检索结果-内蒙古大学图书馆

A New Method of Image Restoration technology Based on WGAN

Computer Systems Science & engineering 2022年第5期41卷 689-698页

作者： Wei Fang Enming Gu Weinan Yi Weiqing Wang Victor S.Sheng School of Computer&Software Engineering Research Center of Digital ForensicsMininstry of EducationNanjing University of Information Science&TechnologyNanjing210044China Provincial Key Laboratory for Computer Information Processing Technology Soochow UniversitySuzhou215325China Texas Tech University USA

With the development of image restoration technology based on deep learning,more complex problems are being solved,especially in image semantic inpainting based on ***,image semantic inpainting techniques are becoming more ***,due to the limitations of memory,the instability of training,and the lack of sample diversity,the results of image restoration are still encountering difficult problems,such as repairing the content of glitches which cannot be well integrated with the original ***,we propose an image inpainting network based on Wasserstein generative adversarial network(WGAN)*** the corresponding technology having been adjusted and improved,we attempted to use the Adam algorithm to replace the traditional stochastic gradient descent,and another algorithm to optimize the training used in recent *** evaluated our algorithm on the ImageNet *** obtained high-quality restoration results,indicating that our algorithm improves the clarity and consistency of the image.

关键词： Image restoration WGAN DCGAN context semantic

来源：评论

学校读者我要写书评

暂无评论

On the Noise Robustness of In-Context Learning for Text Generation 38

On the Noise Robustness of In-Context Learning for Text Gene...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Gao, Hongfu Zhang, Feipeng Jiang, Wenyu Shu, Jun Zheng, Feng Wei, Hongxin Department of Statistics and Data Science Southern University of Science and Technology China School of Economics and Finance Xi'an Jiaotong University China National Key Laboratory for Novel Software Technology Nanjing University China School of Mathematics and Statistics Xi'an Jiaotong University China Department of Computer Science and Engineering Southern University of Science and Technology China

Large language models (LLMs) have shown impressive performance on downstream tasks by in-context learning (ICL), which heavily relies on the quality of demonstrations selected from a large set of annotated examples. Recent works claim that in-context learning is robust to noisy demonstrations in text classification. In this work, we show that, on text generation tasks, noisy annotations significantly hurt the performance of in-context learning. To circumvent the issue, we propose a simple and effective approach called Local Perplexity Ranking (LPR), which replaces the "noisy" candidates with their nearest neighbors that are more likely to be clean. Our method is motivated by analyzing the perplexity deviation caused by noisy labels and decomposing perplexity into inherent perplexity and matching perplexity. Our key idea behind LPR is thus to decouple the matching perplexity by performing the ranking among the neighbors in semantic space. Our approach can prevent the selected demonstrations from including mismatched input-label pairs while preserving the effectiveness of the original selection methods. Extensive experiments demonstrate the effectiveness of LPR, improving the EM score by up to 18.75 on common benchmarks with noisy annotations. Our code is available at https://***/ml-stat-Sustech/Local-Perplexity-Ranking. © 2024 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

MSTF: enhancing long-term forecasting with multi-scale temporal fusion in time series forecasting

引用

The Journal of Supercomputing 2025年第9期81卷 1-21页

作者： Zhou, Chengjie Jiang, Ke Liu, Yunjiong Che, Chao Zhang, Qiang School of Computer Science and Technology Dalian University of Technology Dalian China Key Laboratory of Advanced Design and Intelligent Computing Ministry of Education School of Software Engineering Dalian University Dalian China

Long-term time series forecasting plays a vital role in applications like financial market prediction, energy usage forecasting, and traffic flow analysis. Deep learning models, though widely used in this task, often struggle to capture long-term dependencies and periodic patterns due to the overlapping of variables with different periods. To this end, we propose a multi-scale temporal fusion model named MSTF, which extracts sequential features and periodic patterns across multiple scales using a Time Reverse and Transform block and a Dynamic Combination Reconstruction block. Unlike traditional Transformer-based models, MSTF emphasizes overall temporal continuity rather than individual time point values. Experiments on seven datasets against ten advanced models demonstrate MSTF’s superior performance, faster training time, and reduced model complexity, particularly excelling on high-dimensional datasets.

关键词：

来源：评论

学校读者我要写书评

暂无评论

System design of microscopic ghost imaging 3

System design of microscopic ghost imaging

引用

3rd International Conference on Laser, Optics, and Optoelectronic technology, LOPET 2023

作者： Jin, Lu Lin, Binyu Wu, Yucong Wang, Shun Tang, Huaxu Feng, Yueshu Global Institute of Software Technology Suzhou215163 China Beijing Institute of Space Mechanics and Electricity Beijing100094 China Institute for Interdisciplinary Quantum Information Technology Jilin Engineering Normal Universi ty Jilin Changchun130052 China Jilin Engineering Laboratory for Quantum Information Technology Jilin Changchun130052 China

ISBN: (纸本)9781510667624

As the primary tool for studying cells and biological tissues, micro-imaging technology has significantly promoted the bio-medical development. The microscopic ghost imaging system is designed to meet the diverse needs of microscopy imaging. In this method, the original optical path of a research-grade upright fluorescence microscope was modified to be an optical path of ghost imaging. Three different matrixes were adopted as the preset pattern of the digital micro-mirror device. The experimental results demonstrate that the gold matrix can obtain a relatively perfect result under weak and unstable lighting conditions. This method is expected to promote the application of ghost imaging technology in microscopy imaging of cells and biological tissues. © 2023 SPIE.

关键词： Histology

来源：评论

学校读者我要写书评

暂无评论

A Global Visual Information Intervention Model for Medical Visual Question Answering

引用

Computers in Biology and Medicine 2025年第PT A期192卷 110195-110195页

作者： Peng, Peixi Fan, Wanshu Shen, Yue Yang, Xin Zhou, Dongsheng National and Local Joint Engineering Laboratory of Computer-Aided Design School of Software Engineering Dalian University Dalian116622 China School of Computer Science and Technology Dalian University of Technology Dalian116024 China

Medical Visual Question Answering (Med-VQA) aims to furnish precise responses to clinical queries related to medical imagery. While its transformative potential in healthcare is undeniable, current solutions remain nascent and are yet to see widespread clinical adoption. Med-VQA presents heightened complexities compared to standard visual question answering (VQA) tasks due to the myriad of clinical scenarios and the scarcity of labeled medical imagery. This often culminates in language biases and overfitting vulnerabilities. In light of these challenges, this study introduces Global Visual Information Intervention (GVII), an innovative Med-VQA model designed to mitigate language biases and improve model generalizability. GVII is centered on two key branches: the Global Visual Information Branch (GVIB), which extracts and filters holistic visual data to amplify the image's contribution and reduce question dominance, and the Forward Compensation Branch (FCB), which refines multimodal features to counterbalance disruptions introduced by GVIB. These branches work in tandem to enhance predictive accuracy and robustness. Furthermore, a multi-branch fusion mechanism ensures cohesive integration of features and losses across the model. Experimental results demonstrate that the proposed model outperforms existing state-of-the-art models, achieving a 2.6% improvement in accuracy on the PathVQA dataset. In conclusion, the GVII-based Med-VQA model not only successfully mitigates prevalent language biases and overfitting issues but also significantly improves diagnostic precision, offering a considerable stride toward robust, clinically applicable VQA systems. © 2025

关键词： Question answering

来源：评论

学校读者我要写书评

暂无评论

Analysis of vocational education dynamics evolution based on topic modeling 14

Analysis of vocational education dynamics evolution based on...

引用

14th International Conference on Information technology in Medicine and Education, ITME 2024

作者： Wang, Xinhua Yu, Xiaomei Jiang, Yunmeng Zheng, Xiangwei Li, Wei Shandong Normal University School of Information Science and Engineering Jinan China Shandong Provincial Key Laboratory for Distributed Computer Software Novel Technology Jinan250358 China Shandong Normal University Library Shandong Normal University Jinan China

ISBN: (纸本)9798350356670

Clarifying the focus of vocational education dynamics is crucial for understanding the current situation and future development trends. However, comprehensive exploration on vocational education dynamics is inadequate presently. In this paper, textual information on vocational education is analyzed with Latent Dirichlet Allocation, BERTopic, and the Dynamic Topic Model. Two key issues are thoroughly investigated as follows: (1) What are the main aspects of the current development of vocational education;(2) How to learn the embeddings of vocational education text and further to promote the formulation of policy. The experiments are conducted and the experimental results show that LDA and BERTopic model achieve effective performance in clustering the texts of vocational education dynamics, and the DTM captures the topics trend of vocational education, which facilitate the government to guide the formulation and implementation of policies. © 2024 IEEE.

关键词： Apprentices

来源：评论

学校读者我要写书评

暂无评论

Pressure-stabilized electride Li10Si with superconducting and superionic behavior

引用

Physical Review B 2024年第13期110卷 134114页

作者： Qinfang Wang Wenwen Cui Weishuo Xu Kun Gao Jian Hao Jingming Shi Hanyu Liu Yinwei Li Laboratory of Quantum Functional Materials Design and Application School of Physics and Electronic Engineering Key Laboratory of Material Simulation Methods and Software of Ministry of Education and State Key Laboratory of Superhard Materials College of Physics Shandong Key Laboratory of Optical Communication Science and Technology School of Physical Science & Information Technology of

Electrides have attracted increasing interest due to their diversely physical properties, including low work function, high catalytic activity, as well as potential superconductivity. In this work, using first-principles crystal structure prediction method in combination with first-principles calculations, we uncovered seven thermodynamically stable electrides in the electron-rich Li-Si system at a pressure range of 25–100 GPa, namely C2/cLi5Si, CmcmLi6Si, P21/mLi7Si, ImmaLi7Si, C2/cLi8Si, CmcmLi9Si, and I222Li10Si. Among these predicted structures, five of them are superconductor. In particular, the superconducting critical temperature Tc of I222Li10Si was estimated to be approximately 15 K at 95 GPa. Our in-depth analysis shows that this high superconductivity is attributed to the strong coupling between the Li-p electrons and the Li-dominated phonon softening at low frequencies. Additionally, Li10Si undergoes a phase transition from solid state to superionic state at 60 GPa and 850 K, where Si atoms remain fixed to form the lattice, allowing for the diffusion of Li atoms within the interstitial position. Our results reveal the emergence of two distinct dynamic states of superconducting and superionic in this particular system, and the further experimental studies are thus stimulated.

关键词： Superconductors Density functional calculations Density functional theory First-principles calculations

来源：评论

学校读者我要写书评

暂无评论

Secure Two-Party Computation for Fingerprinting-based Indoor Localization

Secure Two-Party Computation for Fingerprinting-based Indoor...

引用

2023 IEEE/CIC International Conference on Communications in China, ICCC 2023

作者： Wang, Xintong Qiu, Ying Hu, Jinming Cao, Lili Zhang, Yueyue Zhu, Yaping Tongji University School of Software Engineering Shanghai200092 China Test Laboratory The Third Research Institute of Ministry Shanghai200031 China Shanghai Aerospace Electronic Technology Institute Shanghai201109 China

ISBN: (纸本)9798350345384

With the increasing demand for privacy-preserving localization, how to protect the private information of customers (e.g., location) and service providers (e.g., database) is worthy of great attention in the process of realizing indoor positioning. Based on the two-party computation (TPC) protocol, this paper studies and optimizes the indoor localization technology which uses the received signal strength (RSS) of Wi-Fi access point, for the sake of privacy protection. The Paillier encryption algorithm is first used to encrypt the RSS values of the client, in which we propose to optimize the algorithm by predictive calculation and logic optimization, to reduce the communication overhead. Then, the DGK protocol is proposed to calculate the minimum distance in the ciphertext field on the server side. Simulation results show that the proposed algorithm can protect not only the location privacy of the client, but also the database security of the service provider, with a reduced computation cost. © 2023 IEEE.

关键词： Wi-Fi

来源：评论

学校读者我要写书评

暂无评论

FedDGL: Federated Dynamic Graph Learning for Temporal Evolution and Data Heterogeneity 16

FedDGL: Federated Dynamic Graph Learning for Temporal Evolut...

引用

16th Asian Conference on Machine Learning, ACML 2024

作者： Xie, Zaipeng Li, Likun Chen, Xiangbin Yu, Hao Huang, Qian Key Laboratory of Water Big Data Technology of Ministry of Water Resources Hohai University Nanjing China College of Computer Science and Software Engineering Hohai University Nanjing China College of Artificial Intelligence and Automation Hohai University Nanjing China

Federated graph learning enhances federated learning by enabling privacy-preserving collaborative training on distributed graph data. While traditional methods are effective in managing data heterogeneity, they typically assume static graph structures, overlooking the dynamic nature of real-world graphs. Integrating federated graph learning with dynamic graph neural networks addresses this issue but often fails to retain previously acquired knowledge, limiting generalization for both global and personalized models. This paper proposes FedDGL, a novel framework designed to address temporal evolution, and data heterogeneity in federated dynamic graph learning. Unlike conventional approaches, FedDGL captures temporal dynamics through a global knowledge distillation technique and manages client heterogeneity using a global prototype-based regularization method. The framework employs contrastive learning to generate global prototypes, enhancing feature representation while utilizing a prototype similarity-based personalized aggregation strategy for effective adaptation to local and global data distributions. Experiments on multiple benchmark datasets show that FedDGL achieves significant performance improvements over state-of-the-art methods, with up to 9.02% and 8.77% gains in local and global testing, respectively, compared to FedAvg. These results highlight FedDGL’s effectiveness in improving personalized and global model performance in dynamic, heterogeneous federated graph learning scenarios. © 2024 Z. Xie, L. Li, X. Chen, H. Yu & Q. Huang.

关键词： Dynamic Graph Learning Federated Graph Learning Knowledge Distillation Personalized Aggregation Prototype Learning Temporal Evolution

来源：评论

学校读者我要写书评

暂无评论

DevEval: A Manually-Annotated Code Generation Benchmark Aligned with Real-World Code Repositories 62

DevEval: A Manually-Annotated Code Generation Benchmark Alig...

引用

Findings of the 62nd Annual Meeting of the Association for Computational Linguistics, ACL 2024

作者： Li, Jia Li, Ge Zhao, Yunfei Li, Yongmin Liu, Huanyu Zhu, Hao Wang, Lecheng Liu, Kaibo Fang, Zheng Wang, Lanshen Ding, Jiazheng Zhang, Xuanming Zhu, Yuqi Dong, Yihong Jin, Zhi Li, Binhua Huang, Fei Li, Yongbin Gu, Bin Yang, Mengfei School of Computer Science Peking University China Key Laboratory of High Confidence Software Technologies Peking University Ministry of Education China Alibaba Group China Beijing Institute of Control Engineering China China Academy of Space Technology China

ISBN: (纸本)9798891760998

How to evaluate the coding abilities of Large Language Models (LLMs) remains an open question. We find that existing benchmarks are poorly aligned with real-world code repositories and are insufficient to evaluate the coding abilities of LLMs. To address the knowledge gap, we propose a new benchmark named DevEval, which has three advances. 1 DevEval aligns with real-world repositories in multiple dimensions, e.g., code and dependency distributions. 2 DevEval is annotated by 13 developers and contains comprehensive annotations (e.g., requirements, original repositories, reference code, and reference dependencies). 3 DevEval comprises 1,825 testing samples from 115 repositories, covering 10 popular domains (e.g., Internet, Database). Based on DevEval, we propose repository-level code generation and evaluate 8 popular LLMs on DevEval (e.g., gpt-4, gpt-3.5, StarCoder 2, DeepSeek Coder, CodeLLaMa). Our experiments reveal these LLMs' coding abilities in real-world code repositories. For example, the highest Pass@1 of gpt-4 only is 53.04% in our experiments. We also analyze LLMs' failed cases and summarize their shortcomings. We hope DevEval can facilitate the development of LLMs in real code repositories. DevEval, prompts, and LLMs' predictions have been released. © 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

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：