检索结果-内蒙古大学图书馆

37th Conference on Neural Information Processing Systems, NeurIPS 2023

作者： Shi, Lianghe Liu, Weiwei School of Computer Science Wuhan University National Engineering Research Center for Multimedia Software Wuhan University Institute of Artificial Intelligence Wuhan University Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University

ISBN: (纸本)9781713899921

Gradual Domain Adaptation (GDA), in which the learner is provided with additional intermediate domains, has been theoretically and empirically studied in many contexts. Despite its vital role in security-critical scenarios, the adversarial robustness of the GDA model remains unexplored. In this paper, we adopt the effective gradual self-training method and replace vanilla self-training with adversarial self-training (AST). AST first predicts labels on the unlabeled data and then adversarially trains the model on the pseudo-labeled distribution. Intriguingly, we find that gradual AST improves not only adversarial accuracy but also clean accuracy on the target domain. We reveal that this is because adversarial training (AT) performs better than standard training when the pseudo-labels contain a portion of incorrect labels. Accordingly, we first present the generalization error bounds for gradual AST in a multiclass classification setting. We then use the optimal value of the Subset Sum Problem to bridge the standard error on a real distribution and the adversarial error on a pseudo-labeled distribution. The result indicates that AT may obtain a tighter bound than standard training on data with incorrect pseudo-labels. We further present an example of a conditional Gaussian distribution to provide more insights into why gradual AST can improve the clean accuracy for GDA. © 2023 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Model LEGO: Creating Models Like Disassembling and Assembling Building Blocks 38

Model LEGO: Creating Models Like Disassembling and Assemblin...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Hu, Jiacong Gao, Jing Ye, Jingwen Gao, Yang Wang, Xingen Feng, Zunlei Song, Mingli College of Computer Science and Technology Zhejiang University China Robotics Institute School of Computer Science Carnegie Mellon University United States Electrical and Computer Engineering National University of Singapore Singapore School of Software Technology Zhejiang University China State Key Laboratory of Blockchain and Data Security Zhejiang University China Institute of Blockchain and Data Security China Bangsheng Technology Co. Ltd. China

With the rapid development of deep learning, the increasing complexity and scale of parameters make training a new model increasingly resource-intensive. In this paper, we start from the classic convolutional neural network (CNN) and explore a paradigm that does not require training to obtain new models. Similar to the birth of CNN inspired by receptive fields in the biological visual system, we draw inspiration from the information subsystem pathways in the biological visual system and propose Model Disassembling and Assembling (MDA). During model disassembling, we introduce the concept of relative contribution and propose a component locating technique to extract task-aware components from trained CNN classifiers. For model assembling, we present the alignment padding strategy and parameter scaling strategy to construct a new model tailored for a specific task, utilizing the disassembled task-aware components. The entire process is akin to playing with LEGO bricks, enabling arbitrary assembly of new models, and providing a novel perspective for model creation and reuse. Extensive experiments showcase that task-aware components disassembled from CNN classifiers or new models assembled using these components closely match or even surpass the performance of the baseline, demonstrating its promising results for model reuse. Furthermore, MDA exhibits diverse potential applications, with comprehensive experiments exploring model decision route analysis, model compression, knowledge distillation, and more. For more information, please visit https://***/. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

SAM2 for Image and Video Segmentation: A Comprehensive Survey

arXiv

引用

arXiv 2025年

作者： Zhang, Jiaxing Tang, Hao School of Software engineering Sichuan University Chengdu610065 China School of Computer Science Peking University Beijing100871 China

Despite significant advances in deep learning for image and video segmentation, existing models continue to face challenges in cross-domain adaptability and generalization. Image and video segmentation are fundamental tasks in computer vision with wide-ranging applications in healthcare, agriculture, industrial inspection, and autonomous driving. With the advent of large-scale foundation models, SAM2—an improved version of SAM (Segment Anything Model)—has been optimized for segmentation tasks, demonstrating enhanced performance in complex scenarios. However, SAM2’s adaptability and limitations in specific domains require further investigation. This paper systematically analyzes the application of SAM2 in image and video segmentation and evaluates its performance in various fields. We begin by introducing the foundational concepts of image segmentation, categorizing foundation models, and exploring the technical characteristics of SAM and SAM2. Subsequently, we delve into SAM2’s applications in static image and video segmentation, emphasizing its performance in specialized areas such as medical imaging and the challenges of cross-domain adaptability. As part of our research, we reviewed over 200 related papers to provide a comprehensive analysis of the topic. Finally, the paper highlights the strengths and weaknesses of SAM2 in segmentation tasks, identifies the technical challenges it faces, and proposes future development directions. This review provides valuable insights and practical recommendations for optimizing and applying SAM2 in real-world scenarios. Copyright © 2025, 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

Bubble or Not: An Analysis of Ethereum ERC721 and ERC1155 Non-fungible Token Ecosystem

Bubble or Not: An Analysis of Ethereum ERC721 and ERC1155 No...

引用

IEEE International Symposium on Circuits and Systems (ISCAS)

作者： Yixiang Tan Zhiying Wu Jieli Liu Jiajing Wu Ting Chen Kaixin Lin School of Computer Science and Engineering Sun Yat-sen University Guangzhou China School of Software Engineering Sun Yat-sen University Zhuhai China School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China

ISBN: (数字)9798350330991

ISBN: (纸本)9798350331004

The non-fungible token (NFT) is an emergent type of cryptocurrency that has garnered extensive attention since its inception. The uniqueness, indivisibility, and humanistic value of NFTs are the key characteristics that distinguish them from traditional tokens. The market capitalization of NFT reached 21.5 billion USD in 2021, almost 200 times that of all previous transactions. However, the subsequent rapid decline in NFT market fever in the second quarter of 2022 casts doubt on the ostensible boom in the NFT market. To date, there has been no comprehensive and systematic study of the NFT trade market or of the NFT bubble and hype phenomenon. To address this gap, we conduct an in-depth investigation of the entire Ethereum ERC721 and ERC1155 NFT ecosystems by dividing the NFT ecosystem participants into three categories: creators, transferors, and holders, to understand their manipulations of NFTs and infer their intentions. We examine the differences between NFT and ERC20 traders and then analyze the possible reasons behind these differences, leading us to gain insights into the varying degrees of market bubble associated with the two kinds of tokens. Through the construction and analysis of the NFT transfer graph (NTG), we uncover certain anomalous behaviors related to bubbles, along with quantifying the proportion of these anomalous behaviors, to reveal the degree of bubbles within the entire ecosystem.

关键词： Systematics Circuits and systems Ecosystems Feature extraction Cryptocurrency Nonfungible tokens Detection algorithms

来源：评论

学校读者我要写书评

暂无评论

MemHunter: Automated and Verifiable Memorization Detection at Dataset-scale in LLMs

arXiv

引用

arXiv 2024年

作者： Wu, Zhenpeng Lou, Jian Zheng, Zibin Chen, Chuan School of Computer Science and Engineering Sun Yat-sen University China School of Software Engineering Sun Yat-sen University China

Large language models (LLMs) have been shown to memorize and reproduce content from their training data, raising significant privacy concerns, especially with web-scale datasets. Existing methods for detecting memorization are primarily sample-specific, relying on manually crafted or discretely optimized memory-inducing prompts generated on a per-sample basis, which become impractical for dataset-level detection due to the prohibitive computational cost of iterating through all samples. In real-world scenarios, data owners may need to verify whether a susceptible LLM has memorized their dataset, particularly if the LLM may have collected the data from the web without authorization. To address this, we introduce MemHunter, which trains a memory-inducing LLM and employs hypothesis testing to efficiently detect memorization at the dataset level, without requiring sample-specific memory inducing. Experiments on models like Pythia and Llama demonstrate that MemHunter can extract up to 40% more training data than existing methods under constrained time resources and reduce search time by up to 80% when integrated as a plug-in. Crucially, MemHunter is the first method capable of dataset-level memorization detection, providing a critical tool for assessing privacy risks in LLMs powered by large-scale datasets. Copyright © 2024, The Authors. All rights reserved.

关键词： Risk assessment

来源：评论

学校读者我要写书评

暂无评论

Modeling Time Decay Effect in Temporal Knowledge Graphs via Multivariate Hawkes Process

Modeling Time Decay Effect in Temporal Knowledge Graphs via ...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Qianyu Li Jiebin Chen Xiaoli Tang Han Yu Hengjie Song School of Software Engineering South China University of Technology Guangzhou China School of Computer Science and Engineering Nanyang Technological University Singapore

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Knowledge Graph Embedding (KGE) is attracting growing research interest because it offers great flexibility for the manipulation and application of Knowledge Graphs (KGs). However, most existing works focus on static KGE, while temporal KGE is still in its infancy. Recent temporal KGE methods attempt to obtain the long-term dependency of facts in consecutive timestamps by merging historical fact information. However, they ignore the different impacts of historical facts on the current facts due to the time decay effect and heterogeneity of historical facts. To bridge this gap, we formalize the concept of fact formation sequence to describe the evolution of an entity and propose the Modeling Time Decay Effect in Temporal Knowledge Graphs via Multivariate Hawkes Process method (TimeDE). TimeDE uses the Hawkes process to model the time decay effect of historical facts. It also incorporates the attention mechanism based on the score function of static KGE methods to better capture the impacts of heterogeneous historical facts on the current facts. Extensive experiments on the five commonly-used benchmark datasets demonstrate that TimeDE achieves significant improvements in terms of both Mean Reciprocal Rank and Hits@K compared to state-of-the-art methods.

关键词： Knowledge engineering Bridges Attention mechanisms Neural networks Merging Knowledge graphs Benchmark testing

来源：评论

学校读者我要写书评

暂无评论

Problem, Remedy and Item Identification from Maintenance Long Texts 32nd

Problem, Remedy and Item Identification from Maintenance Lon...

引用

32nd European Safety and Reliability Conference, ESREL 2022

作者： Makins, Jordan Aspinall, Melissa Liu, Wei Stewart, Michael Hodkiewicz, Melinda Department of Computer Science and Software Engineering the University of Western Australia Australia Water Corporation Australia School of Mechanical Engineering the University of Western Australia Australia

ISBN: (纸本)9789811851834

Historical maintenance work order (MWO) records contain unstructured data about loss of asset function (problem) and the maintenance actions required to restore or retain function (remedy) of equipment or its components (item). These MWO records also provide structured fields to record, using codes, information of interest to reliability engineers such as the ‘problem’, ‘cause’, and ‘remedy’ for each MWO. However, these codes are often missing or recorded inconsistently by the operators, maintainers, and planners generating the MWOs. This leads to issues when they are later used by reliability engineers for data analysis, troubleshooting, and maintenance strategy effectiveness. This project evaluates the suitability of Named Entity Recognition (NER) to infer structured codes for problem, and remedy, and identify the maintainable item from the unstructured MWO texts, in a consistent way. NER is part of a Technical Language Processing pipeline (TLP) for computer-driven manipulation and interpretation of human language from engineering texts. The TLP pipeline involves collaborative annotation of the 449 unstructured long texts in MWO records to map words to named entities related to semantic concepts in the context of maintenance. This data set is used to train an NER model which is then used to label unseen records from 30,341 historical maintenance work orders from a water utility. Classification accuracy, as measured by F1-score, is 92.5% for item, 75% for problem and 87.5% for remedy. These results confirm the suitability of NER as part of an TLP pipeline to either identify or correct these structured fields automatically, and at scale, on historical work orders. The impact is to improve data quality and hence the productivity of reliability engineers. © 2022 ESREL2022 Organizers. Published by Research Publishing, Singapore.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Arbitrary Scale Super Resolution Network for Satellite Imagery

引用

China Communications 2022年第8期19卷 234-246页

作者： Jing Fang Jing Xiao Xu Wang Dan Chen Ruimin Hu National Engineering Research Center for Multimedia Software School of Computer ScienceWuhan UniversityWuhan 430072China Collaborative Innovation Center of Geospatial Technology Wuhan 430079China National University of Defense Technology Wuhan 430015China

Recently,satellite imagery has been widely applied in many ***,due to the limitations of hardware equipment and transmission bandwidth,the images received on the ground have low resolution and weak *** addition,since ground terminals have various resolutions and real-time playing requirements,it is essential to achieve arbitrary scale super-resolution(SR)of satellite *** this paper,we propose an arbitrary scale SR network for satellite image ***,we propose an arbitrary upscale module for satellite imagery that can map low-resolution satellite image features to arbitrary scale enlarged SR ***,we design an edge reinforcement module to enhance the highfrequency details in satellite images through a twobranch ***,extensive upsample experiments on WHU-RS19 and NWPU-RESISC45 datasets and subsequent image segmentation experiments both show the superiority of our method over the counterparts.

关键词： satellite imagery super resolution arbitrary upscale edge reinforcement video satellite

来源：评论

学校读者我要写书评

暂无评论

Securing Agricultural Communications: Blockchain Integration in UAV Networks for Smart Farming

Securing Agricultural Communications: Blockchain Integration...

引用

IEEE International Conference on Communications Workshops, ICC

作者： Ushasri Peddibhotla Randhir Kumar C.C. Sobin Prabhat Kumar Danish Javeed Najmul Islam Department of Computer Science and Engineering SRM University AP Department of Software Engineering LUT School of Engineering Science LUT University Lappeenranta Finland Software College Northeastern University Shenyang China

ISBN: (数字)9798350304053

ISBN: (纸本)9798350304060

The integration of Unmanned Aerial Vehicles (UAVs) in smart agriculture has significantly enhanced precision farming practices, enabling real-time monitoring and data collection for improved crop management. However, the reliance on wireless communication in UAV networks poses security challenges that can compromise the integrity and confidentiality of sensitive agricultural data. This paper proposes a novel approach to address these concerns through the incorporation of blockchain technology for secure communication in UAV networks deployed for smart agriculture. The proposed system leverages the decentralized and tamper-resistant nature of blockchain to establish a trust-based communication framework. Each UAV node in the network is equipped with a blockchain-enabled communication protocol, ensuring that data exchanges are securely recorded in an immutable ledger. This not only enhances data integrity but also mitigates the risk of unauthorized access and manipulation. To facilitate secure communication, smart contracts are employed to automate and enforce predefined rules governing data transactions within the UAV network. This ensures that only authenticated and authorized entities can access and modify agricultural data, fostering a transparent and accountable ecosystem. Additionally, cryptographic techniques such as public-key encryption enhance the confidentiality of transmitted data, safeguarding sensitive information from eavesdropping and unauthorized interception. The proposed blockchain-enabled secure communication system is further enhanced by incorporating consensus mechanisms that validate and confirm the integrity of data across the network. By doing so, the trustworthiness of the entire UAV network is strengthened, reducing the likelihood of malicious activities and enhancing overall system resilience.

关键词： Smart agriculture Wireless communication Fault tolerance Conferences Smart contracts Public key Autonomous aerial vehicles

来源：评论

学校读者我要写书评

暂无评论

FedIERF: Federated Incremental Extremely Random Forest for Wearable Health Monitoring

引用

Journal of computer science & Technology 2023年第5期38卷 970-984页

作者：胡春雨忽丽莎袁林陆佃杰吕蕾陈益强 Key Laboratory of Computing Power Network and Information Security Ministry of EducationShandong Computer Science Center(National Supercomputer Center in Jinan)Qilu University of Technology(Shandong Academy of Sciences)Jinan 250353China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer ScienceJinan 250000China Shandong Provincial Key Laboratory for Novel Distributed Computer Software Technology Jinan 25000China Institute of Information Technology Hebei University of Economics and BusinessShijiazhuang 050061China School of Information Science and Engineering Shandong Normal UniversityJinan 250358China Institute of Computing Technology Chinese Academy of SciencesBeijing 100190China

Wearable health monitoring is a crucial technical tool that offers early warning for chronic diseases due to its superior portability and low power ***,most wearable health data is distributed across dfferent organizations,such as hospitals,research institutes,and companies,and can only be accessed by the owners of the data in compliance with data privacy *** first challenge addressed in this paper is communicating in a privacy-preserving manner among different *** second technical challenge is handling the dynamic expansion of the federation without model *** address the first challenge,we propose a horizontal federated learning method called Federated Extremely Random Forest(FedERF).Its contribution-based splitting score computing mechanism significantly mitigates the impact of privacy protection constraints on model *** on FedERF,we present a federated incremental learning method called Federated Incremental Extremely Random Forest(FedIERF)to address the second technical *** introduces a hardness-driven weighting mechanism and an importance-based updating scheme to update the existing federated model *** experiments show that FedERF achieves comparable performance with non-federated methods,and FedIERF effectively addresses the dynamic expansion of the *** opens up opportunities for cooperation between different organizations in wearable health monitoring.

关键词： federated learning incremental learning random forest wearable health monitoring

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：