检索结果-内蒙古大学图书馆

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Zhang, Congzhi Zhang, Linhai Wu, Jialong He, Yulan Zhou, Deyu School of Computer Science and Engineering Key Laboratory of Computer Network and Information Integration Ministry of Education Southeast University China Department of Informatics King’s College London United Kingdom The Alan Turing Institute United Kingdom

ISBN: (纸本)157735897X

Despite the notable advancements of existing prompting methods, such as In-Context Learning and Chain-of-Thought for Large Language Models (LLMs), they still face challenges related to various biases. Traditional debiasing methods primarily focus on the model training stage, including approaches based on data augmentation and reweighting, yet they struggle with the complex biases inherent in LLMs. To address such limitations, the causal relationship behind the prompting methods is uncovered using a structural causal model, and a novel causal prompting method based on front-door adjustment is proposed to effectively mitigate LLMs biases. In specific, causal intervention is achieved by designing the prompts without accessing the parameters and logits of LLMs. The chain-of-thought generated by LLM is employed as the mediator variable and the causal effect between input prompts and output answers is calculated through front-door adjustment to mitigate model biases. Moreover, to accurately represent the chain-of-thoughts and estimate the causal effects, contrastive learning is used to fine-tune the encoder of chain-of-thought by aligning its space with that of the LLM. Experimental results show that the proposed causal prompting approach achieves excellent performance across seven natural language processing datasets on both open-source and closed-source LLMs. © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Vision-Language Models are Strong Noisy Label Detectors

arXiv

引用

arXiv 2024年

作者： Wei, Tong Li, Hao-Tian Li, Chun-Shu Shi, Jiang-Xin Li, Yu-Feng Zhang, Min-Ling School of Computer Science and Engineering Southeast University Nanjing China Key Laboratory of Computer Network and Information Integration Southeast University Ministry of Education China National Key Laboratory for Novel Software Technology Nanjing University China School of Artificial Intelligence Nanjing University China

Recent research on fine-tuning vision-language models has demonstrated impressive performance in various downstream tasks. However, the challenge of obtaining accurately labeled data in real-world applications poses a significant obstacle during the fine-tuning process. To address this challenge, this paper presents a Denoising Fine-Tuning framework, called DEFT, for adapting vision-language models. DEFT utilizes the robust alignment of textual and visual features pre-trained on millions of auxiliary image-text pairs to sieve out noisy labels. The proposed framework establishes a noisy label detector by learning positive and negative textual prompts for each class. The positive prompt seeks to reveal distinctive features of the class, while the negative prompt serves as a learnable threshold for separating clean and noisy samples. We employ parameter-efficient fine-tuning for the adaptation of a pre-trained visual encoder to promote its alignment with the learned textual prompts. As a general framework, DEFT can seamlessly fine-tune many pre-trained models to downstream tasks by utilizing carefully selected clean samples. Experimental results on seven synthetic and real-world noisy datasets validate the effectiveness of DEFT in both noisy label detection and image classification tasks. Our source code is available at https://***/HotanLee/DeFT. © 2024, CC BY.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

Optimal dynamic spectrum allocation-assisted latency minimization for multiuser mobile edge computing

引用

Digital Communications and networks 2022年第3期8卷 247-256页

作者： Yang Li Tianshun Wang Yuan Wu Weijia Jia State Key Laboratory of Internet of Things for Smart City University of MacaoTaipaMacaoChina Department of Computer and Information Science University of MacaoTaipaMacaoChina Zhuhai-UM Science and Technology Research Institute Zhuhai519031China BNU-UIC Institute of Artificial Intelligence and Future Networks Beijing Normal University(Zhuhai)Guangdong519087China

Mobile Edge Computing(MEC)has been envisioned as an efficient solution to provide computation-intensive yet latency-sensitive services for wireless *** this paper,we investigate the optimal dynamic spectrum allocation-assisted multiuser computation offloading in MEC for overall latency ***,we first focus on a static multiuser computation offloading scenario and jointly optimize users'offloading decisions,transmission durations,and Edge Servers'(ESs)resource *** to the nonconvexity of our joint optimization problem,we identify its layered structure and decompose it into two problems:a subproblem and a top *** the subproblem,we propose a bisection search-based algorithm to efficiently find the optimal users'offloading decisions and ESs’resource allocations under a given transmission ***,we use a linear search-based algorithm for solving the top problem to obtain the optimal transmission duration based on the result of the ***,after solving the static scenario,we consider a dynamic scenario of multiuser computation offloading with time-varying channels and *** efficiently address this dynamic scenario,we propose a deep reinforcement learning-based online algorithm to determine the near-optimal transmission duration in a real-time *** results are provided to validate our proposed algorithms for minimizing the overall latency in both static and dynamic offloading *** also demonstrate the advantages of our proposed algorithms compared to the conventional multiuser computation offloading schemes.

关键词： Multiuser mobile edge computing Dynamic bandwidth allocation Computation offloading Resource allocations

来源：评论

学校读者我要写书评

暂无评论

New Advanced Computing Architecture for Cryptography Design and Analysis by D-Wave Quantum Annealer

引用

Tsinghua Science and Technology 2022年第4期27卷 751-759页

作者： Xiangmin Ji Baonan Wang Feng Hu Chao Wang Huanguo Zhang College of Computer Information Science Fujian Agriculture and Forestry UniversityFuzhou 350002China School of Cyber Science and Engineering Wuhan UniversityWuhan 430072China College of Computer Science and Technology Shanghai University of Electric PowerShanghai 200090China International Research Laboratory of Specialty Fiber Optics and Advanced Communication Shanghai UniversityShanghai 200444 State Key Laboratory of Cryptology Beijing 100878China laboratory of Specialty Fiber Optics and Optical Access Networks Joint International Research Laboratory of Specialty Fiber Optics and Advanced CommunicationShanghai UniversityShanghai 200444 State Key Laboratory of Cryptology Beijing 100878and also with Center for Quantum ComputingPeng Cheng LaboratoryShenzhen 518000China School of Cyber Science and Engineering Wuhan UniversityWuhan 430072

Universal quantum computers are far from achieving practical *** D-Wave quantum computer is initially designed for combinatorial ***,exploring the potential applications of the D-Wave device in the field of cryptography is of great ***,although we optimize the general quantum Hamiltonian on the basis of the structure of the multiplication table(factor up to 1005973),this study attempts to explore the simplification of Hamiltonian derived from the binary structure of the integers to be factored.A simple factorization on 143 with four qubits is provided to verify the potential of further advancing the integer-factoring ability of the D-Wave ***,by using the quantum computing cryptography based on the D-Wave 2000 Q system,this research further constructs a simple version of quantum-classical computing architecture and a Quantum-Inspired Simulated Annealing(QISA)*** functions and a high-performance platform are introduced,and additional balanced Boolean functions with high nonlinearity and optimal algebraic immunity can be *** comparison between QISA and Quantum Annealing(QA)on six-variable bent functions not only shows the potential speedup of QA,but also suggests the potential of architecture to be a scalable way of D-Wave annealer toward a practical cryptography design.

关键词： Quantum Annealing(QA) factorization Boolean functions brain-inspired cognition

来源：评论

学校读者我要写书评

暂无评论

Timo: In-memory temporal query processing for big temporal data

Timo: In-memory temporal query processing for big temporal d...

引用

作者： Zheng, Xiao Liu, Houkai Wang, Xiujun Wu, Xuangou Yu, Feng School of Computer Science and Technology Anhui University of Technology Maanshan China Institute for Artificial Intelligence Hefei Comprehensive National Science Center Hefei China Anhui Engineering Laboratory for Intelligent Applications and Security of Industrial Internet Anhui University of Technology Anhui Maanshan China School of Computer Science and Engineering & School of Software Guangxi Normal University Guilin China Key Laboratory of Computer Network and Information Integration Southeast University Nanjing China

Today's internet applications generate massive temporal data anywhere and anytime. Although some disk-based temporal systems are currently available, they suffer from poor I/O performance, especially when applied in intelligent applications deployed in the cloud and edge environments. Therefore, how to process temporal operations with low latency and high throughput becomes a crucial problem for efficient data processing. This paper proposes Timo, a distributed in-memory temporal query and analytic model for big temporal data. Firstly, a space-efficient temporal index is proposed to support more efficiently query performance with less memory space than the state-of-art methods. Secondly, based on the temporal locality feature of temporal queries, Timo proposes a partitioner mechanism, which utilizes forward scan algorithm, to improve query throughput. Thirdly, some optimal strategies are proposed to improve the execution process of temporal query and analysis, which reduce intermediate result data size and improve the throughput much further. Lastly, we implement the Timo system on the Apache Spark platform, which extends Spark dataset API with temporal query and analysis API functions for users. Extensive experimental results show that the Timo system outperforms other Spark-based temporal systems in terms of both query latency and throughput. © 2021 John Wiley & Sons, Ltd.

关键词： Data handling

来源：评论

学校读者我要写书评

暂无评论

DM-YOLOv5:An Improved Safety Helmet Detection Algorithm at Complex Construction Scenes

DM-YOLOv5:An Improved Safety Helmet Detection Algorithm at C...

引用

International Conference on computer Supported Cooperative Work in Design

作者： Dexu Yao Aimin Li Deqi Liu Mengfan Cheng Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China

ISBN: (数字)9798350349184

ISBN: (纸本)9798350349191

At complex construction sites, detecting whether workers are wearing safety helmets is often affected by occlusion and sunlight change. In addition, the helmets are relatively small, which can easily lead to missed detection and false detection. This paper proposes an improved YOLOv5 model. Firstly, we added a 152×152 detection layer for scale of small objects, enhancing its feature extraction capabilities. Secondly, we added the Multi-Spectral Channel Attention (MSCA) mechanism to enhance feature learning for small objects, addressing the information loss problem caused by Global Average Pooling (GAP). Finally, different activation functions, bounding box regression loss functions, and post-processing methods were adopted for YOLOv5. The Mish function serves as the activation function to enhance the model’s generalization ability and mitigate the gradient vanishing problem associated with the Leaky Relu function. The CIoU loss was employed as the loss function to improve bounding box regression accuracy and accelerate prediction convergence. DIoU-NMS, instead of NMS, was used as the post-processing method to enhance the filtering ability for prediction boxes of occluded small objects. We tested our algorithm on a dataset with 7000 images and achieved an mAP of 95.1%, surpassing the YOLOv5 model by 2.9%. Our method significantly improves safety helmet detection performance at complex construction scenes.

关键词： YOLO Representation learning Head Filtering Federated learning Prediction algorithms Feature extraction

来源：评论

学校读者我要写书评

暂无评论

An improved Schnorr-based multi-signature scheme with application to blockchain 3

An improved Schnorr-based multi-signature scheme with applic...

引用

3rd IEEE International Conference on Civil Aviation Safety and information Technology, ICCASIT 2021

作者： Li, Chunlan Wu, Yulong Yu, Feng Computer Science and Engineering School of Software Guangxi Normal University Guilin China Key Laboratory of Computer Network and Information Integration Southeast University Nanjing China

ISBN: (纸本)9781665425186

A multi-signature scheme allows a group of signers to jointly generate a signature on a common message, which can be verified by anyone, making the signature more compact. Multi-signature has the advantage of fast verification, and it helps reduce bandwidth and the cost of validation and storage. Recently, the multi-signature has drawn much attention because its advantages are desirable for blockchain and cryptocurrency. However, the traditional Schnorr-based multisignature scheme suffers from an excessive number of communications. This paper proposes an improved Schnorr-based multi-signature scheme ASMS, which reduces one round of communication in a traditional scheme, supporting public key aggregation. Thus, it is suitable for e-business and e-government affairs scenarios. As an application, we implemented our solution in Fabric, an enterprise blockchain platform, using chaincode technology. © 2021 IEEE

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Smartphone-based colorimetric detection of formaldehyde in the air

引用

Building Simulation 2024年第11期17卷 2007-2015页

作者： Meng Yang Jin Ye Tao Yu Ying Song Hua Qian Tianyi Liu Yang Chen Junqi Wang Shi-jie Cao Cong Liu School of Energy and Environment Southeast UniversityNanjing210096China School of Energy and Power Jiangsu University of Science and TechnologyZhenjiangJiangsu212100China Wuhan Second Ship Design and Research Institute Wuhan430205China Hubei Provincial Engineering and Technology Research Center for Food Quality and Safety Test Hubei Provincial Institute for Food Supervision and TestWuhan430075China Laboratory of Image Science and Technology the School of Computer Science and EngineeringSoutheast UniversityNanjingChina Jiangsu Provincial Joint International Research Laboratory of Medical Information Processing Southeast UniversityNanjingChina School of Cyber Science and Engineering Southeast UniversityNanjingChina Key Laboratory of Computer Network and Information Integration Southeast UniversityMinistry of EducationNanjingChina School of Architecture Southeast UniversityNanjingChina Jiangsu Province Engineering Research Center of Urban Heat and Pollution Control Southeast UniversityNanjingChina Global Centre for Clean Air Research(GCARE) University of SurreyGuildfordUK

Adverse impacts of exposure to formaldehyde on human health significantly increases attention in monitoring formaldehyde concentrations in the *** formaldehyde detection methods typically rely on large and costly instruments and requires high skills of expertise,preventing it from being widely accessible to *** study introduced a novel approach utilizing smartphone-based colorimetric *** of green channel signals of digital images by a smartphone successfully capture variation of purple color of 4-amino-3-hydrazino-5-mercapto-1,2,4-triazol solution,which is proportional to formaldehyde *** is because that green and purple are complimentary color pairs.A calibration curve was established between green channel signals and formaldehyde concentrations,with a correlation coefficient of *** limit of the smartphone-based method is 0.008 mg/m^(3).Measurement errors decrease as formaldehyde concentrations increase,with median relative errors of 34%,17%,and 6%for concentration ranges of 0–0.06 mg/m^(3),0.06–0.12 mg/m^(3),and 0.12–0.35 mg/m^(3),*** method replaced scientific instrumentation with ordinary items,greatly reducing cost and operation *** would provide an opportunity to realize onsite measurements for formaldehyde by occupants themselves and increase awareness of air quality for better health protection.

关键词： indoor air quality VOC RGB color identification machine vision

来源：评论

学校读者我要写书评

暂无评论

Deep Convolutional Dictionary Learning Network for Sparse View Ct Reconstruction with a Group Sparse Prior

SSRN

引用

SSRN 2023年

作者： Kang, Yanqin Liu, Jin Wu, Fan Wang, Kun Qiang, Jun Hu, Dianlin Zhang, Yikun College of Computer and Information Anhui Polytechnic University Wuhu China Key Laboratory of Computer Network and Information Integration Southeast University Ministry of Education Nanjing China School of Computer Science and Engineering Southeast University Nanjing China

Purpose: Many deep learning-based methods have been applied in sparse view computed tomography (CT) imaging. However, most methods are built intuitively using state-of-the-art black-box convolutional neural networks (CNNs) and lack interpretability. Moreover, CNNs tend to focus on local receptive fields, neglecting nonlocal self-similarity prior information. How to obtain diagnostically useful images from sparsely sampled projections is a challenging, ill-posed ***: To address this issue, we propose a novel interpretable model based on a convolutional dictionary learning network and nonlocal group sparse prior, called DCDL-GS, for sparse view CT image reconstruction. We apply a statistical iterative reconstruction algorithm for a fixed number of iterations with a neural network to improve the image reconstruction quality. Inspired by a group sparsity prior, we adopt a novel group thresholding operation to improve the feature representation and constraint ability and obtain a theoretical interpretation. Additionally, filtered backprojection (FBP) reconstruction, fast sliding window nonlocal self-similarity operations, and a lightweight convolutional dictionary learning network are integrated into our DCDL-GS model, improving model ***: The visual results based on the LDCT-P and UIH datasets show the efficiency of our proposed DCDL-GS model in edge preservation and feature recovery. The quantitative results show improvement over state-of-the-art methods, with improvements of 0.6-0.8 dB for the peak signal-to-noise ratio (PSNR), 0.005-0.01 for the structural similarity index measure (SSIM), and 1-1.3 for the regulated Fréchet inception distance (rFID) based on the test dataset. The quantitative results also show the effectiveness of our proposed deep convolution iterative reconstruction module and nonlocal group sparse ***: We developed a unified optimized mathematical model incorporating projection data and image prior knowled

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

FSD-YOLO: An Improved Method for Steel Surface Defect Detection Based on YOLOv5

FSD-YOLO: An Improved Method for Steel Surface Defect Detect...

引用

International Conference on computer Supported Cooperative Work in Design

作者： Yuechen Zhang Aimin Li Xiaotong Kong Wenqiang Li Zhiyao Li Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China

ISBN: (数字)9798350349184

ISBN: (纸本)9798350349191

Steel surface defect detection is very important in industrial quality inspection, and there have been many studies on Steel surface defect detection in recent years. Existing steel surface defect detection algorithms suffer from low detection accuracy and high model complexity. To improve the above problems, this paper proposes an optimized target detection algorithm based on YOLOv5. Firstly, the original spatial pyramid pooling (SPP) module is replaced by the SPPFCSPC module to better capture the target and scene information at different scales, and to improve the sensory field and feature expression ability of the model. Secondly, we propose the C2F-Faster module based on FasterNet and C2F module to replace the C3 module of the backbone network, which perfectly integrates the ideas of PConv and ELAN and ensures the detection accuracy while effectively reducing the model size. Finally, the Dynamic Head detection head is fused in the head of the model to improve the detection capability of the target detection head using the separated attention mechanism. We conducted experimental validation on the widely used NEU-DET dataset. The experimental results show that the improved model improves the original YOLOv5 model over the original YOLOv5 model by 3.6% in mAP @50 , 9.9% and 2.8% in AP and AR, respectively, and the amount of model parameters is reduced by 13.2%. The improved model also outperforms SSD, FasterRCNN, YOLOv5, YOLOv6, YOLOv7, YOLOv8 and other mainstream target detection models, which better meets the requirements of actual industrial production on the accuracy and speed of steel surface defects detection model.

关键词： YOLO Accuracy Attention mechanisms Computational modeling Heuristic algorithms Inspection Data models

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：