检索结果-内蒙古大学图书馆

International Conference on Software Engineering (ICSE)

作者： Chenxi Zhang Zhen Dong Xin Peng Bicheng Zhang Miao Chen Fudan University China Shanghai Collaborative Innovation Center of Intelligent Visual Computing China School of Computer Science and Shanghai Key Laboratory of Data Science Fudan University China

ISBN: (数字)9798400702174

ISBN: (纸本)9798350382143

Modern microservice systems have become increasingly complicated due to the dynamic and complex interactions and runtime environment. It leads to the system vulnerable to performance issues caused by a variety of reasons, such as the runtime environments, communications, coordinations, or implementations of services. Traces record the detailed execution process of a request through the system and have been widely used in performance issues diagnosis in microservice systems. By identifying the execution processes and attribute value combinations that are common in anomalous traces but rare in normal traces, engineers may localize the root cause of a performance issue into a smaller scope. However, due to the complex structure of traces and the large number of attribute combinations, it is challenging to find the root cause from the huge search space. In this paper, we propose TraceContrast, a trace-based multidimensional root cause localization approach. TraceContrast uses a sequence representation to describe the complex structure of a trace with attributes of each span. Based on the representation, it combines contrast sequential pattern mining and spectrum analysis to localize multidimensional root causes efficiently. Experimental studies on a widely used microservice benchmark show that TraceContrast outperforms existing approaches in both multidimensional and instance-dimensional root cause localization with significant accuracy advantages. Moreover, Trace-Contrast is efficient and its efficiency can be further improved by parallel execution.

关键词： Location awareness Runtime environment Accuracy Microservice architectures Benchmark testing data mining Spectral analysis

来源：评论

学校读者我要写书评

暂无评论

Explainable Synthetic Image Detection through Diffusion Timestep Ensembling

arXiv

引用

arXiv 2025年

作者： Wu, Yixin Zhang, Feiran Shi, Tianyuan Yin, Ruicheng Wang, Zhenghua Gan, Zhenliang Wang, Xiaohua Lv, Changze Zheng, Xiaoqing Huang, Xuanjing School of Computer Science Fudan University Shanghai Key Laboratory of Intelligent Information Processing Shanghai China

Recent advances in diffusion models have enabled the creation of deceptively real images, posing significant security risks when misused. In this study, we reveal that natural and synthetic images exhibit distinct differences in the high-frequency domains of their Fourier power spectra after undergoing iterative noise perturbations through an inverse multi-step denoising process, suggesting that such noise can provide additional discriminative information for identifying synthetic images. Based on this observation, we propose a novel detection method that amplifies these differences by progressively adding noise to the original images across multiple timesteps, and train an ensemble of classifiers on these noised images. To enhance human comprehension, we introduce an explanation generation and refinement module to identify flaws located in AI-generated images. Additionally, we construct two new datasets, GenHard and GenExplain, derived from the GenImage benchmark, providing detection samples of greater difficulty and high-quality rationales for fake images. Extensive experiments show that our method achieves state-of-the-art performance with 98.91% and 95.89% detection accuracy on regular and harder samples, increasing a minimal of 2.51% and 3.46% compared to baselines. Furthermore, our method also generalizes effectively to images generated by other diffusion models. Our code and datasets will be made publicly available. Copyright © 2025, The Authors. All rights reserved.

关键词： Inverse problems

来源：评论

学校读者我要写书评

暂无评论

Towards Exploratory Query Optimization for Template-Based SQL Workloads 40

Towards Exploratory Query Optimization for Template-Based SQ...

引用

40th IEEE International Conference on data Engineering, ICDE 2024

作者： Feng, Jieming Li, Zhanhuai Chen, Qun School of Computer Science and Engineering Northwestern Polytechnical University Shaanxi Xi'an China Key Laboratory of Big Data Storage and Management Ministry of Industry and Information Technology Northwestern Polytechnical University Shaanxi Xi'an China

ISBN: (纸本)9798350317152

SQL query optimization aims to choose an optimal Query Execution Plan (QEP) for a query. The existing optimizers usually choose the plan with the minimal execution cost. However, in some real scenarios (e.g., cloud OLAP), it is a business imperative to minimize the cost of an entire workload. Unfortunately, the greedy optimizers are prone to generating execution plans that are only suboptimal from the workload perspective. In this paper, we propose a novel QEP optimization approach for template-based SQL that aims to minimize the execution cost of an entire workload instead of individual queries. While choosing an execution plan for a query, the proposed approach considers a plan's impact on future query execution as well as its own execution cost. We first define an exploratory metric, Plan Exploration Value (PEV), to measure a plan's potential benefit to future query execution. Then, we model exploratory plan selection as an optimization problem with cost constraints, and present an efficient algorithm based on dynamic programming for its solution. Finally, we evaluate the performance of the proposed approach by a comparative study on benchmark workloads. Our extensive experiments have shown that it generates more efficient workload execution plans than the existing alternatives. © 2024 IEEE.

关键词： Dynamic programming

来源：评论

学校读者我要写书评

暂无评论

Thematic Event Extraction Based on Event-Related Sentence Detection 1

Thematic Event Extraction Based on Event-Related Sentence De...

引用

1st IEEE International Conference on Medical Artificial Intelligence, MedAI 2023

作者： Zhang, Xing Guo, Yucan Jin, Xiaolong Liang, Haozhe Guan, Saiping School of Computer Science and Technology University of Chinese Academy of Sciences China Institute of Computing Technology Chinese Academy of Sciences Cas Key Laboratory of Network Data Science and Technology China Institute of Systems Engineering Academy of Military Science Australia

ISBN: (纸本)9798350358780

Existing works in event extraction typically extract event arguments within the sentence scope. However, besides the sentence level, events may also be naturally presented at the document level. A document-level event usually reflects, to some extent, the theme (i.e., the main content) of the document (e.g., electronic medical records and news articles), which is thus referred to as the thematic event. Thematic Event Extraction (TEE) aims to extract the arguments of thematic events. TEE faces a major challenge, i.e., the sparsity and dispersion of arguments, which means that the arguments of a thematic event are dispersed in different sentences of the document. To overcome this challenge, we propose an Event-related Sentence Detection based TEE model, called ESDTEE, which first detects the sentences related to the thematic event and then extracts the arguments only within these detected sentences using existing models. Extensive experiments with comprehensive analyses demonstrate the effectiveness of ESDTEE. © 2023 IEEE.

关键词： Medical computing

来源：评论

学校读者我要写书评

暂无评论

Reinforcement Learning Application Testing Method based on Multi-attribute Fusion 9

Reinforcement Learning Application Testing Method based on M...

引用

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

作者： Cai, Lizhi Wang, Jin Chen, Mingang Wang, Jilong School of Information Science and Engineering East China University of Science and Technology Shanghai China Shanghai Development Center of Computer Software Technology Shanghai Key Laboratory of Computer Software Testing & Evaluating Shanghai China

ISBN: (数字)9781665488778

ISBN: (纸本)9781665488778

Reinforcement learning has been successfully applied to assess the reliability of applications, but the existing testing methods based on reinforcement learning have the problems of invalid interactive widgets and difficult training, resulting in low testing efficiency. In order to solve these problems, this paper proposes a lightweight application automation testing method of deep reinforcement learning based on multi-attribute fusion (MARTesting). First, the invalid widgets are removed by the difference operation of the attribute sets of the current and previous state, then the attributes of all widget elements on the page are abstracted into state as the input of the neural network, and a state is accurately determined by fusing the position and text information of page elements, finally combine the novelty of the state and the execution frequency of the action as a reward function. The experimental results on six open source applications show that the MARTesting method proposed in this paper has achieved significant improvements in code coverage and branch coverage compared with existing methods. © 2022 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Multi-Task Learning Network Optimization Based on Weight Adaptive 11

Multi-Task Learning Network Optimization Based on Weight Ada...

引用

11th IEEE International Conference on Behavioural and Social Computing, BESC 2024

作者： Cao, Zizhuo Li, Yidong Ding, Chuntao Zhang, Zhuxi School of Computer Science and Technology Beijing Jiaotong University Key Laboratory of Big Data & Artificial Intelligence in Transportation Ministry of Education Beijing100044 China General Logistics Information Center Beijing100036 China

ISBN: (纸本)9798331531904

Multi-task learning has emerged as a significant topic in artificial intelligence research, where a singular network model performs numerous tasks. This approach simultaneously processes multiple related tasks and shared knowledge, enhancing model generalization while increasing efficiency. This methodology provides innovative solutions to complex real-world problems. However, the single-model-based approach for multi-task learning suffers from inter-task interference in practice. Therefore, the exploration of more efficient multi-task learning strategies, aimed at balancing the synergy and conflict among tasks and minimizing the dependence on computational resources, is pivotal for the field's future progress. We propose a strategy that autonomously adjusts both the parameters and structures of the model to alleviate gradient interference in multi-task learning. This method includes integrating a lightweight, weight-adaptive module that enhances the network's ability to process tasks by optimally balancing parameter sharing and isolation. This adaptation enables the model to share common features across tasks while allocating distinct spaces for each task, thereby reducing interference. Our extensive experimental validation indicates that our framework surpasses other multi-task learning approaches, achieving joint optimization of tasks more effectively. This enhancement not only bolsters performance but also maintains an equilibrium between accuracy and inference speed. © 2024 IEEE.

关键词： Multi-task learning

来源：评论

学校读者我要写书评

暂无评论

Dual-view Label and Feature Supervision Network for Semi-supervised Medical Image Segmentation 24

Dual-view Label and Feature Supervision Network for Semi-sup...

引用

7th International Conference on Signal Processing and Machine Learning, SPML 2024

作者： Zhou, Zhen Li, Zuoyong Wang, Zhengyuan Teng, Shenghua Wang, Tao College of Electronic and Information Engineering Shandong University of Science and Technology Qingdao China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control School of Computer and Big Data Minjiang University Fuzhou China

ISBN: (纸本)9798400717192

Semi-supervised learning has garnered significant attention, particularly in medical image segmentation, owing to its capacity to leverage a large number of unlabeled data and a limited amount of labeled data to improve performance. However, most existing semi-supervised segmentation methods exhibit shortcomings in supervising unlabeled data, both in the label space due to potential noise in pseudo-labels, and the feature space due to indistinct class boundaries. To address the issues above, we propose Dual-view Label and Feature Supervision Network, termed DLFS-Net, to enhance label and feature supervision for unlabeled data. Our approach is based on a dual-view learning strategy that incorporates two modules: the Confidence Fusion Supervision Module (CFS) and the Dual-view Prototype Learning Module (DPL). Specifically, the CFS module generates weight matrices to integrate complementary information from two model outputs, producing more accurate pseudo-labels in the label space. The DPL module reduces intra-class variations in the feature space from two different views through prototype learning to generate clear class boundaries. Experiments on the LA and Pancreas-CT datasets demonstrate that our framework show solid gains (e.g.,1.76% Dice and 2.37% Jaccard improvement on Pancreas-CT dataset with 20% labeled data) compared with the state-of-the-art methods. © 2024 ACM.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Scaling Laws for data-Efficient Visual Transfer Learning

arXiv

引用

arXiv 2025年

作者： Yang, Wenxuan Wei, Qingqu Ma, Chenxi Tan, Weimin Yan, Bo Shanghai Key Laboratory of Intelligent Information Processing School of Computer Science Fudan University Shanghai China

Current scaling laws for visual AI models focus predominantly on large-scale pretraining, leaving a critical gap in understanding how performance scales for data-constrained downstream tasks. To address this limitation, this paper establishes the first practical framework for data-efficient scaling laws in visual transfer learning, addressing two fundamental questions: 1) How do scaling behaviors shift when downstream tasks operate with limited data? 2) What governs the efficacy of knowledge distillation under such constraints? Through systematic analysis of vision tasks across data regimes (1K–1M samples), we propose the distillation boundary theory, revealing a critical turning point in distillation efficiency: 1) Distillation superiority: In data-scarce conditions, distilled models significantly outperform their non-distillation counterparts, efficiently leveraging inherited knowledge to compensate for limited training samples. 2) Pre-training dominance: As pretraining data increases beyond a critical threshold, non-distilled models gradually surpass distilled versions, suggesting diminishing returns from knowledge inheritance when sufficient task-specific data becomes available. Empirical validation across various model scales (2.5M to 38M parameters) and data volumes demonstrate these performance inflection points, with error difference curves transitioning from positive to negative values at critical data thresholds, confirming our theoretical predictions. This work redefines scaling laws for data-limited regimes, bridging the knowledge gap between large-scale pretraining and practical downstream adaptation, addressing a critical barrier to understanding vision model scaling behaviors and optimizing computational resource allocation. Copyright © 2025, The Authors. All rights reserved.

关键词： Resource allocation

来源：评论

学校读者我要写书评

暂无评论

Blind Omnidirectional Image Quality Assessment Based on Swin Transformer with Scanpath-Oriented 12th

Blind Omnidirectional Image Quality Assessment Based on Swi...

引用

12th International Conference on Image and Graphics, ICIG 2023

作者： Tang, Xufeng An, Ping Yang, Chao Key Laboratory of Specialty Fiber Optics and Optical Access Networks Shanghai University Shanghai200444 China Shanghai Institute for Advanced Communication and Data Science Shanghai University Shanghai200444 China School of Communication and Information Engineering Shanghai University Shanghai200444 China

ISBN: (纸本)9783031463167

With the emergence of 5th generation mobile communication technology, the demand for Virtual Reality (VR) applications is on the rise worldwide. As one of the technologies related to visual content in VR, the quality evaluation of omnidirectional images has become an important issue. Inspired by the transformer, we propose a novel blind omnidirectional image quality assessment method. Firstly, we predict the path that the human eye follows when viewing omnidirectional images through headsets, and extract the area with the longest gaze duration on the path as the viewport. Then, to consider the intrinsic structural features of each pixel within each viewport, we use the Swin Transformer to extract viewport features. Finally, to establish a general scene perception and accurately evaluate immersive experiences, we construct a spatial viewport map for the entire perceptual scene. The graph structure performs reasoning on the overall relationship based on the spatial perception path. Experimental results demonstrate that our proposed model outperforms the current state-of-the-art Image Quality Assessment metrics, as evidenced by its superior results on two public databases. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： Quality control

来源：评论

学校读者我要写书评

暂无评论

PpNNT: Multiparty Privacy-Preserving Neural Network Training System

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第1期5卷 370-383页

作者： Feng, Qi He, Debiao Shen, Jian Luo, Min Choo, Kim-Kwang Raymond Wuhan University School of Cyber Science and Engineering Wuhan430072 China Shandong Provincial Key Laboratory of Computer Networks Jinan250014 China School of Information Science and Technology Zhejiang Sci-Tech University Hangzhou310018 China Shanghai Technology Innovation Centre of Distributed Privacy-Preserving Artificial Intelligence Matrix Elements Technologies Shanghai201204 China University of Texas at San Antonio Department of Information Systems and Cyber Security San AntonioTX78249 United States

By leveraging smart devices [e.g., industrial Internet of Things (IIoT)] and real-time data analytics, organizations, such as production plants can benefit from increased productivity, reduced costs, enhanced self-monitoring, and autonomous decision-making. In such a setting, machine learning plays an important role in data analytics, but the use of conventional centralized machine learning solutions may raise uncomfortable concerns about data privacy. Hence, one can explore the use of federated learning. In this article, we propose privacy-preserving deep neural network training (PpNNT), which is designed to support federated learning in the multiparty setting. To minimize the overall costs, we further design a hybrid architecture to fully maximize resource utilization. Our proposed design allows the PpNNT system to provide high security, efficiency, and scalability for IIoT data analytics, as evidenced by our theoretical security proof and experimental results on the CIFAR10 dataset. © 2020 IEEE.

关键词： Decision making

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：