检索结果-内蒙古大学图书馆

37th Conference on Neural Information Processing Systems, NeurIPS 2023

作者： Chen, Yanbo Liu, Weiwei School of Computer Science Wuhan University National Engineering Research Center for Multimedia Software Wuhan University Institute of Artificial Intelligence Wuhan University Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University

ISBN: (纸本)9781713899921

Transfer-based attacks [1] are a practical method of black-box adversarial attacks in which the attacker aims to craft adversarial examples from a source model that is transferable to the target model. Many empirical works [2-6] have tried to explain the transferability of adversarial examples from different angles. However, these works only provide ad hoc explanations without quantitative analyses. The theory behind transfer-based attacks remains a mystery. This paper studies transfer-based attacks under a unified theoretical framework. We propose an explanatory model, called the manifold attack model, that formalizes popular beliefs and explains the existing empirical results. Our model explains why adversarial examples are transferable even when the source model is inaccurate as observed in Papernot et al. [7]. Moreover, our model implies that the existence of transferable adversarial examples depends on the "curvature" of the data manifold, which further explains why the success rates of transfer-based attacks are hard to improve. We also discuss our model's expressive power and applicability. © 2023 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Adversarial Self-Training Improves Robustness and Generalization for Gradual Domain Adaptation 37

Adversarial Self-Training Improves Robustness and Generaliza...

引用

37th Conference on Neural Information Processing Systems, NeurIPS 2023

作者： Shi, Lianghe Liu, Weiwei School of Computer Science Wuhan University National Engineering Research Center for Multimedia Software Wuhan University Institute of Artificial Intelligence Wuhan University Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University

ISBN: (纸本)9781713899921

Gradual Domain Adaptation (GDA), in which the learner is provided with additional intermediate domains, has been theoretically and empirically studied in many contexts. Despite its vital role in security-critical scenarios, the adversarial robustness of the GDA model remains unexplored. In this paper, we adopt the effective gradual self-training method and replace vanilla self-training with adversarial self-training (AST). AST first predicts labels on the unlabeled data and then adversarially trains the model on the pseudo-labeled distribution. Intriguingly, we find that gradual AST improves not only adversarial accuracy but also clean accuracy on the target domain. We reveal that this is because adversarial training (AT) performs better than standard training when the pseudo-labels contain a portion of incorrect labels. Accordingly, we first present the generalization error bounds for gradual AST in a multiclass classification setting. We then use the optimal value of the Subset Sum Problem to bridge the standard error on a real distribution and the adversarial error on a pseudo-labeled distribution. The result indicates that AT may obtain a tighter bound than standard training on data with incorrect pseudo-labels. We further present an example of a conditional Gaussian distribution to provide more insights into why gradual AST can improve the clean accuracy for GDA. © 2023 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Improving Speech Enhancement by Cross- and Sub-band Processing with State Space Model

Improving Speech Enhancement by Cross- and Sub-band Processi...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Li, Jizhen Tu, Weiping Yang, Yuhong Xu, Xinmeng Zhang, Yiqun Ren, Yanzhen NERCMS School of Computer Science Hubei Luojia Laboratory Wuhan University China Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University China School of Cyber Science and Engineering Wuhan University China

ISBN: (纸本)9798350368741

Recently, the state space model (SSM) represented by Mamba has shown remarkable performance in long-term sequence modeling tasks, including speech enhancement. However, due to substantial differences in sub-band features, applying the same SSM to all sub-bands limits its inference capability. Additionally, when processing each time frame of the time-frequency representation, the SSM may forget certain high-frequency information of low energy, making the restoration of structure in the high-frequency bands challenging. For this reason, we propose Cross- and Sub-band Mamba (CSMamba). To assist the SSM in handling different sub-band features flexibly, we propose a band split block that splits the full-band into four sub-bands with different widths based on their information similarity. We then allocate independent weights to each subband, thereby reducing the inference burden on the SSM. Furthermore, to mitigate the forgetting of low-energy information in the high-frequency bands by the SSM, we introduce a spectrum restoration block that enhances the representation of the cross-band features from multiple perspectives. Experimental results on the DNS Challenge 2021 dataset demonstrate that CSMamba outperforms several state-of-the-art (SOTA) speech enhancement methods in three objective evaluation metrics with fewer parameters. © 2025 IEEE.

关键词： band split spectrum restoration speech enhancement state space model

来源：评论

学校读者我要写书评

暂无评论

A Deep Understanding Video Q&A System for Film Education in Acting Department

A Deep Understanding Video Q&A System for Film Education in ...

引用

2023 International Conference on Intelligent Education and Intelligent Research, IEIR 2023

作者： Wu, Zhengqian Li, Ruizhe Guo, Jiahao Wang, Zhongyuan Liang, Chao Hubei Key Laboratory of Multimedia and Network Communication Engineering School of Computer Science China National Engineering Research Center for Multimedia Software School of Computer Science China Wuhan University School of Computer Science China

ISBN: (纸本)9798350342895

Recently, advancements in artificial intelligence technology have greatly influenced the field of education, particularly in the area of intelligent homework assistance. However, current approaches are primarily designed for procedural and logical tasks and often lack comprehension abilities. This limitation is particularly evident when it comes to multi-hop and continuous tasks. To address this challenge, the integration of Large Language Model (LLM) has significantly enhanced the capability of AI systems to handle multi-hop and highly interconnected inputs. In this study, we focus on the learning needs of students in Acting Department, specifically their study of movies and the significance of classic movie videos in their learning process. However, assessing deep comprehension of classic movies poses its own challenges. To overcome these challenges, we develop a quiz system utilizing Knowledge Graphs (KG) and LLM to facilitate a deeper understanding of classic films. The generation of video quiz pairs is achieved through the use of Automatic Speech Recognition (ASR) technology, which leverages movie subtitles for question generation. For answering these questions, we employ techniques KG and LLM to process questions and retrieve corresponding answers. The proposed method achieves good performance in Deep Video Understanding (DVU) task of NIST TRECVID, demonstrating its effectiveness. © 2023 IEEE.

关键词： Motion pictures

来源：评论

学校读者我要写书评

暂无评论

DP-GenFL: a local differentially private federated learning system through generative data

引用

Science China(Information Sciences) 2023年第8期66卷 275-276页

作者： Jun LI Kang WEI Chuan MA Feng SHU School of Electronic and Optical Engineering Nanjing University of Science and Technology Zhejiang Lab Key Laboratory of Computer Network and Information Integration (Southeast University) Ministry of Education School of Information and Communication Engineering Hainan University

With the rapid development of the Internet of Things(Io T),the amount of data from intelligent devices is propagating at unprecedented scales. Meanwhile, machine learning(ML),which relies heavily on such data, is revolutionizing many aspects of our lives [1]. However, conventional centralized ML offers little scalability for efficiently processing this huge amount of data.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

RCache: A Read-Intensive Workload-Aware Page Cache for NVM Filesystem

引用

ZTE communications 2023年第1期21卷 89-94页

作者： TU Yaofeng ZHU Bohong YANG Hongzhang HAN Yinjun SHU Jiwu State Key Laboratory of Mobile Network and Mobile Multimedia Technology Shenzhen 518055China ZTE Corporation Shenzhen 518057China Tsinghua University Beijing 100084China

Byte-addressable non-volatile memory(NVM),as a new participant in the storage hierarchy,gives extremely high performance in storage,which forces changes to be made on current filesystem *** cache,once a significant mechanism filling the performance gap between Dynamic Random Access Memory(DRAM)and block devices,is now a liability that heavily hinders the writing performance of NVM *** state-of-the-art NVM filesystems leverage the direct access(DAX)technology to bypass the page cache ***,the DRAM still provides higher bandwidth than NVM,which prevents skewed read workloads from benefiting from a higher bandwidth of the DRAM and leads to sub-optimal performance for the *** this paper,we propose RCache,a readintensive workload-aware page cache for NVM *** from traditional caching mechanisms where all reads go through DRAM,RCache uses a tiered page cache design,including assigning DRAM and NVM to hot and cold data separately,and reading data from both *** avoid copying data to DRAM in a critical path,RCache migrates data from NVM to DRAM in a background ***,RCache manages data in DRAM in a lock-free manner for better latency and *** on Intel Optane Data Center(DC)Persistent Memory Modules show that,compared with NOVA,RCache achieves 3 times higher bandwidth for read-intensive workloads and introduces little performance loss for write operations.

关键词： storage system file system persistent memory

来源：评论

学校读者我要写书评

暂无评论

Large-scale Satellite Optical network Simulation Architecture and Performance Evaluation

Large-scale Satellite Optical Network Simulation Architectur...

引用

2024 Asia communications and Photonics Conference, ACP 2024 and International Conference on Information Photonics and Optical communications, IPOC 2024

作者： Wang, Xinjun Zhang, Zhenrong Zhu, Kangqi Hua, Nan School of Computer Electronic and Information Guangxi Key Laboratory of Multimedia Communications and Network Technology Guangxi University Nanning China Department of Electronic Engineering Tsinghua University Beijing China

We evaluate the accuracy and performance of different simulation modes in MegaStarSim, analyze end-to-end routing strategies in large-scale satellite optical networks, and assess link quality across various inter-sate... 详细信息

ISBN: (纸本)9798350379266

关键词： Satellite links

来源：评论

学校读者我要写书评

暂无评论

DiriNet:An Estimation network for Spectral Response Function and Point Spread Function

引用

Journal of Beijing Institute of technology 2024年第4期33卷 287-297页

作者： Ting Hu Siyuan Cheng Chang Liu Beijing Key Laboratory of Computational Intelligence and Intelligent System Faculty of Information TechnologyBeijing University of TechnologyBeijing 100124China Space Star Technology Co. LtdBeijing 100086China Research Institute of Intelligent Wire-less Communication Network Technology Faculty of Information TechnologyBeijing University of TechnologyBeijing 100124China

Hyper-and multi-spectral image fusion is an important technology to produce hyper-spectral and hyper-resolution images,which always depends on the spectral response function andthe point spread ***,few works have been payed on the estimation of the two degra-dation *** learn the two functions from image pairs to be fused,we propose a Dirichletnetwork,where both functions are properly ***,the spatial response function isconstrained with positivity,while the Dirichlet distribution along with a total variation is imposedon the point spread *** the best of our knowledge,the neural network and the Dirichlet regularization are exclusively investigated,for the first time,to estimate the degradation *** image degradation and fusion experiments demonstrate the effectiveness and superiority of theproposed Dirichlet network.

关键词： Dirichlet network point spread function spectral response function hyper-spectralimage multi-spectral image

来源：评论

学校读者我要写书评

暂无评论

A throughput and priority optimization strategy for high density healthcare IoT

引用

Intelligent and Converged networks 2025年第1期6卷 41-52页

作者： Zhenlang Su Junyu Ren Yeheng Huang Yang Liao Tuanfa Qin School of Computer Electronic and InformationGuangxi UniversityNanning 530004China School of Physics and Electronic Information Guangxi Minzu UniversityNanning 530006China School of Computer Electronic and Information and the Guangxi Key Laboratory of Multimedia Communications and Network TechnologyGuangxi UniversityNanning 530004China

In the field of wireless body area networks(WBANs),for solving the complex interference problem of inter-WBANs,a density-based adaptive optimization strategy(DAOS)is proposed in this ***,the complex interference problem among WBANs is converted into a distance-based graph coloring model,then time division multiple access and a two-level split clustering methods are adopted to allocate initial time slots for ***,the particle swarm optimization algorithm is used to optimize the time slot of each node for maximizing the *** simulate the scenario on MATLAB *** results show that compared with the traditional scheme in high-density healthcare Internet of Things(IoT)scenarios,DAOS has obvious advantages compared with three comparison strategies of faster convergence rate of 48.94%,60.76%,and 96.82%,and higher throughput of 5.60%,8.08%,and 8.05%in traffic priorities 7 to 4.

关键词： wireless body area networks(WBANs) cluster graph coloring particle swarm optimization(PSO)

来源：评论

学校读者我要写书评

暂无评论

Reliability Research on micro bump and c4bump in Large-Size 2.5D FCBGA

Reliability Research on micro bump and c4bump in Large-Size ...

引用

2023 China Semiconductor technology International Conference, CSTIC 2023

作者： Li, Xiang Wang, Zhuqiu He, Xiao Yang, Dan Mei, Na State Key Laboratory of Mobile Network and Mobile Multimedia Technology Shenzhen518055 China Sanechips Department of Reliability Engineering Shenzhen518055 China

ISBN: (纸本)9798350311006

The electronic components using flip chip bonding technology have high pin density, good thermal conductivity and excellent electrical performance, and are widely used in the telecommunications field. In this paper, -5000mm2 area 2. 5D FCBGA is taken as the research object, and the failure phenomenon of its key interconnect structure under temperature cycle is tested and simulated. In the test, it was found that ubump failed earlier than c4bump, and there were underfill delamination on both sides of the copper pillar with different bump structures. Then, the impact of underfill delamination on the stress of the bump is studied through finite element analysis, and the failure risks of the two kinds of bump structures are compared. Finally, it is proposed that proper underfill materials can reduce the failure risk of bump. © 2023 IEEE.

关键词： Thermal conductivity

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：