检索结果-内蒙古大学图书馆

9th International Conference on Dependable Systems and Their Applications, DSA 2022

作者： Chen, Jinfu Chen, Haibo Wu, Yiming Mao, Chengying Cai, Saihua School of Computer Science and Communication Engineering Jiangsu University Zhenjiang212013 China Jiangsu University Jiangsu Key Laboratory of Security Technology for Industrial Cyberspace Zhenjiang212013 China School of Software and IoT Engineering Jiangxi University of Finance and Economics Nanchang330013 China

ISBN: (数字)9781665488778

ISBN: (纸本)9781665488778

Adaptive Random Testing (ART) is a series of testing techniques proposed as an enhancement to random testing (RT). ART achieves better failure-detection than RT by distributing test cases more evenly throughout the input domain. However, the process of selecting test cases leads to significant computational costs and the increase of dimension leads to the decrease of effectiveness. In this paper, we propose a new ART approach to improve the efficiency and effectiveness of Fixed-size-Candidate-set ART (FSCS-ART) by applying a modified Metric-Memory tree and distance information entropy selection strategy, namely FSCS based on the modified MM-tree and information entropy (MMIE-FSCS). Simulations and empirical studies are conducted to examine the efficiency and effectiveness of the approach. The experimental results show that the approach reduces the computational cost of FSCS-ART and improves failure-detection effectiveness. © 2022 IEEE.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

TUBENCH: BENCHMARKING LARGE VISION-LANGUAGE MODELS ON TRUSTWORTHINESS WITH UNANSWERABLE QUESTIONS

arXiv

引用

arXiv 2024年

作者： He, Xingwei Zhang, Qianru Jin, A-Long Yuan, Yuan Yiu, Siu-Ming The University of Hong Kong Hong Kong Xi’an Jiaotong-Liverpool University China School of Computer Science and Engineering Beihang University Beijing China State Key Laboratory of Software Development Environment China Zhongguancun Laboratory China

Large Vision-Language Models (LVLMs) have achieved remarkable progress on visual perception and linguistic interpretation. Despite their impressive capabilities across various tasks, LVLMs still suffer from the issue of hallucination, which involves generating content that is incorrect or unfaithful to the visual or textual inputs. Traditional benchmarks, such as MME and POPE, evaluate hallucination in LVLMs within the scope of Visual Question Answering (VQA) using answerable questions. However, some questions are unanswerable due to insufficient information in the images, and the performance of LVLMs on such unanswerable questions remains underexplored. To bridge this research gap, we propose TUBench, a benchmark specifically designed to evaluate the reliability of LVLMs using unanswerable questions. TUBench comprises an extensive collection of high-quality, unanswerable questions that are meticulously crafted using ten distinct strategies. To thoroughly evaluate LVLMs, the unanswerable questions in TUBench are based on images from four diverse domains as visual contexts: screenshots of code snippets, natural images, geometry diagrams, and screenshots of statistical tables. These unanswerable questions are tailored to test LVLMs’ trustworthiness in code reasoning, commonsense reasoning, geometric reasoning, and mathematical reasoning related to tables, respectively. We conducted a comprehensive quantitative evaluation of 28 leading foundational models on TUBench, with Gemini-1.5-Pro, the top-performing model, achieving an average accuracy of 69.2%, and GPT-4o, the third-ranked model, reaching 66.7% average accuracy, in determining whether questions are answerable. Furthermore, our manual analysis of the model outputs reveals that: (1) Gemini-1.5-Pro provides both correct answers and explanations in only 41% of cases, and (2) hallucinations are the primary cause of error, accounting for 58.5% of the incorrect explanations generated by Gemini-1.5-Pro. These findings

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

Precise Timing over Beyond 5G Networks for Intelligent Transport in the Smart City

Precise Timing over Beyond 5G Networks for Intelligent Trans...

引用

IEEE International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC)

作者： Hongxing Li Guochu Shou Yaqiong Liu Yihong Hu State Key Laboratory of Networking and Switching Technology School of Computer Science (National Pilot Software Engineering School) Beijing University of Posts and Telecommunications Beijing China Beijing Key Laboratory of Network System Architecture and Convergence School of Information and Communication Engineering Beijing University of Posts and Telecommunications Beijing China

ISBN: (数字)9798350362244

ISBN: (纸本)9798350362251

The need for precise timing is increasing with the development of the smart city, and intelligent transport is a key application that often relies on the distribution of accurate timing. Existing time synchronization solutions cannot adequately meet the precise timing needs for practical applications in intelligent transportation. Global Navigation Satellite Systems (GNSS) signals, for instance, can be obstructed, weakened, or deflected in urban canyon environments. While certain sectors like telecommunications and smart grids have successfully adopted IEEE 1588 for high-precision time synchronization, its dependence on standalone networks and limited application within local area networks poses challenges when catering to the wide-ranging and mobile demands of intelligent transportation applications. This paper categorizes the time synchronization requirements of intelligent transport and proposes a time synchronization scheme over converged networks, which separates time transmission and precision compensation based on software-defined networking (SDN) principles, and makes it possible to provide precise timing for intelligent transport devices, including on-board units (OBUs) and roadside units (RSUs), over wired and wireless communication networks. Experimental results indicate that the proposed scheme achieves a relative time error of less than 1.2 microseconds over the converged networks.

关键词： Wireless communication Global navigation satellite system Accuracy Smart cities Transportation Telecommunications Smart grids Synchronization software defined networking Local area networks

来源：评论

学校读者我要写书评

暂无评论

MFN: Explainable DNA triple helixes Stabilized Design based on mCGR and flow network

MFN: Explainable DNA triple helixes Stabilized Design based ...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Xiaoru Wen Lijun Sun Lei Xie Yanfen Zheng Ben Cao Bin Wang Key Laboratory of Advanced Design and Intelligent Computing Ministry of Education School of Software Engineering Dalian University Dalian China School of Computer Science and Technology Dalian University of Technology Dalian China

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

DNA triple helix structure, as a highly specific gene targeting tool, enable gene regulation by precisely identifying and binding to target DNA sequences. However, the limits of design quality and efficiency affect their wide application in gene therapy. Therefore, in this paper, we propose an antiparallel DNA triple helixes design method-MFN based on matrix chaotic game representation (mCGR) and flow network. Leveraging the structural characteristics of DNA sequences, this method employs the mCGR algorithm to construct an initial matrix, generating a set of DNA sequences that conform to foundational constraints. Then, these sequences are mapped as stream network nodes to screen crosstalk structures by path search, and the whole process is observable and interpretable. Experimental results show that MFN significantly improves the design efficiency of triple helix structure and reduces crosstalk phenomenon. Wet experiments further verify the effectiveness of the method. In summary, MFN achieves an efficient and high-quality design of DNA triple helixes and provides a new idea for targeted gene therapy.

关键词： Scalability Design methodology DNA Crosstalk Genomics Games Reliability engineering Regulation Gene therapy Bioinformatics

来源：评论

学校读者我要写书评

暂无评论

Bilinear-Experts Network with Self-Adaptive Sampler for Long-Tailed Visual Recognition

SSRN

引用

SSRN 2024年

作者： Wang, Qin Wang, Xizhao Big Data Institute College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China The Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen518060 China

Long-tail distributed data hinders the practical application of state-of-the-art deep models in computer vision. Consequently, exclusive methodologies for handling the long-tailed problem are proposed, focusing on different hierarchies. For embedding hierarchy, existing works manually augment the diversity of tail-class features for specific datasets. However, prior knowledge about datasets is not always available for practical use, which brings unsatisfactory generalization ability in human fine-turned augmentation under such circumstances. To figure out this problem, we introduce a novel model named Bilinear-Experts Network (BENet) with Self-Adaptive Sampler (SAS). This model leverages model-driven perturbations to tail-class embeddings while preserving generalization capability on head classes through a designed bilinear experts system. The designed perturbations adaptively augment tail-class space and shift the class boundary away from the tail-class centers. Moreover, we surprisingly find that SAS automatically assigns more significant perturbations to specific tail classes rather than fewer-sample classes, which is against the common assumption that fewer-sample classes deserve greater attention. Also, experiments conducted across various long-tailed benchmarks validate the comparable efficacy of proposed BENet. © 2024, The Authors. All rights reserved.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Dynamic personalized federated learning with adaptive differential privacy 23

Dynamic personalized federated learning with adaptive differ...

引用

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Xiyuan Yang Wenke Huang Mang Ye National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence Hubei Key Laboratory of Multimedia and Network Communication Engineering School of Computer Science Hubei Luojia Laboratory Wuhan University Wuhan China

Personalized federated learning with differential privacy has been considered a feasible solution to address non-IID distribution of data and privacy leakage risks. However, current personalized federated learning methods suffer from inflexible personalization and convergence difficulties due to two main factors: 1) Firstly, we observe that the prevailing personalization methods mainly achieve this by personalizing a fixed portion of the model, which lacks flexibility. 2) Moreover, we further demonstrate that the default gradient calculation is sensitive to the widely-used clipping operations in differential privacy, resulting in difficulties in convergence. Considering that Fisher information values can serve as an effective measure for estimating the information content of parameters by reflecting the model sensitivity to parameters, we aim to leverage this property to address the aforementioned challenges. In this paper, we propose a novel federated learning method with Dynamic Fisher Personalization and Adaptive Constraint (FedDPA) to handle these challenges. Firstly, by using layer-wise Fisher information to measure the information content of local parameters, we retain local parameters with high Fisher values during the personalization process, which are considered informative, simultaneously prevent these parameters from noise perturbation. Secondly, we introduce an adaptive approach by applying differential constraint strategies to personalized parameters and shared parameters identified in the previous for better convergence. Our method boosts performance through flexible personalization while mitigating the slow convergence caused by clipping operations. Experimental results on CIFAR-10, FEMNIST and SVHN dataset demonstrate the effectiveness of our approach in achieving better performance and robustness against clipping, under personalized federated learning with differential privacy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Robust Heterogeneous Federated Learning under Data Corruption

Robust Heterogeneous Federated Learning under Data Corruptio...

引用

International Conference on computer Vision (ICCV)

作者： Xiuwen Fang Mang Ye Xiyuan Yang National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence Hubei Key Laboratory of Multimedia and Network Communication Engineering School of Computer Science Hubei Luojia Laboratory Wuhan University Wuhan China

Model heterogeneous federated learning is a realistic and challenging problem. However, due to the limitations of data collection, storage, and transmission conditions, as well as the existence of free-rider participants, the clients may suffer from data corruption. This paper starts the first attempt to investigate the problem of data corruption in the model heterogeneous federated learning framework. We design a novel method named Augmented Heterogeneous Federated Learning (AugHFL), which consists of two stages: 1) In the local update stage, a corruption-robust data augmentation strategy is adopted to minimize the adverse effects of local corruption while enabling the models to learn rich local knowledge. 2) In the collaborative update stage, we design a robust re-weighted communication approach, which implements communication between heterogeneous models while mitigating corrupted knowledge transfer from others. Extensive experiments demonstrate the effectiveness of our method in coping with various corruption patterns in the model heterogeneous federated learning setting.

关键词：

来源：评论

学校读者我要写书评

暂无评论

ProCQA: A Large-scale Community-based Programming Question Answering Dataset for Code Search

arXiv

引用

arXiv 2024年

作者： Li, Zehan Zhang, Jianfei Yin, Chuantao Ouyang, Yuanxin Rong, Wenge State Key Laboratory of Complex & Critical Software Environment Beihang University China Sino-French Engineer School Beihang University China School of Computer Science and Engineering Beihang University China

Retrieval-based code question answering seeks to match user queries in natural language to relevant code snippets. Previous approaches typically rely on pretraining models using crafted bi-modal and uni-modal datasets to align text and code representations. In this paper, we introduce ProCQA, a large-scale programming question answering dataset extracted from the StackOverflow community, offering naturally structured mixed-modal QA pairs. To validate its effectiveness, we propose a modality-agnostic contrastive pre-training approach to improve the alignment of text and code representations of current code language models. Compared to previous models that primarily employ bimodal and unimodal pairs extracted from CodeSearchNet for pre-training, our model exhibits significant performance improvements across a wide range of code retrieval benchmarks. © 2024, CC BY.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

A Web Service Classification Method Based on Graph Neural Network Knowledge Distillation 19

A Web Service Classification Method Based on Graph Neural Ne...

引用

2022 IEEE SmartWorld, 19th IEEE International Conference on Ubiquitous Intelligence and Computing, 2022 IEEE International Conference on Autonomous and Trusted Vehicles Conference, 22nd IEEE International Conference on Scalable Computing and Communications, 2022 IEEE International Conference on Digital Twin, 8th IEEE International Conference on Privacy Computing and 2022 IEEE International Conference on Metaverse, SmartWorld/UIC/ATC/ScalCom/DigitalTwin/PriComp/Metaverse 2022

作者： Huang, Hao Cao, Buqing Liu, Shanpeng Zhou, Dong Tang, Mingdong Xiao, Feng Hunan University of Science and Technology School of Computer Science and Engineering Hunan Key Laboratory of Service Computing and New Software Service Technology Xiangtan China Guangdong University of Foreign Studies School of Information Science and Technology Guangzhou China

ISBN: (纸本)9798350346558

With the increasing number of Web services, service discovery becomes a significant challenge, and service classification methods based on Graph Neural Network (GNN) are considered to be an efficient way for service discovery. However, these methods rarely exploit the structure-based and feature-based prior knowledge of services. To address this problem, this paper proposes a Web service classification method based on graph neural network knowledge distillation. In this method, firstly, it employs Word2Vec to extract the semantic feature vector from service descriptions, and then builds the service relationship network based on the shared tag annotation relationship of service. Secondly, a graph neural network knowledge distillation framework for Web service classification consisting of a teacher model and a student model is designed. The teacher model extracts the knowledge of GNN model, and the student model obtains the structure-based and feature-based prior knowledge of the service relationship network from teacher model by neighbor feature aggregation and feature transformation. Finally, GNN models (GCN, GAT, SAGE, APPNP, SGC, and GCNII) as teacher models for accuracy comparison are used in the experiment. From the experiment result, the classification accuracy of the student model is 11.64%23.10% higher than that of the teacher model. © 2022 IEEE.

关键词： Web services

来源：评论

学校读者我要写书评

暂无评论

E2VIDiff: Perceptual Events-to-Video Reconstruction using Diffusion Priors

arXiv

引用

arXiv 2024年

作者： Liang, Jinxiu Yu, Bohan Yang, Yixin Han, Yiming Shi, Boxin National Key Laboratory for Multimedia Information Processing National Engineering Research Center of Visual Technology School of Computer Science Peking University China School of Software and Microelectronics Peking University China

Event cameras, mimicking the human retina, capture brightness changes with unparalleled temporal resolution and dynamic range. Integrating events into intensities poses a highly ill-posed challenge, marred by initial condition ambiguities. Traditional regression-based deep learning methods fall short in perceptual quality, offering deterministic and often unrealistic reconstructions. In this paper, we introduce diffusion models to events-to-video reconstruction, achieving colorful, realistic, and perceptually superior video generation from achromatic events. Powered by the image generation ability and knowledge of pretrained diffusion models, the proposed method can achieve a better trade-off between the perception and distortion of the reconstructed frame compared to previous solutions. Extensive experiments on benchmark datasets demonstrate that our approach can produce diverse, realistic frames with faithfulness to the given events. © 2024, CC BY-NC-ND.

关键词： Cameras

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：