检索结果-内蒙古大学图书馆

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Yin, Jia-Li Wang, Weijian Lyhwa Lin, Wei Liu, Ximeng Fujian Province Key Laboratory of Information Security and Network Systems Fuzhou350108 China College of Computer and Data Science Fuzhou University Fuzhou350118 China Fujian Provincial Key Laboratory of Big Data Mining and Applications Fuzhou350118 China College of Computer Science and Mathematics Fujian University of Technology Fuzhou350118 China Lion Rock Labs of Cyberspace Security CTIHE Hong Kong

ISBN: (纸本)157735897X

Backdoor attacks and adversarial attacks are two major security threats to deep neural networks (DNNs), with the former one is a training-time data poisoning attack that aims to implant backdoor triggers into models by injecting trigger patterns into training samples, and the latter one is a testing-time attack trying to generate adversarial examples (AEs) from benign images to mislead a well-trained model. While previous works generally treat these two attacks separately, the inherent connection between these two attacks is rarely explored. In this paper, we focus on bridging backdoor and adversarial attacks and observe two intriguing phenomena when applying adversarial attacks on an infected model implanted with backdoors: 1) the sample is harder to be turned into an AE when the trigger is presented;2) the AEs generated from backdoor samples are highly likely to be predicted as its true labels. Inspired by these observations, we proposed a novel backdoor defense method, dubbed Adversarial-Inspired Backdoor Defense (AIBD), to isolate the backdoor samples by leveraging a progressive top-q scheme and break the correlation between backdoor samples and their target labels using adversarial labels. Through extensive experiments on various datasets against six state-of-the-art backdoor attacks, the AIBD-trained models on poisoned data demonstrate superior performance over the existing defense methods. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

FR2Seg: Continual Segmentation Across Multiple Sites via Fourier Style Replay and Adaptive Consistency Regularization 39

FR2Seg: Continual Segmentation Across Multiple Sites via Fou...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Xu, Cheng Zhang, Weiwen Zhang, Hongrui Xu, Xuemiao Zhang, Huaidong Zou, Jing Qin, Jing South China University of Technology China The Hong Kong Polytechnic University Hong Kong Guangdong Engineering Center for Large Model and GenAI Technology China State Key Laboratory of Subtropical Building Science China Ministry of Education Key Laboratory of Big Data and Intelligent Robot China Guangdong Provincial Key Lab of Computational Intelligence and Cyberspace Information China

ISBN: (纸本)157735897X

In clinical imaging, medical segmentation networks typically require continually adapting to new data from multiple sites over time, as aggregating all data for learning at once can be impractical due to storage limitations and privacy concerns. However, existing methods basically overlook domain-specific characteristics and fall short of adequately capturing domain-invariant knowledge during continual learning, leading to undesired catastrophic forgetting of previous sites and inferior generalization to new sites. To tackle this issue, this paper introduces FR2Seg, to sufficiently exploit both domain-specific and domain-invariant knowledge for efficient continual learning with the aid of low-frequency cues. For the former aspect, we propose a Fourier style replay module to synthesize pseudo images with old-site styles for data augmentation during new-site training, effectively preventing catastrophic forgetting without sacrificing data privacy. For the latter, we present a Fourier adaptive consistency regularization to identify and constrain the optimization of domain-invariant parameters with explicit awareness of knowledge transferability across sites, ensuring excellent generalizability to new sites. Experimental results on two public datasets confirm our method's superiority over existing state-of-the-art continual learning methods. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

FedNHN: Generated data-driven Personalized Federated Learning with Heterogeneous data

FedNHN: Generated Data-driven Personalized Federated Learnin...

引用

2024 IEEE Global Communications Conference, GLOBECOM 2024

作者： Sun, Jialong Dong, Jing Su, Zhanye Zhang, Wenchao Zhang, Kejia Heilongjiang University School of Data Science and Technology Harbin150080 China Nanjing Audit University School of Mathematics Nanjing211815 China Heilongjiang University School of Mathematical Science Harbin150080 China Guizhou University State Key Laboratory of Public Big Data Guiyang550000 China

ISBN: (纸本)9798350351255

The emergence of heterogeneous data brings new challenges to Federated Learning (FL). Unlike homogeneous datasets, heterogeneous data are inherently characterized by sample domain center offsets, which makes traditional federated learning often suffer from poor model results due to catastrophic forgetting and increased communication costs when dealing with such data. To address this problem, we introduce FedNHN, a novel Personalized Federated Learning (PFL) algorithm. FedNHN regularizes the local training loss by quantifying the disparity between the local and global models to generate pseudo-data feature representations. Specifically, it generates two types of pseudo-data: Highly Pseudo and Perturbed data, by employing the Fast Gradient Sign Method (FGSM) with both the global model and local data. Furthermore, FedNHN leverages the Hilbert-Schmidt Independence Criterion (DN-HSIC) to assess the distances between the feature representations of the generated data by the global model and the local model, respectively, and utilizes the Centered Kernel Alignment (CKA) similarity based on DN-HSIC to regulate the local training loss effectively. Our mathematical analyses show that our design can maintain the utility of the federated model under heterogeneous data, and extensive evaluations on three classical datasets illustrate the effectiveness and performance of our proposed implementation. © 2024 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

A Graph Sequence Generator and Multi-head Self-attention Mechanism based Knowledge Graph Reasoning Architecture 26

A Graph Sequence Generator and Multi-head Self-attention Mec...

引用

26th International Conference on Computer Supported Cooperative Work in Design, CSCWD 2023

作者： Wu, Yuejia Zhou, Jian-Tao College of Computer Science Inner Mongolia University Hohhot China National & Local Joint Engineering Research Center Intelligent Info. Proc. Technology for Mongolian Engineering Research Center of Ecological Big Data Ministry of Education Hohhot China Inner Mongolia Engineering Laboratory for Cloud Computing and Service Software Inner Mongolia Key Laboratory of Social Computing and Data Processing Hohhot China Inner Mongolia Key Laboratory of Discipline Inspection and Supervision Big Data Inner Mongolia Engineering Laboratory for Big Data Analysis Technology Hohhot China

ISBN: (纸本)9798350331684

Knowledge Graph (KG) is an essential research direction that involves storing and managing knowledge data, but its incompleteness and sparsity hinder its development in various applications. Knowledge Graph Reasoning (KGR) is an effective method to solve this limitation via reasoning missing knowledge based on existing knowledge. The graph Convolution Network (GCN) based method is one of the state-of-the-art approaches to this work. However, there are still some problems, such as the insufficient ability to perceive graph structure and the poor effect of learning data features which may limit the reasoning accuracy. This paper proposes a KGR architecture based on a graph sequence generator and multi-head self-attention mechanism, named GaM-KGR, to improve the above problems and enhance prediction accuracy. Specifically, the GaM-KGR first introduces the graph generation model into the field of KGR for graph representation learning to obtain the hidden features in the data so that enhancing the reasoning effect and then embeds the generated graph sequence into the multi-head self-attention mechanism for subsequent processing to improve the graph structure perception ability of the proposed architecture, so that it can process the graph structure data more appropriately. Extensive experimental results show that the GaM-KGR architecture can achieve the state-of-the-art prediction results of current GCN-based models. © 2023 IEEE.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Face anti-spoofing based on multi-modal and multi-scale features fusion

引用

The Journal of China Universities of Posts and Telecommunications 2022年第6期29卷 73-82页

作者： Kong Chao Ou Weihua Gong Xiaofeng Li Weian Han Jie Yao Yi Xiong Jiahao School of Big Data and Computer Science Guizhou Normal UniversityGuiyang 550025China Special Key Laboratory of Artificial Intelligence and Intelligent Control of Guizhou Province Guizhou Institute of TechnologyGuiyang 550003China Guizhou Science and Technology Information Center Department of Science and Technology of Guizhou ProvinceGuiyang 550002China

Face anti-spoofing is used to assist face recognition system to judge whether the detected face is real face or fake face. In the traditional face anti-spoofing methods, features extracted by hand are used to describe the difference between living face and fraudulent face. But these handmade features do not apply to different variations in an unconstrained environment. The convolutional neural network(CNN) for face deceptions achieves considerable results. However, most existing neural network-based methods simply use neural networks to extract single-scale features from single-modal data, while ignoring multi-scale and multi-modal information. To address this problem, a novel face anti-spoofing method based on multi-modal and multi-scale features fusion(MMFF) is proposed. Specifically, first residual network(Resnet)-34 is adopted to extract features of different scales from each modality, then these features of different scales are fused by feature pyramid network(FPN), finally squeeze-and-excitation fusion(SEF) module and self-attention network(SAN) are combined to fuse features from different modalities for classification. Experiments on the CASIA-SURF dataset show that the new method based on MMFF achieves better performance compared with most existing methods.

关键词： face anti-spoofing multi-modal fusion multi-scale fusion self-attention network(SAN) feature pyramid network(FPN)

来源：评论

学校读者我要写书评

暂无评论

Accurate Thin Film Defect Detection Using Transformer and Guided Feature Fusion

引用

Pattern Recognition and Image Analysis 2025年第2期35卷 129-140页

作者： Yang, Tao Liu, Qinghuan Wang, Huiyan Li, Shengjie School of Computer Science and Technology Zhejiang Gongshang University Hangzhou China Zhejiang Key Laboratory of Big Data and Future E-Commerce Technology Hangzhou China

Although deep neural networks have made significant advancements in machine vision, detecting small defects on thin films using deep neural networks remains a challenging task. The shape and size of the target defect are often uncertain, while environmental conditions such as illumination and camera vibration can affect image quality. Additionally, the defect detection model needs to process images at high speed, further adding to the complexity of the task. To address these challenges, this paper proposes a novel approach by utilizing the “one-stage” object detection method as the backbone structure, while also enhancing global representation and multilevel feature fusion for improved defect detection. Evaluation results demonstrate that the proposed network structure not only performs well on our datasets but also outperforms other state-of-the-art object detection methods when tested on public datasets.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Perturbative QCD evidence for spin-2 particles in the di-J/ψ resonances

引用

science Bulletin 2025年第12期70卷 1915-1917页

作者： Zhang, Hong-Fei Ma, Yan-Qing Sang, Wen-Long College of Big Data Statistics Guizhou University of Finance and Economics Guiyang550025 China Research Centre of Big-data Corpus & Language Projects School of Foreign Languages Guizhou University of Finance and Economics Guiyang550025 China School of Physics and State Key Laboratory of Nuclear Physics and Technology Peking University Beijing100871 China Center for High Energy Physics Peking University Beijing100871 China Collaborative Innovation Center of Quantum Matter Beijing100871 China School of Physical Science and Technology Southwest University Chongqing400700 China

来源：评论

学校读者我要写书评

暂无评论

A Trajectory Tracking System for Zebrafish Based on Embedded Edge Artificial Intelligence 29

A Trajectory Tracking System for Zebrafish Based on Embedded...

引用

29th IEEE International Conference on Parallel and Distributed Systems, ICPADS 2023

作者： Zang, Chuanhao Dong, Anming Yu, Jiguo School of Computer Science and Technology Jinan China Big Data Institute Jinan China Shandong Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Computer Networks Jinan China

ISBN: (纸本)9798350330717

Trajectory tracking of zebrafish is an important requirement in studying neurological disorders and developing new psychoactive drug. However, many challenges emerge for stable tracking, since zebrafish are similar in appearance, occlusion, agile, non-linear in moving and easy to swarm, all of which will lead to mistrack for multiple fish. And there is no precedent for tracking zebrafish through embedded edge artificial intelligence device. To overcome these difficulties, we present a tracking system for zebrafish based on RK3588-S. First, We construct an embedded edge AI hardware system consisting of two cameras driven by the RK3588-S, one for the front view and the other for top view of the fish. Then, we develop a 2D tracking algorithm based on YOLOv5 and the Observation-Centric Simple online and real-time tracking (OC-SORT) algorithm, which are transplanted to the RK3588-S for tracking the top and front views of the fish at the edge device. Compared with the previous methods, our method has fewer ID exchanges and highly real-time. Moreover, we apply the MQTT mechanism to establish communication links between the edge and the cloud to reliably transmit data to the cloud. The correspondence between cloud server and embedded AI is 1: N. Finally, we design a multi-view data fusion association algorithm to fuse the data of the two views in the cloud, which are further utilized to build the 3D tracklets of the zebrafish. © 2023 IEEE.

关键词： A Tracking System for Zebrafish Embedded edge artificial intelligence RK3588-S Zebrafish

来源：评论

学校读者我要写书评

暂无评论

Research on Question Matching of Operation System FAQ with Knowledge Graph and Image Information 3

Research on Question Matching of Operation System FAQ with K...

引用

2022 3rd International Conference on Computer Information and big data Applications, CIBDA 2022

作者： Zhao, Haomin Liu, Yu Gu, Jinguang College of Computer Science and Technology Wuhan University of Science and Technology Hubei Wuhan China Key Laboralory of Intelligent Information Processing and Real-time Industrial System in Hubei Province Hubei Wuhan China Institute of Big Data Science and Engineering Wuhan University of Science and Technology Hubei Wuhan China

ISBN: (纸本)9783800758760

The FAQ system is to match the questions asked by the user with the questions in the FAQ library, and subsequently return the answers to the questions according to the smenatic similarity between questions. The existing matching methods of question pair are not specially designated for the OS domain and do not incorporate domain knowledge. The screenshots of Operating System provided by user usually contain important information, which can be uesed to improve the effectiveness of question matching method. In this paper, we evaluate the important of text in image with the highlighted evaluation, location evaluation, and text evaluation, and filter out important text for question matching. In order to use knowledge of Operation System, we introduce a pretraining model incorporating the domain knowledge that can be used for problem matching. In the experiment, the method with knowledge graph and image information can fully improve the accuracy rate, recall rate and F1 score of the matching reuslts compared to the mainstream method. © VDE VERLAG GMBH - Berlin - Offenbach.

关键词： Domain Knowledge

来源：评论

学校读者我要写书评

暂无评论

Polynomial-Time Assignment-Based Cell Association with Generic Utility Functions

引用

China Communications 2022年第9期19卷 214-228页

作者： Lusheng Wang Chao Fang Hai Lin Min Peng Caihong Kai Key Laboratory of Knowledge Engineering with Big Data Ministry of Education.School of Computer Science and Information EngineeringHefei University of TechnologyHefei 230601China Key Laboratory of Aerospace Information Security and Trusted Computing Ministry of Education.School of Cyber Science and EngineeringWuhan UniversityWuhan 430072China

Cell association is a significant research issue in future mobile communication systems due to the unacceptably large computational time of traditional *** article proposes a polynomial-time cell association scheme which not only completes the association in polynomial time but also fits for a generic optimization objective *** the one hand,traditional cell association as a non-deterministic polynomial(NP)hard problem with a generic utility function is heuristically transformed into a 2-dimensional assignment optimization and solved by a certain polynomial-time algorithm,which significantly saves computational *** the other hand,the scheme jointly considers utility maximization and load balancing among multiple base stations(BSs)by maintaining an experience pool storing a set of weighting factor values and their corresponding *** an association optimization is required,a suitable weighting factor value is taken from the pool to calculate a long square utility matrix and a certain polynomial-time algorithm will be applied for the *** with several representative schemes,the proposed scheme achieves large system capacity and high fairness within a relatively short computational time.

关键词： mobile communication system 2-dimensional assignment problem hungarian algorithm fairness cell association

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：