检索结果-内蒙古大学图书馆

11th International Conference on Learning Representations, ICLR 2023

作者： Liu, Zhenghao Xiong, Chenyan Lv, Yuanhuiyi Liu, Zhiyuan Yu, Ge Department of Computer Science and Technology Northeastern University Shenyang China Microsoft Research Redmond United States Department of Computer Science and Technology Tsinghua University Beijing China Institute for Artificial Intelligence Tsinghua University Beijing China State Key Lab on Intelligent Technology and Systems Tsinghua University Beijing China

This paper presents Universal vision-Language Dense Retrieval (UniVL-DR), which builds a unified model for multi-modal retrieval. UniVL-DR encodes queries and multi-modality resources in an embedding space for searching candidates from different modalities. To learn a unified embedding space for multi-modal retrieval, UniVL-DR proposes two techniques: 1) Universal embedding optimization strategy, which contrastively optimizes the embedding space using the modality-balanced hard negatives;2) Image verbalization method, which bridges the modality gap between images and texts in the raw data space. UniVL-DR achieves the state-of-the-art on the multi-modal open-domain question answering benchmark, WebQA, and outperforms all retrieval models on the two subtasks, text-text retrieval and text-image retrieval. It demonstrates that universal multi-modal search is feasible to replace the divide-and-conquer pipeline with a united model and also benefits single/cross modality tasks. All source codes of this work are available at https://***/OpenMatch/UniVL-DR. © 2023 11th International Conference on Learning Representations, ICLR 2023. All rights reserved.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

RJoules: An Energy Measurement Tool for R

RJoules: An Energy Measurement Tool for R

引用

IEEE International Conference on Automated Software Engineering (ASE)

作者： Rajrupa Chattaraj Sridhar Chimalakonda Department of Computer Science and Engineering Research in Intelligent Systems and Human Analytics Lab Indian Institute of Technology Tirupati India

With the exponential growth of data, the demand for effective data analysis tools has increased significantly. R language, known for its statistical modeling and data analysis capabilities, has become one of the most popular programming languages among data scientists and researchers. As the importance of energy-aware software systems continues to rise, several studies investigate the impact of source code and different stages of machine learning model training on energy consumption. However, existing studies in this domain primarily focus on programming languages like Python and Java, resulting in a lack of energy measuring tools for other programming languages such as R. To address this gap, we propose “RJoules”, a tool designed to measure the energy consumption of R code snippets. We evaluate the correctness and performance of RJoules by applying it to four machine learning algorithms on three different systems. Our aim is to support developers and practitioners in building energy-aware systems in R. The demonstration of the tool is available at https://***/yMKFuvAM-DE and related artifacts at https://***/RJoules/.

关键词：

来源：评论

学校读者我要写书评

暂无评论

DBJoules: An Energy Measurement Tool for Database Management systems

arXiv

引用

arXiv 2023年

作者： Lella, Hemasri Sai Chattaraj, Rajrupa Manasa, Kurra Chimalakonda, Sridhar Research in Intelligent Systems and Human Analytics Lab Department of Computer Science and Engineering Indian Institute of Technology Tirupati India

In the rapidly evolving landscape of modern data-driven technologies, software relies on large datasets and constant data center operations using various database systems to support computation-intensive tasks. As energy consumption in software systems becomes a growing concern, selecting the right database from energy-efficiency perspective is also critical. To address this, we introduce DBJoules, a tool that measures the energy consumption of activities in database systems. DBJoules supports energy measurement of CRUD operations for four popular databases. Through evaluations on two widely-used datasets, we identify disparities of 7% to 38% in the energy consumption of these databases. Hence, the goal is to raise developer awareness about the effect of running queries in different databases from an energy consumption perspective, enabling them to select appropriate database for sustainable usage. The tool’s demonstration is available at https://***/D1MTZum0jok and related artifacts at https://***/DBJoules/. Copyright © 2023, The Authors. All rights reserved.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

An Efficient Deep Learning Approach to Detect Neurodegenerative Diseases Using Retinal Images

An Efficient Deep Learning Approach to Detect Neurodegenerat...

引用

computer Science and Data Engineering (CSDE), IEEE Asia-Pacific Conference on

作者： Chowdhury Mohammad Irfanuddin Wasique Islam Shafin Koushik Ahmed Md. Hasib Khan Md. Ashraful Alam Rafeed Rahman Shakib Mahmud Dipto Department of Computer Science and Engineering Brac University Dhaka Bangladesh Dept. of CSE Computer Vision and Intelligent Systems (CVIS) Research Lab Brac University Dhaka Bangladesh Department of Computer Science and Engineering University of Liberal Arts Bangladesh (ULAB) Dhaka Bangladesh

Neurodegenerative disorders like Multiple Sclerosis, Parkinson's disease, and Alzheimer's disease typically get diagnosed through brain MRI, CT scans, genetic testing, and various laboratory screening tests that are often tedious, time-consuming, and beyond the reach of the financial capability of many people especially, those living in the developing world. Moreover, they often pose potential hazards for patients with certain pre-existing conditions. To remedy this, we propose an efficient deep-learning approach that enables the detection of such neurodegenerative diseases through retinal images rather than brain images. Our proposed system can proactively detect such disorders simply through retinal scans, which are fast and cost-effective compared to traditional diagnostic approaches, which require expensive and sophisticated equipment. We used a dataset containing retinal cross-sectional images of 21 Multiple Sclerosis patients and 14 healthy individuals for our research, and our model achieved 98.85% accuracy while classifying healthy and diseased individuals from retinal scans.

关键词：

来源：评论

学校读者我要写书评

暂无评论

FedPerfix: Towards Partial Model Personalization of vision Transformers in Federated Learning

FedPerfix: Towards Partial Model Personalization of Vision T...

引用

International Conference on computer vision (ICCV)

作者： Guangyu Sun Matias Mendieta Jun Luo Shandong Wu Chen Chen Center for Research in Computer Vision University of Central Florida USA Intelligent Systems Program University of Pittsburgh USA Department of Radiology Biomedical Informatics and Bioengineering University of Pittsburgh USA

Personalized Federated Learning (PFL) represents a promising solution for decentralized learning in heterogeneous data environments. Partial model personalization has been proposed to improve the efficiency of PFL by selectively updating local model parameters instead of aggregating all of them. However, previous work on partial model personalization has mainly focused on Convolutional Neural Networks (CNNs), leaving a gap in understanding how it can be applied to other popular models such as vision Transformers (ViTs). In this work, we investigate where and how to partially personalize a ViT model. Specifically, we empirically evaluate the sensitivity to data distribution of each type of layer. Based on the insights that the self-attention layer and the classification head are the most sensitive parts of a ViT, we propose a novel approach called FedPerfix, which leverages plugins to transfer information from the aggregated model to the local client as a personalization. Finally, we evaluate the proposed approach on CIFAR-100, OrganAMNIST, and Office-Home datasets and demonstrate its effectiveness in improving the model’s performance compared to several advanced PFL methods. Code is available at https://***/imguangyu/FedPerfix

关键词：

来源：评论

学校读者我要写书评

暂无评论

BotScan: An Unsupervised Bot Detection Based on Adversarial Learning and Social Perception

BotScan: An Unsupervised Bot Detection Based on Adversarial ...

引用

Asian Control Conference

作者： Hong Lin Nuo Chen Yang Chen Xiang Li Cong Li Department of Electronic Engineering Adaptive Networks and Control Lab School of Information Science and Technology Fudan University China Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University China The Institute of Complex Networks and Intelligent Systems Shanghai Research Institute for Intelligent Autonomous Systems Tongji University China

ISBN: (数字)9789887581598

ISBN: (纸本)9798331540845

Within online social networks, the rapid expansion of automated accounts, known as social bots, poses a significant challenge. This dynamic has sparked a strategic contest between bots and detectors. Both sides continually learn and adjust their strategies to gain an edge in this silent war. To effectively manage risks from bot evolution, proactive detection methods have garnered widespread attention. In this work, we propose a graph-based and structure-aware adversarial learning framework for multi-category social bot detection. In detail, we adopt a categorical generative adversarial network to create synthetic evolved bot samples for adversarial learning, aiming to boost the detection performance. Besides, we design a user representation learning module, including local and remote feature extractors to mine neighborhood information and achieve multiple network structure representations. Results demonstrate that our model outperforms state-of-the-art approaches and exhibits strong robustness.

关键词： Representation learning Training Technological innovation Social networking (online) Image edge detection Detectors Feature extraction

来源：评论

学校读者我要写书评

暂无评论

MIXTURE OF EXPERTS MADE PERSONALIZED: FEDERATED PROMPT LEARNING FOR vision-LANGUAGE MODELS

arXiv

引用

arXiv 2024年

作者： Luo, Jun Chen, Chen Wu, Shandong Intelligent Systems Program University of Pittsburgh PittsburghPA15213 United States Intelligent Systems Program Department of Radiology Department of Biomedical Informatics Department of Bioengineering University of Pittsburgh PittsburghPA15213 United States Center for Research in Computer Vision University of Central Florida OrlandoFL32816 United States

Federated prompt learning benefits federated learning with CLIP-like vision-Language Model’s (VLM’s) robust representation learning ability through prompt learning. However, current federated prompt learning methods are habitually restricted to the traditional FL paradigm, where the participating clients are generally only allowed to download a single globally aggregated model from the server. While justifiable for training full-sized models under federated settings, in this work, we argue that this paradigm is ill-suited for lightweight prompts. By facilitating the clients to download multiple pre-aggregated prompts as fixed non-local experts, we propose Personalized Federated Mixture of Adaptive Prompts (pFedMoAP), a novel FL framework that personalizes the prompt learning process through the lens of Mixture of Experts (MoE). pFedMoAP implements a local attention-based gating network that learns to generate enhanced text features for better alignment with local image data, benefiting from both local and downloaded non-local adaptive prompt experts. Extensive experiments on 9 datasets under various federated settings demonstrate the efficacy of the proposed pFedMoAP algorithm. The code is available at https://***/ljaiverson/pFedMoAP. © 2024, CC BY.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Guidance method of simulating weld trajectory between planes based on single-point laser 6

Guidance method of simulating weld trajectory between planes...

引用

6th International Conference on Mechanical, Aeronautical and Automotive Engineering, ICMAA 2022

作者： Chen, Min Ma, Zhiling Chen, Li Chen, Junhong Liu, Yaohui Hunan Engineering Research Center of Advanced Embedded Computing and Intelligent Medical Systems Hunan Chenzhou China School of Computer and Artificial Intelligence Xiangnan University Hunan Chenzhou China Super Accurate Vision Technology Co. Ltd. Guangdong Shenzhen China

In the face of problems such as welding of small objects or too small welding space, an application method of welding small plane intersecting objects based on point laser was proposed. The demonstration points pointing to different planes were preset, and the laser displacement sensor was driven to measure the physical value by simulating the sharp workpiece of the welding gun. Multiple projections at different locations were made on a certain plane of the welding object, so as to ensure that the laser points were not collinear and obtain the laser point parameter set. The plane equation was solved respectively according to the planes pointed by different demonstration points, and a geometric model was built. The equation of the intersecting line between the planes in the welding object was calculated. The points on the line were obtained as the welding start points. The workpiece tip was controlled to move along the intersection direction by the mechanical arm, so as to achieve the weld effect. © Published under licence by IOP Publishing Ltd.

关键词： Welding

来源：评论

学校读者我要写书评

暂无评论

Characterizing and Understanding Development of Social Computing Through DBLP: A Data-Driven Analysis

引用

Journal of Social Computing 2022年第4期3卷 287-302页

作者： Jiaqi Wu Bodian Ye Qingyuan Gong Atte Oksanen Cong Li Jingjing Qu Felicia F.Tian Xiang Li Yang Chen the Shanghai Key Lab of Intelligent Information Processing the School of Computer ScienceFudan UniversityShanghai 200438China the Faculty of Social Sciences Tampere UniversityTampere 33100Finland School of Information Science and Technology Fudan UniversityShanghai 200438China Shanghai Artificial Intelligence Laboratory Shanghai 200232China. School of Social Development and Public Policy Fudan UniversityShanghai 200433China. Institute of Complex Networks and Intelligent Systems Shanghai Research Institute for Intelligent Autonomous SystemsTongji UniversityShanghai 200092China.

During the past decades,the term“social computing”has become a promising interdisciplinary area in the intersection of computer science and social *** this work,we conduct a data-driven study to understand the development of social computing using the data collected from Digital Bibliography and Library Project(DBLP),a representative computer science bibliography *** have observed a series of trends in the development of social computing,including the evolution of the number of publications,popular keywords,top venues,international collaborations,and research *** findings will be helpful for researchers and practitioners working in relevant fields.

关键词： social computing Digital Bibliography and Library Project(DBLP) bibliometric evolution visualization

来源：评论

学校读者我要写书评

暂无评论

Spectroformer: Multi-Domain Query Cascaded Transformer Network For Underwater Image Enhancement

Spectroformer: Multi-Domain Query Cascaded Transformer Netwo...

引用

IEEE Workshop on Applications of computer vision (WACV)

作者： Md Raqib Khan Priyanka Mishra Nancy Mehta Shruti S. Phutke Santosh Kumar Vipparthi Sukumar Nandi Subrahmanyam Murala CVPR Lab School of Computer Science and Statistics Trinity College Dublin Ireland CVPR Lab Indian Institute of Technology Ropar India Computer Vision Lab CAIDAS IFI University of Würzburg Germany Institute for Integrated and Intelligent Systems Griffith Univeristy Australia Indian Institute of Technology Guwahati India

Underwater images often suffer from color distortion, haze, and limited visibility due to light refraction and absorption in water. These challenges significantly impact autonomous underwater vehicle applications, necessitating efficient image enhancement techniques. To address these challenges, we propose a Multi-Domain Query Cascaded Transformer Network for underwater image enhancement. Our approach includes a novel Multi-Domain Query Cascaded Attention mechanism that integrates localized transmission features and global illumination features. To improve feature propagation from the encoder to the decoder, we propose a Spatio-Spectro Fusion-Based Attention Block. Additionally, we introduce a Hybrid Fourier-Spatial Up-sampling Block, which uniquely combines Fourier and spatial upsampling techniques to enhance feature resolution effectively. We evaluate our method on benchmark synthetic and real-world underwater image datasets, demonstrating its superiority through extensive ablation studies and comparative analysis. The testing code is available at: https://***/Mdraqibkhan/Spectroformer.

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：