检索结果-内蒙古大学图书馆

Weighted Consistent Multi-view Discriminant Analysis in Unreliable Labeling Environment 1

3rd International Conference on Artificial Intelligence Logic and Applications, AILA 2023

作者： Li, Meihua Zhao, Yang Pei, Jihong Yang, Xuan College of Electronics and Information Engineering Shenzhen University Guangdong Shenzhen China Guangdong Key Laboratory of Intelligent Information Processing Guangdong Shenzhen China Department of Computer Science City University of Hong Kong Hong Kong College of Computer Science and Software Engineering Shenzhen University Guangdong Shenzhen China

ISBN: (数字)9789819978694

ISBN: (纸本)9789819978687

Multi-view discriminant analysis method (MvDA) is an effective supervised multi-view learning method. However, in practical multi-view learning application scenarios, there may be the problem that the sample label information from some viewpoints is unreliable. In the MvDA method, the information of all views is considered to have equal reliability. The data information in views containing unreliable label information may make it difficult for MvDA to learn accurate common features among data from different views. Therefore, in this paper, a weighted consistent multi-view discriminant analysis (WMvDA-VC) is proposed for the multi-view learning task in unreliable labeling environment. By considering the data characteristics under different views, the information from different views is assigned different reliability weights. Using the weighted scatter matrices, multiple projection matrices are learned. Then the data from different views are projected into the same common projection space. In the common subspace, dissimilar samples in different views are dispersed as much as possible and similar samples are aggregated as much as possible. The impact of data from views containing unreliable labels on the multi-view learning performance is reduced by adjusting the weights of the views with unreliable labels. The method is experimented on four widely used datasets. The experimental results show that the proposed WMvDA-VC exhibits excellent performance in the classification recognition task with unreliably labeled environment. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2023.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

StyleGene: Crossover and Mutation of Region-level Facial Genes for Kinship Face Synthesis

StyleGene: Crossover and Mutation of Region-level Facial Gen...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Hao Li Xianxu Hou Zepeng Huang Linlin Shen Computer Vision Institute College of Computer Science and Software Engineering Shenzhen University National Engineering Laboratory for Big Data System Computing Technology Shenzhen University School of AI and Advanced Computing Xi'an Jiaotong-Liverpool University Shenzhen Institute of Artificial Intelligence and Robotics for Society Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University

High-fidelity kinship face synthesis has many potential applications, such as kinship verification, missing child identification, and social media analysis. However, it is challenging to synthesize high-quality descendant faces with genetic relations due to the lack of large-scale, high-quality annotated kinship data. This paper proposes RFG (Region-level Facial Gene) extraction framework to address this issue. We propose to use IGE (Image-based Gene Encoder), LGE (Latent-based Gene Encoder) and Gene Decoder to learn the RFGs of a given face image, and the relationships between RFGs and the latent space of Style-GAN2. As cycle-like losses are designed to measure the $\mathcal{L}_{2}$ distances between the output of Gene Decoder and image encoder, and that between the output of LGE and IGE, only face images are required to train our framework, i.e. no paired kinship face data is required. Based upon the proposed RFGs, a crossover and mutation module is further designed to inherit the facial parts of parents. A Gene Pool has also been used to introduce the variations into the mutation of RFGs. The diversity of the faces of descendants can thus be significantly increased. Qualitative, quantitative, and subjective experiments on FIW, TSKinFace, and FF-Databases clearly show that the quality and diversity of kinship faces generated by our approach are much better than the existing state-of-the-art methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Regularized Loose Coupled Deep Non-negative Basis Matrix Factorization for Low-Resolution Face Image Recognition 1

引用

3rd International Conference on Artificial Intelligence Logic and Applications, AILA 2023

作者： Li, Jianhua Wang, Jinxin Pei, Jihong Zhao, Yang College of Electronics and Information Engineering Shenzhen University Guangdong Shenzhen China Guangdong Key Laboratory of Intelligent Information Processing Guangdong Shenzhen China Department of Computer Science City University of Hong Kong Hong Kong College of Computer Science and Software Engineering Shenzhen University Guangdong Shenzhen China

ISBN: (数字)9789819978694

ISBN: (纸本)9789819978687

Low-resolution face image recognition is a research focus in computer vision and pattern recognition. In this paper, the potential relationship between matched high-resolution face and low-resolution face images is considered to propose the regularized loose coupled deep non-negative basis matrix factorization (RLCDNBMF) architecture, which uses regularized deep non-negative basis matrix factorization for high-resolution images and couples its coefficient matrix with the coefficient matrix obtained from low-resolution non-negative factorization, so that the discriminative information of high-resolution face images can be fully utilized to guide the non-negative matrix factorization of low-resolution face images. Comparative experiments are conducted on three mainstream face databases, and the experimental results show that the method can improve the accuracy of low-resolution face recognition. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2023.

关键词： Non-negative matrix factorization

来源：评论

学校读者我要写书评

暂无评论

Decentralized Reputation-based Leader Election for Privacy-preserving Federated Learning on Internet of Things

Decentralized Reputation-based Leader Election for Privacy-p...

引用

IEEE/ACM Int'l Conference on & Int'l Conference on Cyber, Physical and Social Computing (CPSCom) Green Computing and Communications (GreenCom)

作者： Luyao Peng Xiangyun Tang Chenxi Li Yao Xiao Tao Zhang Yu Weng School of Information Engineering & Key Laboratory of Ethnic Language Intelligent Analysis and Security Governance Minzu University of China Beijing China State Key Laboratory of Integrated Services Networks Xidian University Shaanxi China School of Cyberspace Security Beijing Institute of Technology Beijing China School of Software Engineering Beijing Jiaotong University Beijing China

The Internet of Things (IoT) based on Deep Learning (DL) technologies has facilitated people’s lives in various aspects. However, since the IoT data used to train DL models contains users’ sensitive personal information, privacy and security concerns arise in IoT. Although many works have presented security solutions for the privacy and security concerns on IoT, they cannot monitor the model quality of data owners, resulting in unusable models making misleading decisions, and they cannot defend against the curious participants inferring private data in the model training process. In this paper, we propose a Decentralized Reputation-based Leader Election scheme (DeRLE) for privacy-preserving distributed model training in IoT based on Federated Learning (FL) and Blockchain. DeRLE adopts decentralized model training while preserving privacy. To avoid a single point of failure in FL, DeRLE elects a refreshed leader in each epoch of model update, which prevents the fixed server of the basic FL from deriving sensitive data from historical local models. Furthermore, to protect the privacy of local models in FL, we design a reputation-based Differential Privacy (DP) mechanism to supervise the quality of local models and encourage data owners to inject reasonable DP noise. We conduct extensive experiments using Hyperledger Fabric and MNIST. The evaluation results confirm the fairness of DeRLE’s probability distribution and demonstrate its feasibility and effectiveness.

关键词：

来源：评论

学校读者我要写书评

暂无评论

CIRCLE: Continual Repair across Programming Languages

arXiv

引用

arXiv 2022年

作者： Yuan, Wei Zhang, Quanjun He, Tieke Fang, Chunrong Hung, Nguyen Quoc Viet Hao, Xiaodong Yin, Hongzhi School of Information Technology and Electrical Engineering The University of Queensland Australia State Key Laboratory for Novel Software Technology Nanjing University China Institute for Integrated and Intelligent Systems Griffith University Australia

Automatic Program Repair (APR) aims at fixing buggy source code with less manual debugging efforts, which plays a vital role in improving software reliability and development productivity. Recent APR works have achieved remarkable progress via applying deep learning (DL), particularly neural machine translation (NMT) techniques. However, we observe that existing DL-based APR models suffer from at least two severe drawbacks: (1) Most of them can only generate patches for a single programming language, as a result, to repair multiple languages, we have to build and train many repairing models. (2) Most of them are developed offline. Therefore, they won’t function when there are new-coming requirements. To address the above problems, a T5-based APR framework equipped with continual learning ability across multiple programming languages is proposed, namely ContInual Repair aCross Programming LanguagEs (CIRCLE). Specifically, (1) CIRCLE utilizes a prompting function to narrow the gap between natural language processing (NLP) pre-trained tasks and APR. (2) CIRCLE adopts a difficulty-based rehearsal strategy to achieve lifelong learning for APR without access to the full historical data. (3) An elastic regularization method is employed to strengthen CIRCLE’s continual learning ability further, preventing it from catastrophic forgetting. (4) CIRCLE applies a simple but effective re-repairing method to revise generated errors caused by crossing multiple programming languages. We train CIRCLE for four languages (i.e., C, JAVA, JavaScript, and Python) and evaluate it on five commonly used benchmarks. The experimental results demonstrate that CIRCLE not only effectively and efficiently repairs multiple programming languages in continual learning settings, but also achieves state-of-the-art performance (e.g., fixes 64 Defects4J bugs) with a single repair model. © 2022, CC BY-NC-SA.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Low Resolution Face Image Recognition Based on Consistent Discriminant Correlation Analysis with Weight Correction 1

引用

3rd International Conference on Artificial Intelligence Logic and Applications, AILA 2023

作者： Lin, Xiaoan Li, Meihua Pei, Jihong Zhao, Yang College of Electronics and Information Engineering Shenzhen University Guangdong Shenzhen China Guangdong Key Laboratory of Intelligent Information Processing Guangdong Shenzhen China Department of Computer Science City University of Hong Kong Hong Kong College of Computer Science and Software Engineering Shenzhen University Guangdong Shenzhen China

ISBN: (数字)9789819978694

ISBN: (纸本)9789819978687

Consistent Discriminant Correlation Analysis (CDCA) is an effective algorithm for dual-view learning. However, the importance of information from different samples and features may vary. In CDCA, the sample features from both views are equally weighted during training, which may not fully utilize the information contained in certain sample features. This can negatively impact the decision-making and predictive capabilities of the model. Additionally, CDCA is only applicable to dual-view data and cannot effectively utilize multi-view data. To address these issues, this paper extends CDCA to multi-view scenarios and proposes Consistent Discriminant Correlation Analysis with Weight Correction (CDCA-WC). The feature weighting approach used in this paper involves calculating the average weight of each feature using the ReliefF algorithm. The sample weighting method employed is based on a weighted loss function, where a larger weight indicates a stronger classification ability for the corresponding feature or sample. During the training process, CDCA-WC is used to obtain the feature subspace mappings for the training samples from multiple views. The data’s feature and sample dimensions are then adjusted based on their respective weights, and the adjusted data is used for a second round of training. During testing, the similarity between samples is measured using a KNN classifier. Experimental results on three publicly available face recognition datasets demonstrate that CDCA-WC can effectively improve the accuracy of low-resolution face image recognition. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2023.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Coupled Non-negative Matrix Factorization with Deep Part-Based Feature Learning for Low-Resolution Image Recognition 1

引用

3rd International Conference on Artificial Intelligence Logic and Applications, AILA 2023

作者： Wang, Jinxin Zhao, Yang Pei, Jihong Yang, Xuan College of Electronics and Information Engineering Shenzhen University Guangdong Shenzhen China Guangdong Key Laboratory of Intelligent Information Processing Guangdong Shenzhen China Department of Computer Science City University of Hong Kong Hong Kong College of Computer Science and Software Engineering Shenzhen University Guangdong Shenzhen China

ISBN: (数字)9789819978694

ISBN: (纸本)9789819978687

The existing low-resolution (LR) image recognition methods based on coupled relationship learning of high- and low-resolution images usually take similar feature extraction steps for both high- and low-resolution images. However, the high- and low-resolution features thus obtained may differ in terms of information content and information scale. This leads to a robust coupled relationship between the obtained high- and low-resolution images feature is difficult to be learned. Therefore, a coupled non-negative matrix factorization with a deep part-based feature learning method is proposed for the LR image recognition task. This method is divided into two main steps. Firstly, the depth non-negative matrix factorization method by graph convolution is used to obtain a robust depth underlying basis images of HR images for feature representation. Then the coupled relationship between the depth basis images feature of the HR images and the LR basis images feature is learned. Learning More Robust LR Basis images features using depth underlying features of HR images to assist LR images. Improve the expression of LR basis images of features. Experimental results show that the method can provide higher recognition performance. It outperforms existing image recognition methods in image recognition. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2023.

关键词： Image recognition

来源：评论

学校读者我要写书评

暂无评论

Distance- And velocity-based collision avoidance for time-varying formation control of second-order multi-agent systems

引用

IEEE Transactions on Circuits and Systems II: Express Briefs 2021年第4期68卷 1253-1257页

作者： Pang, Zhong-Hua Zheng, Chang-Bing Sun, Jian Han, Qing-Long Liu, Guo-Ping Key Laboratory of Fieldbus Technology and Automation of Beijing North China University of Technology Beijing100144 China State Key Laboratory of Intelligent Control and Decision of Complex Systems School of Automation Beijing Institute of Technology Beijing100081 China School of Software and Electrical Engineering Swinburne University of Technology MelbourneVIC3122 Australia Department of Artificial Intelligence and Automation Wuhan University Wuhan430072 China

This brief addresses the time-varying formation control problem with collision avoidance for second-order multi-agent systems. By taking both distances and velocities between agents into account, a novel collision avoidance scheme is proposed on the basis of conventional distance-based artificial potential field methods. Compared with the latter, the proposed scheme can more accurately determine possible collision situations and thus significantly reduce possible collision areas, which consequently not only can reduce energy consumption, but also has as few adverse effects on formation maintenance as possible. Then a time-varying formation control protocol is designed so as to achieve zero steady-state position and velocity formation tracking errors without collision. Finally, theoretical analysis, numerical demonstration, as well as comparative simulation are provided to verify the effectiveness of the proposed method. © 2004-2012 IEEE.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

Adversarial Attacks on Large Language Model-Based System and Mitigating Strategies: A Case Study on ChatGPT

引用

Security and Communication Networks 2023年第1期2023卷

作者： Liu, Bowen Xiao, Boao Jiang, Xutong Cen, Siyuan He, Xin Dou, Wanchun State Key Laboratory for Novel Software Technology Nanjing University Nanjing China Guangdong Laboratory of Artificial Intelligence and Digital Economy Shenzhen China School of Computer Science & Technology Nanjing University of Posts and Telecommunications Nanjing China College of Big Data and Intelligent Engineering Southwest Forestry University Kunming China

Machine learning algorithms are at the forefront of the development of advanced information systems. The rapid progress in machine learning technology has enabled cutting-edge large language models (LLMs), represented by GPT-3 and ChatGPT, to perform a wide range of NLP tasks with a stunning performance. However, research on adversarial machine learning highlights the need for these intelligent systems to be more robust. Adversarial machine learning aims to evaluate attack and defense mechanisms to prevent the malicious exploitation of these systems. In the case of ChatGPT, adversarial induction prompt can cause the model to generate toxic texts that could pose serious security risks or propagate false information. To address this challenge, we first analyze the effectiveness of inducing attacks on ChatGPT. Then, two effective mitigating mechanisms are proposed. The first is a training-free prefix prompt mechanism to detect and prevent the generation of toxic texts. The second is a RoBERTa-based mechanism that identifies manipulative or misleading input text via external detection models. The availability of this method is demonstrated through experiments. © 2023 Bowen Liu et al.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Towards Combating Frequency Simplicity-biased Learning for Domain Generalization

arXiv

引用

arXiv 2024年

作者： He, Xilin Hu, Jingyu Lin, Qinliang Luo, Cheng Xie, Weicheng Song, Siyang Khan, Muhammad Haris Shen, Linlin Computer Vision Institute School of Computer Science & Software Engineering Shenzhen University China Shenzhen Institute of Artificial Intelligence and Robotics for Society China Guangdong Provincial Key Laboratory of Intelligent Information Processing China University of Exeter United Kingdom Mohamed bin Zayed University of Artificial Intelligence United Arab Emirates

Domain generalization methods aim to learn transferable knowledge from source domains that can generalize well to unseen target domains. Recent studies show that neural networks frequently suffer from a simplicity-biased learning behavior which leads to over-reliance on specific frequency sets, namely as frequency shortcuts, instead of semantic information, resulting in poor generalization performance. Despite previous data augmentation techniques successfully enhancing generalization performances, they intend to apply more frequency shortcuts, thereby causing hallucinations of generalization improvement. In this paper, we aim to prevent such learning behavior of applying frequency shortcuts from a data-driven perspective. Given the theoretical justification of models’ biased learning behavior on different spatial frequency components, which is based on the dataset frequency properties, we argue that the learning behavior on various frequency components could be manipulated by changing the dataset statistical structure in the Fourier domain. Intuitively, as frequency shortcuts are hidden in the dominant and highly dependent frequencies of dataset structure, dynamically perturbating the over-reliance frequency components could prevent the application of frequency shortcuts. To this end, we propose two effective data augmentation modules designed to collaboratively and adaptively adjust the frequency characteristic of the dataset, aiming to dynamically influence the learning behavior of the model and ultimately serving as a strategy to mitigate shortcut learning. Code is available at AdvFrequency. © 2024, CC BY.

关键词： Contrastive Learning

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：