检索结果-内蒙古大学图书馆

Decoupled Prototype Learning for Reliable Test-Time Adaptation

IEEE Transactions on Multimedia 2025年 27卷 3585-3597页

作者： Wang, Guowei Ding, Changxing Tan, Wentao Tan, Mingkui South China University of Technology School of Electronic and Information Engineering 381 Wushan Road Tianhe District Guangzhou510000 China Pazhou Lab Guangzhou510330 China South China University of Technology School of Future Technology 381 Wushan Road Tianhe District Guangzhou510000 China South China University of Technology School of Software Engineering Key Laboratory of Big Data and Intelligent Robot Ministry of Education Guangzhou510006 China

Test-time adaptation (TTA) is a task that continually adapts a pre-trained source model to the target domain during inference. One popular approach involves fine-tuning model with cross-entropy loss according to estimated pseudo-labels. However, its performance is significantly affected by noisy pseudo-labels. This study reveals that minimizing the classification error of each sample causes the cross-entropy loss's vulnerability to label noise. To address this issue, we propose a novel Decoupled Prototype Learning (DPL) method that features prototype-centric loss computation. First, we decouple the optimization of class prototypes. For each class prototype, we reduce its distance with positive samples and enlarge its distance with negative samples in a contrastive manner. This strategy prevents the model from overfitting to noisy pseudo-labels. Second, we propose a memory-based strategy to enhance DPL's robustness for the small batch sizes often encountered in TTA. We update each class's pseudo-feature from a memory in a momentum manner and insert an additional DPL loss. Finally, we introduce a consistency regularization-based approach to leverage samples with unconfident pseudo-labels. This approach transfers feature styles of samples with unconfident pseudo-labels to those with confident pseudo-labels. Thus, more reliable samples for TTA are created. The experimental results demonstrate that our methods achieve state-of-the-art performance on domain generalization benchmarks, and reliably improve the performance of self-training-based methods on image corruption benchmarks. The code will be released. © 1999-2012 IEEE.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Research on performance optimization of virtual data space across WAN

引用

Frontiers of Computer Science 2024年第6期18卷 167-187页

作者： Jiantong HUO Zhisheng HUO Limin XIAO Zhenxue HE State Key Laboratory of Software Development Environment Beihang UniversityBeijing 100191China School of Computer Science and Engineering Beihang UniversityBeijing 100191China High Performance Computing Center Beihang UniversityBeijing 100191China Hebei Key Laboratory of Agricultural Big Data Hebei Agricultural UniversityBaoding 071001China

For the high-performance computing in a WAN environment,the geographical locations of national supercomputing centers are scattered and the network topology is complex,so it is difficult to form a unified view of *** aggregate the widely dispersed storage resources of national supercomputing centers in China,we have previously proposed a global virtual data space named GVDS in the project of“High Performance Computing Virtual data Space”,a part of the National key Research and Development Program of *** GVDS enables large-scale applications of the high-performance computing to run efficiently across ***,the applications running on the GVDS are often data-intensive,requiring large amounts of data from multiple supercomputing centers across *** this regard,the GVDS suffers from performance bottlenecks in data migration and access across *** solve the above-mentioned problem,this paper proposes a performance optimization framework of GVDS including the multitask-oriented data migration method and the request access-aware IO proxy resource allocation *** a WAN environment,the framework proposed in this paper can make an efficient migration decision based on the amount of migrated data and the number of multiple data sources,guaranteeing lower average migration latency when multiple data migration tasks are running in *** addition,it can ensure that the thread resource of the IO proxy node is fairly allocated among different types of requests(the IO proxy is a module of GVDS),so as to improve the application’s performance across *** experimental results show that the framework can effectively reduce the average data access delay of GVDS while improving the performance of the application greatly.

关键词： storage aggregation across WANs large-scale applications GVDS data migration allocation of IO proxy resource

来源：评论

学校读者我要写书评

暂无评论

Updating Large Language Models' Memories with Time Constraints

Updating Large Language Models' Memories with Time Constrain...

引用

2024 Findings of the Association for Computational Linguistics, EMNLP 2024

作者： Wu, Xin Bu, Yuqi Cai, Yi Wang, Tao School of Software Engineering South China University of Technology China Key Laboratory of Big Data and Intelligent Robot South China University of Technology Ministry of Education China Department of Biostatistics and Health Informatics King's College London United Kingdom

ISBN: (纸本)9798891761681

By incorporating the latest external knowledge, large language models (LLMs) can modify their internal memory. However, in practical applications, LLMs may encounter outdated information, necessitating the filtering of such data and updating of knowledge beyond internal memory. This paper explores whether LLMs can selectively update their memories based on the time constraints between internal memory and external knowledge. We evaluate existing LLMs using three types of data that exhibit different time constraints. Our experimental results reveal the challenges most LLMs face with time-constrained knowledge and highlight the differences in how various LLMs handle such information. Additionally, to address the difficulties LLMs encounter in understanding time constraints, we propose a two-stage decoupling framework that separates the identification and computation of time constraint into a symbolic system. Experimental results demonstrate that the proposed framework yields an improvement of over 60% in ChatGPT's performance, and achieves a 12-24% enhancement in state-of-the-art LLM GPT-4. © 2024 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Image denoising based on residual network 3

Image denoising based on residual network

引用

3rd International Conference on Electronic Information engineering, big data, and Computer Technology, EIBDCT 2024

作者： Ma, Lihe Wang, Yan Sha, Ning Ma, Lin School of Information Engineering Harbin University Harbin China Heilongjiang Government Affairs Big Data Center3 Harbin China Heilongjiang Provincial Key Laboratory of the Intelligent Perception and Intelligent Software Harbin China

ISBN: (纸本)9781510680449

Image denoising has always been a hot research topic in the field of computer vision, playing an important role in improving image quality and accuracy. In this paper, a method for image denoising based on residual network is proposed, which uses deep learning technology to improve the effect of image processing. This method can automatically learn useful features in the image and effectively remove noise in the image, achieving automatic removal of image noise. Finally, experiments were conducted on standard image datasets for evaluation. The experimental results show that the image denoising method based on residual network has better performance compared to traditional methods. It can effectively remove various types of noise, improve image quality and clarity, and has broad application prospects in image processing. © COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.

关键词： Image denoising

来源：评论

学校读者我要写书评

暂无评论

CLCoSum: Curriculum Learning-Based Code Summarization for Code Language Models

CLCoSum: Curriculum Learning-Based Code Summarization for Co...

引用

IEEE/ACM International Conference on Program Comprehension (ICPC)

作者： Hongkui He Jiexin Wang Liuwen Cao Yi Cai School of Software Engineering South China University of Technology Key Laboratory of Big Data and Intelligent Robot (SCUT) MOE of China

ISBN: (数字)9798331502232

ISBN: (纸本)9798331502249

The code summarization task aims to automatically generate natural language descriptions for code snippets. Recently, pre-trained code language models (CLMs) have demonstrated outstanding performance on code summarization. Additionally, researchers have shown that there is a strong correlation between code function names and summaries, and poorly defined function names lead to worse summaries generated by models. To mitigate this issue, in this paper, we propose CLCoSum, a curriculum learning-based code summarization method for CLMs that improves their performance in poorly named function scenarios. CLCoSum helps CLMs avoid overreliance on function names when they are poorly defined. First, CLCoSum employs data augmentation operators on function names to generate semantically equivalent poorly named codes, which are considered harder data and assist in reducing the model's reliance on unclear function names. Subsequently, CLCoSum uses a curriculum learning paradigm to allow the model to learn these harder codes in an organized way during finetuning. This approach enables CLMs to progress from easier to more difficult training data, similar to the human learning process. Extensive experiments on two existing datasets for Java and Python demonstrate that CLCoSum boosts the performance of various CLMs in code summarization. Specifically, the improvements in BLEU-4 score range from approximately 5% to $\mathbf{2 0. 8 \%}$ . The fine-tuning speed of CLCoSum on the augmented dataset is also competitive. Our code and data are available at https://***/KuiH/CLCoSum.

关键词： Java Codes Correlation Natural languages Training data data augmentation data models Python

来源：评论

学校读者我要写书评

暂无评论

RGCNU: Recurrent Graph Convolutional Network With Uncertainty Estimation for Remaining Useful Life Prediction

引用

IEEE/CAA Journal of Automatica Sinica 2023年第7期10卷 1640-1642页

作者： Qiwu Zhu Qingyu Xiong Zhengyi Yang Yang Yu School of Big Data&Software Engineering Chongqing UniversityChongqing 400044 Key Laboratory of Dependable Service Computing in Cyber Physical Society Ministry of EducationChongqing 400044China School of Biology and Engineering Guizhou Medical UniversityGuiyang 550025China

Dear Editor,This letter focuses on the problem of remaining useful life(RUL)prediction of equipment. Existing graph neural network(GCN)-based approaches merely provide the point estimation of RUL. However,the estimated RUL often varies widely due to the model parameters and the noise in data. It is important to know the uncertainty in predictions for reliable risk analysis and maintenance decision *** map the relationship between noisy condition monitoring data and RUL with uncertainty.

关键词： letter estimation prediction

来源：评论

学校读者我要写书评

暂无评论

DCEL:classifier fusion model for Android malware detection

引用

Journal of Systems engineering and Electronics 2024年第1期35卷 163-177页

作者： XU Xiaolong JIANG Shuai ZHAO Jinbo WANG Xinheng Jiangsu Key Laboratory of Big Data Security&Intelligent Processing Nanjing University of Posts and TelecommunicationsNanjing 210023China School of Computer Science Nanjing University of Posts and TelecommunicationsNanjing 210023China School of Computing and Engineering University of West LondonLondon W55RFUK

The rapid growth of mobile applications,the popularity of the Android system and its openness have attracted many hackers and even criminals,who are creating lots of Android ***,the current methods of Android malware detection need a lot of time in the feature engineering ***,these models have the defects of low detection rate,high complexity,and poor practicability,*** analyze the Android malware samples,and the distribution of malware and benign software in application programming interface(API)calls,permissions,and other *** classify the software’s threat levels based on the correlation of ***,we propose deep neural networks and convolutional neural networks with ensemble learning(DCEL),a new classifier fusion model for Android malware ***,DCEL preprocesses the malware data to remove redundant data,and converts the one-dimensional data into a two-dimensional gray ***,the ensemble learning approach is used to combine the deep neural network with the convolutional neural network,and the final classification results are obtained by voting on the prediction of each single *** based on the Drebin and Malgenome datasets show that compared with current state-of-art models,the proposed DCEL has a higher detection rate,higher recall rate,and lower computational cost.

关键词： Android malware detection deep learning ensemble learning model fusion

来源：评论

学校读者我要写书评

暂无评论

UniSleepPos: Sleep Posture Identification System Utilizing Millimeter-wave Radar

UniSleepPos: Sleep Posture Identification System Utilizing M...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Liu, Kun Li, Min He, Chu Tian, Xu Mao, Junbin Zeng, Min Liu, Jin Xinjiang University Xinjiang Engineering Research Center of Big Data and Intelligent Software School of Software Urumqi China Central South University Hunan Provincial Key Lab on Bioinformatics School of Computer Science and Engineering Changsha China

ISBN: (纸本)9798350386226

Sleep posture identification is crucial for accurately assessing sleep quality and diagnosing related diseases. In the realm of non-intrusive sleep monitoring, non-contact technologies are becoming increasingly mainstream. Millimeter-wave radar is frequently utilized in sleep posture identification due to its high resolution, strong penetration, and excellent sensitivity. However, traditional radar-based methods for sleep posture identification often struggle with reliability when dealing with diverse individuals and complex sleep environments. To address these challenges, we propose UniSleepPos, which designs a novel dual-view fusion mechanism to integrate depression and elevation angle signals obtained from radar, thus accurately capturing the posture information of the monitored subject in three-dimensional space. Furthermore, we combine sleep posture identification with individual characteristics, utilizing existing individual labels as prior knowledge to assist in sleep posture identification. The integration of prior knowledge provides a valuable information source for the model, helping to enhance its understanding of the data and improve its performance. We collected sleep posture data from eight volunteers using millimeter-wave radar devices under various environmental conditions. Leave-one-subject-out experiments were conducted to validate the effectiveness of UniSleepPos. The results indicated that UniSleepPos significantly outperforms existing methods, demonstrating its potential for practical applications. © 2024 IEEE.

关键词： Sleep research

来源：评论

学校读者我要写书评

暂无评论

Distributed Truss Computation in Dynamic Graphs

引用

Tsinghua Science and Technology 2023年第5期28卷 873-887页

作者： Ziwei Mo Qi Luo Dongxiao Yu Hao Sheng Jiguo Yu Xiuzhen Cheng School of Computer Science and Technology Shandong UniversityQingdao 266200China State Key Laboratory of Software Development Environment School of Computer Science and Engineering and the Beijing Advanced Innovation Center for Big Data and Brain ComputingBeihang UniversityBeijing 100191China Big Data Institute Qilu University of Technology(Shandong Academy of Sciences)Jinan 250353China

Large-scale graphs usually exhibit global sparsity with local cohesiveness,and mining the representative cohesive subgraphs is a fundamental problem in graph *** k-truss is one of the most commonly studied cohesive subgraphs,in which each edge is formed in at least k 2 triangles.A critical issue in mining a k-truss lies in the computation of the trussness of each edge,which is the maximum value of k that an edge can be in a *** works mostly focus on truss computation in static graphs by sequential ***,the graphs are constantly changing dynamically in the real *** study distributed truss computation in dynamic graphs in this *** particular,we compute the trussness of edges based on the local nature of the k-truss in a synchronized node-centric distributed *** decomposing the trussness of edges by relying only on local topological information is possible with the proposed distributed decomposition ***,the distributed maintenance algorithm only needs to update a small amount of dynamic information to complete the *** experiments have been conducted to show the scalability and efficiency of the proposed algorithm.

关键词： distributed algorithm dynamic graph graph mining cohesive subgraph k-truss

来源：评论

学校读者我要写书评

暂无评论

A survey for light field super-resolution

引用

High-Confidence Computing 2024年第1期4卷 118-129页

作者： Mingyuan Zhao Hao Sheng Da Yang Sizhe Wang Ruixuan Cong Zhenglong Cui Rongshan Chen Tun Wang Shuai Wang Yang Huang Jiahao Shen State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and EngineeringBeihang UniversityBeijing 100191China Key Laboratory of Data Science and Intelligent Computing International Innovation InstituteBeihang UniversityHangzhou 311115China State Key Laboratory of Software Development Environment School of Computer Science and EngineeringBeihang UniversityBeijing 100191China

Compared to 2D imaging data,the 4D light field(LF)data retains richer scene’s structure information,which can significantly improve the computer’s perception capability,including depth estimation,semantic segmentation,and LF ***,there is a contradiction between spatial and angular resolution during the LF image acquisition *** overcome the above problem,researchers have gradually focused on the light field super-resolution(LFSR).In the traditional solutions,researchers achieved the LFSR based on various optimization frameworks,such as Bayesian and Gaussian *** learning-based methods are more popular than conventional methods because they have better performance and more robust generalization *** this paper,the present approach can mainly divided into conventional methods and deep learning-based *** discuss these two branches in light field spatial super-resolution(LFSSR),light field angular super-resolution(LFASR),and light field spatial and angular super-resolution(LFSASR),***,this paper also introduces the primary public datasets and analyzes the performance of the prevalent approaches on these ***,we discuss the potential innovations of the LFSR to propose the progress of our research field.

关键词： Light field super-resolution Convolutional neural network Transformer Sub-aperture image Epipolar-plane image

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：