检索结果-内蒙古大学图书馆

2025 Design, Automation and Test in Europe Conference, DATE 2025

作者： Hung, Jing-Jia Chen, Yi-Jung Cheng, Hsiang-Yun Kao, Hsu Yang, Chia-Lin National Taiwan University Department of Computer Science and Information Engineering Taipei Taiwan National Chi Nan University Department of Computer Science and Information Engineering Nantou Taiwan Academia Sinica Research Center for Information Technology Innovation Taipei Taiwan National Tsing Hua University Department of Engineering and System Science Hsinchu Taiwan

ISBN: (纸本)9783982674100

Incremental Learning (IL) enhances Machine Learning (ML) models over time with new data, ideal for edge devices at the forefront of data collection. However, executing IL on edges faces challenges due to limited resources. Common methods involve IL followed by model pruning or specialized IL methods for edges. However, the former increases training time due to fine-tuning and compromises accuracy for past classes due to limited retained samples or features. Meanwhile, existing edge-specific IL methods utilize weight pruning, which requires specialized hardware or compilers to speed up and cannot reduce computations on general embedded platforms. In this paper, we propose Filter-based Adaptive Model Pruning (FAMP), the first pruning method designed specifically for IL. FAMP prunes the model before the IL process, allowing fine-tuning to occur concurrently with IL, thereby avoiding extended training time. To maintain high accuracy for both new and past data classes, FAMP adapts the compressed model based on observed data classes and retains filter settings from the previous IL iteration to mitigate forgetting. Across all tests, FAMP achieves the best average accuracy, with only a 2.78% accuracy drop over full ML models with IL. Moreover, unlike the common methods that prolong training time, FAMP takes 35% shorter training time on average than using the full ML models for IL. © 2025 EDAA.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhancing Daily Reports: Application of Multimodal GPT for Image Description Generation in Construction Site Quality Assurance

Enhancing Daily Reports: Application of Multimodal GPT for I...

引用

Image Processing Challenges (ICIPC), IEEE International Conference on

作者： Chuan-Yu Chang Abida Khanum Hui-Huang Hsu Ming-Hsiu Tsai Wei-Ting Chen Sheng-Gui Su Intelligent Recognition Industry Service Research Center National Yunlin University of Science and Technology Department of Computer Science Information Engineering Tamkang University Department of Civil Engineering Tamkang University

ISBN: (数字)9798331515942

ISBN: (纸本)9798331515959

In recent years, cutting-edge language models like GPT, TAIDE, LLaMa, and VLM have exhibited remarkable prowess across diverse natural language tasks. This surge in artificial intelligence and computer vision technologies has revolutionized image analysis, offering a fresh and viable approach. Yet, the management and analysis of construction site images persist as formidable challenges in construction projects. While these images harbor valuable insights, conventional manual analysis methods are plagued by inefficiency and error susceptibility. Our study introduces an innovative multimodal approach named Daily Report for Construction Site GPT (DrCS-GPT), designed to navigate the intricacies of building construction sites. The study was initiated by compiling a diverse dataset encompassing visual images and reports from building construction sites in collaboration with CECI engineering Consultants, Inc., Taiwan. In the data acquisition, the focus shifted towards refining our proposed model through pre-training and fine-tuning processes. This model exhibits proficiency in generating high-quality textual content while addressing common issues such as fragmented sentences and word repetition. The methodology entailed dataset assembly, model refinement, and integration with advanced linguistic tools to ensure precision and coherence in scientific communication. Our results underscore the model’s exceptional performance on 1600 images, with inference times of just 0.21s per task.

关键词： computer vision Visualization Image analysis Quality assurance Computational modeling Buildings Refining Security Artificial intelligence Surges

来源：评论

学校读者我要写书评

暂无评论

DarkSAM: fooling segment anything model to segment nothing 24

DarkSAM: fooling segment anything model to segment nothing

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Ziqi Zhou Yufei Song Minghui Li Shengshan Hu Xianlong Wang Leo Yu Zhang Dezhong Yao Hai Jin National Engineering Research Center for Big Data Technology and System and Services Computing Technology and System Lab and Cluster and Grid Computing Lab and School of Computer Science and Technology Huazhong University of Science and Technology School of Cyber Science and Engineering Huazhong University of Science and Technology School of Software Engineering Huazhong University of Science and Technology National Engineering Research Center for Big Data Technology and System and Services Computing Technology and System Lab and Hubei Engineering Research Center on Big Data Security and Hubei Key Laboratory of Distributed System Security and School of Cyber Science and Engineering Huazhong University of Science and Technology School of Information and Communication Technology Griffith University

ISBN: (纸本)9798331314385

Segment Anything Model (SAM) has recently gained much attention for its outstanding generalization to unseen data and tasks. Despite its promising prospect, the vulnerabilities of SAM, especially to universal adversarial perturbation (UAP) have not been thoroughly investigated yet. In this paper, we propose DarkSAM, the first prompt-free universal attack framework against SAM, including a semantic decoupling-based spatial attack and a texture distortion-based frequency attack. We first divide the output of SAM into foreground and background. Then, we design a shadow target strategy to obtain the semantic blueprint of the image as the attack target. DarkSAM is dedicated to fooling SAM by extracting and destroying crucial object features from images in both spatial and frequency domains. In the spatial domain, we disrupt the semantics of both the foreground and background in the image to confuse SAM. In the frequency domain, we further enhance the attack effectiveness by distorting the high-frequency components (i.e., texture information) of the image. Consequently, with a single UAP, DarkSAM renders SAM incapable of segmenting objects across diverse images with varying prompts. Experimental results on four datasets for SAM and its two variant models demonstrate the powerful attack capability and transferability of DarkSAM. Our codes are available at: https://***/CGCL-codes/DarkSAM.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Generative Adversarial Network-Based Approach for Reflective-Metasurface Unit-Cell Synthesis in mmWave Bands

A Generative Adversarial Network-Based Approach for Reflecti...

引用

International Technical Conference o Circuits/Systems, computers and Communications (ITC-CSCC)

作者： Panithan La-aiddee Paramin Sangwongngam Lunchakorn Wuttisittikulkij Pisit Vanichchanunt Department of Electrical Engineering Wireless Communication Ecosystem Research Unit Faculty of Engineering Chulalongkorn University Bangkok Thailand National Electronics and Computer Technology Center (NECTEC) National Science and Technology Development Agency (NSTDA) Pathum Thani Thailand Department of Electrical and Computer Engineering Faculty of Engineering King Mongkut's University of Technology North Bangkok Bangkok Thailand

ISBN: (数字)9798350379051

ISBN: (纸本)9798350379068

In recent years, data-driven design approaches based on generative machine learning (ML) have been applied in the field of metasurface design. Even though generative machine learning has demonstrated remarkable capabilities in metasurface synthesis, training procedures to obtain an appropriate model remain a challenge. In this work, we present the deployment of conditional generative adversarial networks (cGAN) to design reflective standard unit cells for the use of 5G millimeter wave (mm Wave) passive metasurface reflectors. A total of 48 different configurations of cGAN were trained over a range of hyperparameters selected under proper guidelines used in the literature. The design performance of each cGAN configuration is measured by a mean absolute error (MAE) between a simulated reflection phase of a generated unit cell and a target reflection phase. The test results show that cGAN s trained by updating the discriminator one step for each single generator update tend to offer lower MAEs compared to cGANs trained by updating the discriminator three iterations for one generator update. The optimal cGAN among 48 hyperparameter configurations can generate unit cells with reflection phase resembling the desired target one.

关键词： Training Structural rings Phase measurement 5G mobile communication Machine learning Metasurfaces Reflection

来源：评论

学校读者我要写书评

暂无评论

A comprehensive study on Frequent Pattern Mining and Clustering categories for topic detection in Persian text stream

arXiv

引用

arXiv 2024年

作者： Zafarani-Moattar, Elnaz Kangavari, Mohammad Reza Rahmani, Amir Masoud Department of Computer Engineering Science and Research Branch Islamic Azad University Tehran Iran Department of Computer Engineering Iran University of Science and Technology Tehran Iran Future Technology Research Center National Yunlin University of Science and Technology 123 University Road Section 3 Yunlin Douliou64002 Taiwan

Topic detection in social networks is extracting and summarizing frequent posts about an event or subject. Topic detection is a complex process and depends on language because it somehow needs to analyze text. There have been few studies on topic detection in Persian, and the existing algorithms are not remarkable. Therefore, we aimed to study topic detection in Persian. The objectives of this study are: 1) to conduct an extensive study on the best algorithms for topic detection, 2) to identify necessary adaptations to make these algorithms suitable for the Persian language, and 3) to evaluate their performance on Persian social network texts. To achieve these objectives, we have formulated two research questions: First, considering the lack of research in Persian, what modifications should be made to existing frameworks, especially those developed in English, to make them compatible with Persian? Second, how do these algorithms perform, and which one is superior? There are various topic detection methods that can be categorized into different categories. Frequent pattern and clustering are selected for this research, and a hybrid of both is proposed as a new category. Then, ten methods from these three categories are selected. All of them are re-implemented from scratch, changed, and adapted with Persian. These ten methods encompass different types of topic detection methods and have shown good performance in English. The text of Persian social network posts is used as the dataset. Additionally, a new multiclass evaluation criterion, called FS, is used in this paper for the first time in the field of topic detection. Approximately 1.4 billion tokens are processed during experiments. The results indicate that if we are searching for keyword-topics that are easily understandable by humans, the hybrid category is better. However, if the aim is to cluster posts for further analysis, the frequent pattern category is more suitable. © 2024, CC BY-NC-ND.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Attention Feature Fusion and Refinement Network for Point Cloud Upsampling

Hierarchical Attention Feature Fusion and Refinement Network...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Yaori Zhang Shujin Lin Fan Zhou Ruomei Wang National Engineering Research Center of Digital Life School of Computer Science and Engineering Guangdong Provincial Science and Technology Collaborative Innovation Center for Culture and Tourism Sun Yat-sen University Guangzhou China School of Communication and Design Guangdong Key Laboratory for Big Data Analysis and Simulation of Public Opinion Guangdong Provincial Science and Technology Collaborative Innovation Center for Culture and Tourism Sun Yat-sen University Guangzhou China Guangdong Provincial Science and Technology Collaborative Innovation Center for Culture and Tourism National Engineering Research Center of Digital Life School of Computer Science and Engineering Sun Yat-sen University Guangzhou China National Engineering Research Center of Digital Life School of Computer Science and Engineering Sun Yat-sen University Guangzhou China

ISBN: (数字)9798350390155

ISBN: (纸本)9798350390162

This paper presents a novel hierarchical attention feature fusion and refinement network designed to address challenges in existing deep learning based point cloud upsampling methods. The network combines self-attention layers with a multi-level feature extraction architecture, effectively integrating local and global features, thereby enhancing the robustness and uniformity of the point cloud. Furthermore, a spatial refinement module is employed to predict the offset between the generated coarse dense point clouds and real point clouds, thereby enhancing consistency with the ground truth. Concurrently, a filter function is applied in the loss function to handle outliers of generated point clouds. Extensive experimental results across multiple datasets indicate that our method outperforms existing approaches.

关键词： Point cloud compression Deep learning Feature extraction Robustness Encoding

来源：评论

学校读者我要写书评

暂无评论

Fused Gromov-Wasserstein Graph Mixup for Graph-level Classifications

arXiv

引用

arXiv 2023年

作者： Ma, Xinyu Chu, Xu Wang, Yasha Lin, Yang Zhao, Junfeng Ma, Liantao Zhu, Wenwu School of Computer Science Peking University China Department of Computer Science and Technology Tsinghua University China National Research and Engineering Center of Software Engineering Peking University China

Graph data augmentation has shown superiority in enhancing generalizability and robustness of GNNs in graph-level classifications. However, existing methods primarily focus on the augmentation in the graph signal space and the graph structure space independently, neglecting the joint interaction between them. In this paper, we address this limitation by formulating the problem as an optimal transport problem that aims to find an optimal inter-graph node matching strategy considering the interactions between graph structures and signals. To solve this problem, we propose a novel graph mixup algorithm called FGWMixup, which seeks a "midpoint" of source graphs in the Fused Gromov-Wasserstein (FGW) metric space. To enhance the scalability of our method, we introduce a relaxed FGW solver that accelerates FGWMixup by improving the convergence rate from O(t−1) to O(t−2). Extensive experiments conducted on five datasets using both classic (MPNNs) and advanced (Graphormers) GNN backbones demonstrate that FGWMixup effectively improves the generalizability and robustness of GNNs. Codes are available at https://***/ArthurLeoM/FGWMixup. Copyright © 2023, The Authors. All rights reserved.

关键词： Graphic methods

来源：评论

学校读者我要写书评

暂无评论

EventPS: Real-Time Photometric Stereo Using an Event Camera

EventPS: Real-Time Photometric Stereo Using an Event Camera

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Bohan Yu Jieji Ren Jin Han Feishi Wang Jinxiu Liang Boxin Shi National Key Laboratory for Multimedia Information Processing School of Computer Science Peking University National Engineering Research Center of Visual Technology School of Computer Science Peking University School of Mechanical Engineering Shanghai Jiao Tong University Graduate School of Information Science and Technology The University of Tokyo National Institute of Informatics

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Photometric stereo is a well-established technique to es-timate the surface normal of an object. However, the re-quirement of capturing multiple high dynamic range images under different illumination conditions limits the speed and real-time applications. This paper introduces EventPS, a novel approach to real-time photometric stereo using an event camera. Capitalizing on the exceptional temporal resolution, dynamic range, and low bandwidth character-istics of event cameras, EventPS estimates surface nor-mal only from the radiance changes, significantly enhancing data efficiency. EventPS seamlessly integrates with both optimization-based and deep-learning-based photo-metric stereo techniques to offer a robust solution for non-Lambertian surfaces. Extensive experiments validate the effectiveness and efficiency of EventPS compared to frame-based counterparts. Our algorithm runs at over 30 fps in real-world scenarios, unleashing the potential of EventPS in time-sensitive and high-speed downstream applications. 1 1 Code available: https://***/ybh1998/EventPS

关键词： computer vision Image resolution Lighting Bandwidth Cameras Real-time systems Pattern recognition

来源：评论

学校读者我要写书评

暂无评论

A Method for Soybean Germination Rate Detection Based on Image Processing 49

A Method for Soybean Germination Rate Detection Based on Ima...

引用

49th Annual Conference of the IEEE Industrial Electronics Society, IECON 2023

作者： Han, Ru Shu, Lei Yin, Menghan Deng, Der-Jiunn Li, Kailiang Zhang, Jin Yi, Xuefang School of Artificial Intelligence Nanjing Agricultural University China Nanjing Agricultural University NAU-Lincoln Joint Research Center of Intelligent Engineering China School of Engineering University of Lincoln United Kingdom National Changhua University of Education Department of Computer Science and Information Engineering Taiwan China Telecom Hongxin Infomation Technology Company Nanjing China

ISBN: (纸本)9798350331820

As the birthplace of soybeans, China has become the world's largest importer and consumer of soybeans. The supply and demand imbalance of soybeans has become one of the significant food and oil security concerns in *** solve this problem, this paper aims to study a soybean germination rate detection method based on image processing. By replacing manual detection of soybean germination rate and measuring soybean root length with machine-based approaches, basic image processing techniques including grayscale conversion, denoising, binarization, dilation, and erosion are applied to preprocess the images of soybean germination. An improved object detection algorithm is used to extract phenotypic features during soybean germination. The main focus of the study is twofold: (1) Measuring the seed area and the minimum bounding rectangle area of the image regions to determine the germination of seeds by comparing their ratio, thus obtaining the germination rate;(2) Using skeleton extraction and embryo-root separation methods to measure the changes in seed root length during germination, thereby selecting seeds with high vitality and improving the quality of soybean seeds. © 2023 IEEE.

关键词： Germination

来源：评论

学校读者我要写书评

暂无评论

QUALYST: Data Quality Assessment System for Thailand Open Government Data

QUALYST: Data Quality Assessment System for Thailand Open Go...

引用

International Joint Conference on computer Science and Software engineering (JCSSE)

作者： Tanapat Samakit Chutiporn Anutariya Marut Buranarach ICT Department Computer Science & Information Management School of Engineering and Technology Asian Institute of Technology Thailand Data Science and Analytics Research Group National Electronics and Computer Technology Center Thailand

Open Government Data (OGD) refers to the provision of data produced by the government to the general public, in a format that is readily readable and can be used by machines with ease. It can also promote transparency, improve decision-making, enhance accountability, create economic opportunities, and encourage civic engagement. The OGD can help citizens understand the government and its legitimacy and transparency. Thus, when the government shares its data with people, it helps to create trust by being transparent, accountable, and promoting innovative solutions that benefit everyone. However, each published dataset has no indication of its quality assessment at all; thus, making it difficult for citizens to assess the reliability of the data from the OGD. Therefore, a data quality assessment for OGD should be developed. This will help create effective datasets which in turn help users understand the data. This study proposes QUALYST, a system that assesses Thailand's OGD dataset and validates it for analytic and visualization purposes. The study focuses on designing the data storage and implementing the assessment system. Furthermore, the proposed data quality dimensions, the developed data pipeline, and the assessment process are elaborated. Finally, the prototype system is demonstrated using Thailand's OGD datasets with examples in a visualized format.

关键词：

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：