检索结果-内蒙古大学图书馆

arXiv 2024年

作者： He, Weizhao Zhang, Yang Zhuo, Wei Shen, Linlin Yang, Jiaqi Deng, Songhe Sun, Liang Computer Vision Institute School of Computer Science & Software Engineering Shenzhen University China Shenzhen Institute of Artificial Intelligence and Robotics for Society China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China School of Computer Science University of Nottingham China

Few-shot semantic segmentation (FSS) endeavors to segment unseen classes with only a few labeled samples. Current FSS methods are commonly built on the assumption that their training and application scenarios share similar domains, and their performances degrade significantly while applied to a distinct domain. To this end, we propose to leverage the cutting-edge foundation model, the Segment Anything Model (SAM), for generalization enhancement. The SAM however performs unsatisfactorily on domains that are distinct from its training data, which primarily comprise natural scene images, and it does not support automatic segmentation of specific semantics due to its interactive prompting mechanism. In our work, we introduce APSeg, a novel auto-prompt network for cross-domain few-shot semantic segmentation (CD-FSS), which is designed to be auto-prompted for guiding cross-domain segmentation. Specifically, we propose a Dual Prototype Anchor Transformation (DPAT) module that fuses pseudo query prototypes extracted based on cycle-consistency with support prototypes, allowing features to be transformed into a more stable domain-agnostic space. Additionally, a Meta Prompt Generator (MPG) module is introduced to automatically generate prompt embeddings, eliminating the need for manual visual prompts. We build an efficient model which can be applied directly to target domains without fine-tuning. Extensive experiments on four cross-domain datasets show that our model outperforms the state-of-the-art CD-FSS method by 5.24% and 3.10% in average accuracy on 1-shot and 5-shot settings, respectively. Copyright © 2024, The Authors. All rights reserved.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Machine learning strategies for small sample size in materials science

引用

science China Materials 2025年第2期68卷 387-405页

作者： Qiuling Tao JinXin Yu Xiangyu Mu Xue Jia Rongpei Shi Zhifu Yao Cuiping Wang Haijun Zhang Xingjun Liu School of Materials Science and Engineering and Institute of Materials Genome&Big DataHarbin Institute of TechnologyShenzhenShenzhen 518055China School of Computer Science&Technology Harbin Institute of TechnologyShenzhenShenzhen 518055China Advanced Institute for Materials Research(WPI-AIMR) Tohoku UniversitySendai 980-8577Japan Department of Materials Science and Engineering College of MaterialsXiamen UniversityXiamen 361005China State Key Laboratory of Advanced Welding and Joining Harbin Institute of TechnologyShenzhenShenzhen 518055China

Machine learning (ML) has been widely used todesign and develop new materials owing to its low computational cost and powerful predictive capabilities. In recentyears, the shortcomings of ML in materials science have gradually emerged, with a primary concern being the scarcity ofdata. It is challenging to build reliable and accurate ML modelsusing limited data. Moreover, the small sample size problemwill remain long-standing in materials science because of theslow accumulation of material data. Therefore, it is importantto review and categorize strategies for small-sample learningfor the development of ML in materials science. This reviewsystematically sorts the research progress of small-samplelearning strategies in materials science, including ensemblelearning, unsupervised learning, active learning, and transferlearning. The directions for future research are proposed, including few-shot learning, and virtual sample *** importantly, we emphasize the significance of embedding material domain knowledge into ML and elaborate on thebasic idea for implementing this strategy.

关键词： material design machine learning small sample size few-shot learning material domain knowledge

来源：评论

学校读者我要写书评

暂无评论

Deploying DAPHNE Computational Intelligence on EuroHPC Vega for Benchmarking Randomised Optimisation Algorithms

Deploying DAPHNE Computational Intelligence on EuroHPC Vega ...

引用

International Conference on Broadband Communications for Next Generation Networks and Multimedia Applications (CoBCom)

作者： Aleš Zamuda Mark Dokter Faculty of Electrical Engineering and Computer Science University of Maribor Maribor Slovenia KNOW-CENTER GmbH Research Center for Data-Driven Business & Big Data Analytics Graz Austria

ISBN: (数字)9798350388459

ISBN: (纸本)9798350388466

This paper presents a deployment of DAPHNE (Integrated data Analysis Pipelines for Large-Scale data Management, HPC and Machine Learning) for Computational Intelligence (CI). As CI progresses, e.g. through effort in human societies like the IEEE Computational Intelligence Society (CIS), the latest advances have become more widely popularized. Likewise, with the accessibility of supercomputing resources to advance CI, like with infrastructures such as EuroHPC machines including Vega, this paper demonstrates deployment of Randomised Optimisation Algorithms (ROAs) as a subset of CI algorithms, on EuroHPC Vega. As the Vega is a cluster of distributed nodes, a successful computation on several nodes at once in parallel and concurrently, requires an orchestrated deployment across the nodes, batched using Slurm in this paper. An example ROA benchmarking scenario is then presented in this scope.

关键词： data analysis Pipelines Clustering algorithms Text summarization Machine learning Benchmark testing Timing

来源：评论

学校读者我要写书评

暂无评论

Bilateral Network with Residual U-blocks and Dual-Guided Attention for Real-time Semantic Segmentation

Bilateral Network with Residual U-blocks and Dual-Guided Att...

引用

Chinese Automation Congress (CAC)

作者： Liang Liao Liang Wan Mingsheng Liu Shusheng Li State Key Laboratory of Public Big Data College of Computer Science and Technology Guizhou University Guiyang China School Of Computer Science And Engineering Northeastern Univiversity Shenyang China

When some application scenarios need to use semantic segmentation technology, like automatic driving, the primary concern comes to real-time performance rather than extremely high segmentation accuracy. To achieve a good trade-off between speed and accuracy, two-branch architecture has been proposed in recent years. It treats spatial information and semantics information separately which allows the module to be composed of two networks both not heavy. However, the process of fusing features with two different scales becomes a performance bottleneck for many nowaday two-branch models. In this research, we design a new fusion mechanism for two-branch architecture which is guided by attention computation. To be precise, we use the Dual-Guided Attention (DGA) module we proposed to replace some multi-scale transformations with the calculation of attention which means we only use several attention layers of near linear complexity to achieve performance comparable to frequently-used multi-layer fusion. To ensure that our module can be effective, we use Residual U-blocks (RSU) to build one of the two branches in our networks which aims to obtain better multi-scale features. Extensive experiments on Cityscapes and CamVid dataset show the effectiveness of our method. On Cityscapes, our light version network without pretrain weight can achieve 71.1% mIoU at 163 FPS on a single Nvidia RTX 3070 using full resolution images(1024×2048pix). And the large version can achieve 77.9% mIoU with a speed of 43 FPS which still reaches the real-time criterion. Our code and module has been open sourced at https://***/LikeLidoA/Mymodule.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Rockburst prediction using artificial intelligence techniques:A review

Rock Mechanics Bulletin

引用

Rock Mechanics Bulletin 2024年第3期3卷 1-13页

作者： Yu Zhang Kongyi Fang Manchao He Dongqiao Liu Junchao Wang Zhengjia Guo School of Electrical and Information Engineering Beijing University of Civil Engineering and ArchitectureBeijing100044China Beijing Key Laboratory of Intelligent Processing for Building Big Data Beijing University of Civil Engineering and ArchitectureBeijing100044China State Key Laboratory for Geomechanics and Deep Underground Engineering China University of Mining and TechnologyBeijing100083China Thomas Lord Department of Computer Science University of Southern CaliforniaLos Angeles90007CAUSA

Rockburst is a phenomenon where sudden,catastrophic failure of the rock mass occurs in underground deep regions or areas with high tectonic stress during the excavation *** disasters endanger the safety of people's lives and property,national energy security,and social interests,so it is very important to accurately predict *** rockburst prediction has not been able to find an effective prediction method,and the study of the rockburst mechanism is facing a *** the development of artificial intelligence(AI)techniques in recent years,more and more experts and scholars have begun to introduce AI techniques into the study of the rockburst *** previous research,several scholars have attempted to summarize the application of AI techniques in rockburst ***,these studies either are not specifically focused on reviews of the application of AI techniques in rockburst prediction,or they do not provide a comprehensive *** on the advantages of extensive interdisciplinary research and a deep understanding of AI techniques,this paper conducts a comprehensive review of rockburst prediction methods leveraging AI ***,pertinent definitions of rockburst and its associated hazards are ***,the applications of both traditional prediction methods and those rooted in AI techniques for rockburst prediction are summarized,with emphasis placed on the respective advantages and disadvantages of each ***,the strengths and weaknesses of prediction methods leveraging AI are summarized,alongside forecasting future research trends to address existing challenges,while simultaneously proposing directions for improvement to advance the field and meet emerging demands effectively.

关键词： Rockburst Rockburst prediction Artificial intelligence techniques

来源：评论

学校读者我要写书评

暂无评论

Localization of Image Splicing Under Segment Anything Model With Integrated Compression and Edge Artifacts

Localization of Image Splicing Under Segment Anything Model ...

引用

IEEE International Conference on Image Processing

作者： Ruhao Zhao Xian Zhong Liang Liao Wenxuan Liu Wenxin Huang Zheng Wang School of Computer Science and Artificial Intelligence Hubei Key Laboratory of Transportation Internet of Things Wuhan University of Technology School of Electrical and Electronic Engineering Rapid-Rich Object Search Lab Nanyang Technological University College of Computing and Data Science Nanyang Technological University School of Computer Science and Information Engineering Hubei University School of Computer Science National Engineering Research Center for Multimedia Software Wuhan University

ISBN: (数字)9798350349399

ISBN: (纸本)9798350349405

The localization of image splicing involves identifying pixels in an image that have been spliced from other images, necessitating the discernment of splicing features. Despite significant advancements driven by the rise of social media and deep learning, existing methods exhibit limitations, often neglecting the integration of coarse and precise features and lacking the ability to understand objects. This leads to erroneous predictions in identifying spliced regions. This paper proposes Segment Anything Model with Integrated Compression and Edge artifacts (SAM-ICE) for the localization of image splicing, addressing these limitations by fusing forged edge features and compression artifact features. Leveraging SAM’s object understanding ability, our method identifies spliced regions using the fused features as guidance. Specifically, we employ Edge Artifact Extractor (EAE) to extract fine high-frequency edge splicing features and Compression Artifact Extractor (CAE) to extract coarse compression artifact features. By combining these features, our method utilizes coarse-fine features to accurately pinpoint the spliced portions of the image. Experimental results demonstrate the superior accuracy, robustness, and generalizability of our method compared to the state-of-the-arts.

关键词： Location awareness Image segmentation Image coding Social networking (online) Image edge detection Splicing Feature extraction

来源：评论

学校读者我要写书评

暂无评论

LineConGraphs: Line Conversation Graphs for Effective Emotion Recognition using Graph Neural Networks

引用

IEEE Transactions on Affective Computing 2025年

作者： Krishnan, Gokul S. Padi, Sarala Greenberg, Craig S. Ravindran, Balaraman Manocha, Dinesh Sriram, Ram D. IIT Madras Centre for Responsible AI Wadhwani School of Data Science and AI Chennai India National Institute of Standards and Technology GaithersburgMD United States University of Maryland Computer Science and Engineering College ParkMD United States

Emotion Recognition in Conversations (ERC) is an important aspect of affective computing with practical applications in healthcare, education, chatbots, and social media platforms. Previous approaches to ERC analysis involved using graph neural network architectures to model both speaker and long-term contextual information. In this paper, we introduce new models for ERC analysis: the LineConGCN and LineConGAT models, which are constructed using a graph construction strategy for conversations called line conversational graphs (LineConGraphs). LineConGraph is designed to capture short-term conversational context using one previous and future utterance, while also capturing long-term context using GCN or GAT layers without explicitly integrating into the graph construction strategy. We evaluate the performance of our proposed models on two benchmark datasets, rm IEMOCAP and rm {MELD}$, and show that our LineConGAT model outperforms the state-of-the-art methods with an F1-score of rm 64.58% and rm 76.50%. Furthermore, we demonstrate that incorporating sentiment shift information into line conversation graphs further enhances rm {ERC}$ performance in the case of LineConGCN models. We also evaluate the performance of our proposed model by embedding speaker information into LineConGCN and LineConGAT models and show that LineConGAT and LineConGAT with speaker embeddings performed equally for ERC analysis. © 2010-2012 IEEE.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Hybrid Model for Lung Cancer Prognosis: Integrating SVM and 3D CNN on Nodule data

Hybrid Model for Lung Cancer Prognosis: Integrating SVM and ...

引用

Emerging Research in Computational science (ICERCS), International Conference on

作者： Carmel Mary Belinda M J Kannan E Alex David S Sriram Kannan Ravi Kumar S. Anstey Vathani Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai India Department of Computer Science and Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai India Data Engineering Fidelity Investments Chennai India Department of Civil Engineering Vel Tech Rangarajan Dr Sagunthala RD Institute of Science and Technology

ISBN: (数字)9798331534967

ISBN: (纸本)9798331534974

In this research, a huge dataset of lung cancer images is processed using advanced image processing techniques gathered from different medical establishments. Images will be edited and color profiles retouched from original look into Strawberry corrected one. Key part of our research is to preprocess the images by using Gaussian preprocessing at initial front levels followed with Gabor filtering which improves clarity and focus in x-ray image. Findings also contribute to the field of biomedical science in studies related to lung cancer diagnosis, by proving that advanced image processing techniques are useful. These techniques are essential tools in many medical fields ensuring high quality imaging, which allows early detection and treatment planning. Lung cancer, characterized by rapid uncontrolled proliferation of cells in the lungs with a potential for distant spread either via blood or lymphatic system requires precise diagnostic techniques. After preprocessing, we apply segmentation and enhancement techniques on images to detect the salient features separating normal from affected lung tissues. Extensive experiments are conducted to validate our method compared with other methods using pixel level percentage and mask labels for anomaly detection. This work highlights the importance of a robust imaging approach for health care, especially in biomedical research where various diseases could be detected and treated.

关键词： Image segmentation Three-dimensional displays Lungs Lung cancer Feature extraction Vectors Gabor filters X-ray imaging Medical diagnostic imaging Image enhancement

来源：评论

学校读者我要写书评

暂无评论

AMRDB: Design of an automatic analytical model for density-based clustering using augmented rule mining

AMRDB: Design of an automatic analytical model for density-b...

引用

International Conference on Computing and Networking Technology (ICCNT)

作者： Jayshri Harde Swapnili Karmore Computer Science and Engineering G H Raisoni University Saikheda Sausar India Data Science Department G H Raisoni Institute of Engineering and Technology Nagpur India

Density based clustering (DBC) is an unsupervised learning method which is capable of identifying distinct groups of information. It works on the principle of instance-based variance maximization between distinct groups, while minimizing variance between similar groups of data. DBC models are capable of detecting regions of similar concentrated instances, and discard sparse instances based on pre-set distance ratios. Thus, selection of this distance ratio must be done intelligently in order to perform effective density-based clustering. A wide range of models are proposed for this purpose, but most of them work in a context-dependent manner, thereby limiting their scalability. In order to remove this drawback, an augmented rule mining approach that utilizes a combination of Apriori and frequent pattern growth (FPGrowth) is proposed in this text. The proposed approach initially evaluates minimum support values for Apriori & FPGrowth models via variance-based analytical modelling. Rules for these models are combined using instance-based matching, and are used for parametric tuning of Density-Based Spatial Clustering of Applications with Noise (DBSCAN) model. Due to a combination of Apriori & FPGrowth a large number of rules are extracted in a dataset-independent manner, which assist in optimization of DBSCAN’s inter-class and intra-class variance metrics. The results are compared with various state-of-the-art clustering models, and cluster metrics are evaluated. It is observed that the proposed model outperforms DBSCAN, and other density-based clustering techniques in terms of cluster formation efficiency, scalability and computational complexity on multiple datasets.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Snapshot boosting: a fast ensemble framework for deep neural networks

引用

science China(Information sciences) 2020年第1期63卷 77-88页

作者： Wentao ZHANG Jiawei JIANG Yingxia SHAO Bin CUI Center for Data Science Peking University National Engineering Laboratory for Big Data Analysis and Applications Department of Computer Science Beijing Key Lab of Intelligent Telecommunications Software and Multimedia School of Computer ScienceBeijing University of Posts and Telecommunications Key Lab of High Confidence Software Technologies Department of Computer SciencePeking University

Boosting has been proven to be effective in improving the generalization of machine learning models in many fields. It is capable of getting high-diversity base learners and getting an accurate ensemble model by combining a sufficient number of weak learners. However, it is rarely used in deep learning due to the high training budget of the neural network. Another method named snapshot ensemble can significantly reduce the training budget, but it is hard to balance the tradeoff between training costs and diversity. Inspired by the ideas of snapshot ensemble and boosting, we propose a method named snapshot boosting. A series of operations are performed to get many base models with high diversity and accuracy, such as the use of the validation set, the boosting-based training framework, and the effective ensemble strategy. Last, we evaluate our method on the computer vision(CV) and the natural language processing(NLP) tasks, and the results show that snapshot boosting can get a more balanced trade-off between training expenses and ensemble accuracy than other well-known ensemble methods.

关键词： ensemble learning deep learning boosting neural network snapshot ensemble

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：