propose a novel end-to-end deep learning model, termed graph neural network with Neural Granger Causality (CauGNN) in this paper. To characterize the causal information among variables, we introduce the Neural Granger Causality graph in our model. Each variable is regarded as a graph node, and each edge represents the casual relationship between variables. In addition, convolutional neural network (CNN) filters with different perception scales are used for time series feature extraction, which is used to generate the feature of each node. Finally, Graph Neural Network (GNN) is adopted to tackle the forecasting problem of graph structure generated by MTS. Three benchmark datasets from the real world are used to evaluate the proposed CauGNN. The comprehensive experiments show that the proposed method achieves state-of-the-art results in the MTS forecasting task. Copyright © 2020, The Authors. All rights reserved.

关键词： Graph neural networks

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：