检索结果-内蒙古大学图书馆

THE RIEMANN PROBLEM WITH DELTA INITIAL data FOR THE NON-ISENTROPIC IMPROVED AW-RASCLE-ZHANG MODEL

Acta Mathematica Scientia 2023年第1期43卷 237-258页

作者：蒋伟峰陈停停李彤王振 College of Science Key Laboratory of Intelligent Manufacturing Quality Big Data Tracing and Analysis of Zhejiang ProvinceChina Jiliang UniversityHangzhou310018China School of Mathematics and Physics China University of GeosciencesWuhan430074China Department of Mathematics The University of IowaIowaIA52246USA Center for Mathematical Sciences and Department of Mathematics Wuhan University of TechnologyWuhan430070China

In this paper,we study the Radon measure initial value problem for the nonisentropic improved Aw-Rascle-Zhang *** arbitrary convex F(u)in this model we construct the Riemann solutions by elementary waves andδ-shock waves using the method of generalized characteristic *** obtain the solutions constructively for initial data containing the Dirac measure by taking the limit of the solutions for that with three piecewise ***,we analyze different kinds of wave interactions,including the interactions of theδ-shock waves with elementary waves.

关键词： Riemann problem non-isentropic improved Aw-Rascle-Zhang model δ-shock wave wave interactions traffic flow

来源：评论

学校读者我要写书评

暂无评论

TASK ARITHMETIC IN TRUST REGION: A TRAINING-FREE MODEL MERGING APPROACH TO NAVIGATE KNOWLEDGE CONFLICTS

arXiv

引用

arXiv 2025年

作者： Sun, Wenju Li, Qingyong Wang, Wen Geng, Yangli-Ao Li, Boyang Key Laboratory of Big Data & Artificial Intelligence in Transportation Beijing Jiaotong University Beijing100044 China College of Computing and Data Science Nanyang Technological University 639798 Singapore

Multi-task model merging offers an efficient solution for integrating knowledge from multiple fine-tuned models, mitigating the significant computational and storage demands associated with multi-task training. As a key technique in this field, Task Arithmetic (TA) defines task vectors by subtracting the pre-trained model (θpre) from the fine-tuned task models in parameter space, then adjusting the weight between these task vectors and θpre to balance task-generalized and task-specific knowledge. Despite the promising performance of TA, conflicts can arise among the task vectors, particularly when different tasks require distinct model adaptations. In this paper, we formally define this issue as knowledge conflicts, characterized by the performance degradation of one task after merging with a model fine-tuned for another task. Through in-depth analysis, we show that these conflicts stem primarily from the components of task vectors that align with the gradient of task-specific losses at θpre. To address this, we propose Task Arithmetic in Trust Region (TATR), which defines the trust region as dimensions in the model parameter space that cause only small changes (corresponding to the task vector components with gradient orthogonal direction) in the task-specific losses. Restricting parameter merging within this trust region, TATR can effectively alleviate knowledge conflicts. Moreover, TATR serves as both an independent approach and a plug-and-play module compatible with a wide range of TA-based methods. Extensive empirical evaluations on eight distinct datasets robustly demonstrate that TATR improves the multi-task performance of several TA-based model merging methods by an observable margin. Copyright © 2025, The Authors. All rights reserved.

关键词： Vectors

来源：评论

学校读者我要写书评

暂无评论

Identifying Outliers in Astronomical Images with Unsupervised Machine Learning

引用

Research in Astronomy and Astrophysics 2022年第8期22卷 74-84页

作者： Yang Han Zhiqiang Zou Nan Li Yanli Chen School of Computer Science Nanjing University of Posts and TelecommunicationsNanjing 210023China Jiangsu Key Laboratory of Big Data Security and Intelligent Processing Nanjing 210023China Key Laboratory of Optical Astronomy National Astronomical ObservatoriesChinese Academy of SciencesBeijing 100101China University of Chinese Academy of Sciences Beijing 100049China

Astronomical outliers,such as unusual,rare or unknown types of astronomical objects or phenomena,constantly lead to the discovery of genuinely unforeseen knowledge in *** unpredictable outliers will be uncovered in principle with the increment of the coverage and quality of upcoming survey ***,it is a severe challenge to mine rare and unexpected targets from enormous data with human inspection due to a significant *** learning is also unsuitable for this purpose because designing proper training sets for unanticipated signals is *** by these challenges,we adopt unsupervised machine learning approaches to identify outliers in the data of galaxy images to explore the paths for detecting astronomical *** comparison,we construct three methods,which are built upon the k-nearest neighbors(KNN),Convolutional Auto-Encoder(CAE)+KNN,and CAE+KNN+Attention Mechanism(att CAE_KNN)*** sets are created based on the Galaxy Zoo image data published online to evaluate the performance of the above *** show that att CAE_KNN achieves the best recall(78%),which is 53%higher than the classical KNN method and 22%higher than CAE+*** efficiency of att CAE_KNN(10 minutes)is also superior to KNN(4 h)and equal to CAE+KNN(10 minutes)for accomplishing the same ***,we believe that it is feasible to detect astronomical outliers in the data of galaxy images in an unsupervised ***,we will apply att CAE_KNN to available survey data sets to assess its applicability and reliability.

关键词： Galaxy Physical data and Processes Galaxy:fundamental parameters

来源：评论

学校读者我要写书评

暂无评论

CAT: A Collaborative Annotation Tool for Chinese Genealogy Textual Documents 26

CAT: A Collaborative Annotation Tool for Chinese Genealogy T...

引用

26th International Conference on Computer Supported Cooperative Work in Design, CSCWD 2023

作者： Jiang, Huan Wang, Zihao Li, Rongrong Peng, Yuwei Peng, Zhiyong Xu, Bin School of Computer Science Wuhan University Wuhan430072 China School of History Wuhan University Wuhan430072 China The Big Data Institute Wuhan University Wuhan430072 China Cultural Heritage Intelligent Computing Laboratory Wuhan University Wuhan430072 China

ISBN: (纸本)9798350331684

The annotation for Chinese genealogy textual documents is helpful for constructing genealogy knowledge graph, training effective machine learning models for knowledge extraction, etc. However, this kind of documents is difficult to annotate. The primary reason is that the texts are written in both classical and vernacular Chinese. These texts also contain numerous ancient characters and are usually without punctuation. Understanding genealogy texts requires sufficient expertise. When multiple users labeling the same text, conflicts may occur. Existing annotation tools are inappropriate for this work. In this paper, we propose a novel interactive labeling tool, which provides text segmenting, entity and relationship tagging etc. With the annotated information, it is convenient to construct knowledge graph from textual documents, which can be used to analyze Chinese genealogy texts. Furthermore, we introduce a weak supervised mechanism with Hidden Markov Model for collaborative annotating with crowdsourcing. The practice shows that our approach is effective for collaborative annotation. It also facilitates the construction of knowledge graph and obtains more high-quality data sets. At present, this annotation tool has been applied into service. © 2023 IEEE.

关键词： Hidden Markov models

来源：评论

学校读者我要写书评

暂无评论

Diagnosis model for mouse lung cancer based on terahertz spectroscopy and a transformer network

引用

Optics Express 2025年第11期33卷 23178-23193页

作者： Jianwei Li Shisheng Zhao Xuxu Ma Ziyu Li Xichuan Li Hebei Key Laboratory of Big Data Computing School of Artificial Intelligence Hebei University of Technology Tianjin 300401 China School of Life Sciences Tianjin Normal University Tianjin 300387 China

Terahertz time-domain spectroscopy technology offers a non-destructive and non-invasive approach to elucidating microstructure and chemical properties of cancer tissues, providing significant advantages for early diagnosis and monitoring. However, challenges such as the presence of outliers, sample class imbalance, and limited diagnostic accuracy persist. To enhance dataset quality, the boxplots were applied to identify and remove abnormal data, and the Savitzky-Golay filter was employed for spectral denoising in this paper. A high-quality dataset comprising 1,028 spectra from normal mouse lung tissues and 1,547 spectra from mouse lung cancer tissues was obtained. To address the shortage of normal lung tissue samples, a Wasserstein generative adversarial network with gradient penalty was utilized. Furthermore, to improve diagnostic accuracy, we developed a novel diagnostic model, MSFPT-Net. This model integrated seven distinct terahertz spectral features and employed a feature pyramid network to extract multi-scale representations, alongside a Transformer network to capture long-range dependencies within spectral sequences. The processed features were subsequently input into a fully connected network to achieve precise lung cancer diagnosis. Experimental results indicate that MSFPT-Net achieves outstanding performance across six evaluation metrics and opens new possibilities for lung cancer diagnosis and treatment.

关键词： Absorption coefficient Deep learning Extinction coefficients Machine learning Neural networks Refractive index

来源：评论

学校读者我要写书评

暂无评论

Image Denoising Method Based on Channel Compression and Split-Attention Mechanism

Image Denoising Method Based on Channel Compression and Spli...

引用

Computer Engineering and intelligent Control (ICCEIC) International Conference on

作者： Hao Sun Xiaoyan Qiao Yantai Key Laboratory of Big Data Modeling and Intelligent Computing Immersion School of Computer Science and Technology Shandong Technology and Business University Technology and Evaluation Shandong Engineering Research Center Yantai Shandong

ISBN: (数字)9798331507992

ISBN: (纸本)9798331508005

In the image restoration task, how to make full use of spatial and channel feature information to improve the reconstruction quality of the model without significantly increasing the computational complexity is an important research issue. To address this challenge, this paper proposes a CS module (Channel Compression and Split-Attention) specifically for optimizing image denoising tasks. The module first compresses the features through a preliminary convolution operation, then introduces the split attention convolution mechanism to split the features by channel and dynamically weight them, thereby enhancing the model's adaptive attention to different feature channels and improving feature expression capabilities. Through experiments on multiple image denoising datasets, the results show that the CS module significantly improves the image reconstruction quality, especially in terms of peak signal-to-noise ratio (PSNR). At the same time, the introduction of the CS module does not lead to a significant increase in computational complexity, maintaining a high computational efficiency, which verifies the practicality and superiority of the module in image denoising tasks.

关键词： Image coding PSNR Convolution Computational modeling Refining Image restoration Computational efficiency Computational complexity Image reconstruction Image denoising

来源：评论

学校读者我要写书评

暂无评论

A Weighted Flat Lattice Transformer-based Knowledge Extraction Architecture for Chinese Named Entity Recognition

A Weighted Flat Lattice Transformer-based Knowledge Extracti...

引用

International Conference on Computer Supported Cooperative Work in Design

作者： Hengwei Zhang Yuejia Wu Jian-Tao Zhou Inner Mongolia University College of Computer Science Hohhot China Ministry of Education National & Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian Engineering Research Center of Ecological Big Data Hohhot China Inner Mongolia Engineering Laboratory for Cloud Computing and Service Software Hohhot China Inner Mongolia Key Laboratory of Social Computing and Data Processing Hohhot China Inner Mongolia Key Laboratory of Discipline Inspection and Supervision Big Data Hohhot China Inner Mongolia Engineering Laboratory for Big Data Analysis Technology Hohhot China

ISBN: (数字)9798350349184

ISBN: (纸本)9798350349191

Named Entity Recognition (NER) is one of the contents of Knowledge Extraction (KE) that transforms data into knowledge representation. However, Chinese NER faces the problem of lacking clear word boundaries that limit the effectiveness of the KE. Although the flat lattice Transformer (FLAT) framework, which converts lattice structure into a flat structure including a set of spans, can effectively improve this problem and obtain advanced results, there still exist the problems of insensitivity to entity importance weights and insufficient feature learning. This paper proposes a weighted flat lattice Transformer architecture for Chinese NER, namely WFLAT. The WFLAT first adds a weight matrix into self-attention calculation, which can obtain finer-grained partitioning of entities to improve experimental performance, and then adopts a multi-layer Transformer encoder with each layer using a multi-head self-attention mechanism. Extensive experimental results on benchmarks demonstrate that our proposed KE model can obtain state-of-the-art performance for the Chinese NER task.

关键词： Representation learning Computational modeling Memory management Lattices Named entity recognition Transforms Knowledge representation

来源：评论

学校读者我要写书评

暂无评论

StyleMI: An Image Processing-Based Method for Detecting Unauthorized Style Mimicry in Fine-Tuned Diffusion Models in a More Realistic Scenario

引用

IEEE Access 2025年 13卷 97364-97375页

作者： Xinjun Zhang Shixin Zuo Yu Sang School of Electronics and Information Engineering Liaoning Technical University Huludao China Liaoning Key Laboratory of Radio Frequency and Big Data for Intelligent Applications Liaoning Technical University Huludao Liaoning China

The rapid development of diffusion models and model fine-tuning methods have enabled widespread applications in artistic style mimicry while also leading to significant concerns about copyright infringement. Existing approaches protect artists from unauthorized style mimicry by introducing adversarial examples, watermarks, or membership inference attacks. However, the former two are vulnerable to image pre-processing and unable to be applied to published artworks, while the latter requires access to the target model, which is typically inaccessible in real-world scenarios. To this end, the task of detecting unauthorized style mimicry without access to the target model is formulated into a novel membership inference problem. The key insight is that images generated by a diffusion model inherently carry information of its training dataset. A style comparison-based method is proposed, which consists of a LoRA-based style transfer module and a CLIP-based style extraction and comparison module. The style transfer module first learns the artist’s artistic style, then removes the style of the given image to avoid its influence, and finally transfers the artist’s style to the given image. The style extraction and comparison module utilizes a diffusion model to extract the content information of an image and then remove it in a latent semantic space with the pre-trained CLIP model to acquire style-related features and compare them. Experiments on Stable Diffusion demonstrate the effectiveness of the proposed method. The best result achieved a True Positive Rate of 85%, a False Positive Rate of 0%, an Attack Success Rate of 99.29%, a Precision of 100%, and an Area Under the Curve of 1.

关键词： Diffusion models Training Feature extraction data mining Image synthesis data models Copyright protection Computational modeling Watermarking Perturbation methods

来源：评论

学校读者我要写书评

暂无评论

SSFam: Scribble Supervised Salient Object Detection Family

arXiv

引用

arXiv 2024年

作者： Liu, Zhengyi Deng, Sheng Wang, Xinrui Wang, Linbo Fang, Xianyong Tang, Bin Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and Technology Anhui University Hefei China School of Artificial Intelligence and Big Data Hefei University Hefei China

Scribble supervised salient object detection (SSSOD) constructs segmentation ability of attractive objects from surroundings under the supervision of sparse scribble labels. For the better segmentation, depth and thermal infrared modalities serve as the supplement to RGB images in the complex scenes. Existing methods specifically design various feature extraction and multi-modal fusion strategies for RGB, RGB-Depth, RGB-Thermal, and Visual-Depth-Thermal image input respectively, leading to similar model flood. As the recently proposed Segment Anything Model (SAM) possesses extraordinary segmentation and prompt interactive capability, we propose an SSSOD family based on SAM, named SSFam, for the combination input with different modalities. Firstly, different modal-aware modulators are designed to attain modal-specific knowledge which cooperates with modal-agnostic information extracted from the frozen SAM encoder for the better feature ensemble. Secondly, a siamese decoder is tailored to bridge the gap between the training with scribble prompt and the testing with no prompt for the stronger decoding ability. Our model demonstrates the remarkable performance among combinations of different modalities and refreshes the highest level of scribble supervised methods and comes close to the ones of fully supervised methods. https://***/liuzywen/SSFam Copyright © 2024, The Authors. All rights reserved.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

keypoint-based Progressive Chain-of-Thought Distillation for LLMs

arXiv

引用

arXiv 2024年

作者： Feng, Kaituo Li, Changsheng Zhang, Xiaolu Zhou, Jun Yuan, Ye Wang, Guoren Beijing Institute of Technology China Ant Group China Hebei Province Key Laboratory of Big Data Science and Intelligent Technology China

Chain-of-thought distillation is a powerful technique for transferring reasoning abilities from large language models (LLMs) to smaller student models. Previous methods typically require the student to mimic the step-by-step rationale produced by LLMs, often facing the following challenges: (i) Tokens within a rationale vary in significance, and treating them equally may fail to accurately mimic keypoint tokens, leading to reasoning errors. (ii) They usually distill knowledge by consistently predicting all the steps in a rationale, which falls short in distinguishing the learning order of step generation. This diverges from the human cognitive progression of starting with easy tasks and advancing to harder ones, resulting in sub-optimal outcomes. To this end, we propose a unified framework, called KPOD, to address these issues. Specifically, we propose a token weighting module utilizing mask learning to encourage accurate mimicry of keypoint tokens by the student during distillation. Besides, we develop an in-rationale progressive distillation strategy, starting with training the student to generate the final reasoning steps and gradually extending to cover the entire rationale. To accomplish this, a weighted token generation loss is proposed to assess step reasoning difficulty, and a value function is devised to schedule the progressive distillation by considering both step difficulty and question diversity. Extensive experiments on four reasoning benchmarks illustrate our KPOD outperforms previous methods by a large margin. Copyright © 2024, The Authors. All rights reserved.

关键词： Distillation

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：