检索结果-内蒙古大学图书馆

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Tianqi Li Guansong Pang Xiao Bai Wenjun Miao Jin Zheng State Key Laboratory of Complex & Critical Software Environment School of Computer Science and Engineering Jiangxi Research Institute Beihang University China School of Computing and Information Systems Singapore Management University

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Existing prompt learning methods have shown certain capabilities in Out-of-Distribution (OOD) detection, but the lack of OOD images in the target dataset in their training can lead to mismatches between OOD images and In-Distribution (ID) categories, resulting in a high false positive rate. To address this issue, we introduce a novel OOD detection method, named ‘NegPrompt’, to learn a set of negative prompts, each representing a negative connotation of a given class label, for delineating the boundaries between ID and OOD images. It learns such negative prompts with ID data only, without any reliance on external out-lier data. Further, current methods assume the availability of samples of all ID classes, rendering them ineffective in open-vocabulary learning scenarios where the inference stage can contain novel ID classes not present during training. In contrast, our learned negative prompts are transferable to novel class labels. Experiments on various ImageNet benchmarks show that NegPrompt surpasses state-of-the-art prompt-learning-based OOD detection methods and maintains a consistent lead in hard OOD detection in closed- and open-vocabulary classification scenarios. Code is available at https://***/mala-lab/negprompt.

关键词： Training Learning systems Computer vision Codes Computational modeling Semantics Lead

来源：评论

学校读者我要写书评

暂无评论

BayLing 2: A Multilingual Large Language Model with Efficient Language Alignment

arXiv

引用

arXiv 2024年

作者： Zhang, Shaolei Zhang, Kehao Fang, Qingkai Guo, Shoutao Zhou, Yan Liu, Xiaodong Feng, Yang Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences ICT CAS China Key Laboratory of AI Safety Chinese Academy of Sciences China University of Chinese Academy of Sciences Beijing China Research Center of Distributed Systems Institute of Computing Technology Chinese Academy of Sciences ICT CAS China

Large language models (LLMs), with their powerful generative capabilities and vast knowledge, empower various tasks in everyday life. However, these abilities are primarily concentrated in high-resource languages, leaving low-resource languages with weaker generative capabilities and relatively limited knowledge. Enhancing the multilingual capabilities of LLMs is therefore crucial for serving over 100 linguistic communities worldwide. An intuitive approach to enhance the multilingual capabilities would be to construct instruction data for various languages, but constructing instruction data for over 100 languages is prohibitively costly. In this paper, we introduce BayLing 2, which efficiently transfers generative capabilities and knowledge from high-resource languages to low-resource languages through language alignment. To achieve this, we constructed a dataset of 3.2 million instructions, comprising high-resource language instructions (Chinese and English) and cross-lingual instructions for 100+ languages and performed instruction tuning based on the dataset to facilitate the capability transfer between languages. Using Llama as the foundation model, we developed BayLing-2-7B, BayLing-2-13B, and BayLing-2-8B, and conducted a comprehensive evaluation of BayLing. For multilingual translation across 100+ languages, BayLing shows superior performance compared to open-source models of similar scale. For multilingual knowledge and understanding benchmarks, BayLing achieves significant improvements across over 20 low-resource languages, demonstrating its capability of effective knowledge transfer from high-resource to low-resource languages. Furthermore, results on English benchmarks indicate that BayLing maintains high performance in high-resource languages while enhancing the performance in low-resource languages. Demo2, homepage3, code4 and models5of BayLing are available. © 2024, CC BY-NC-ND.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Transforming Research with Quantum computing

Journal of Economy and Technology

引用

Journal of Economy and Technology 2024年

作者： Sukhpal Singh Gill Rajkumar Buyya School of Electronic Engineering and Computer Science Queen Mary University of London London UK Cloud Computing and Distributed Systems (CLOUDS) Laboratory School of Computing and Information Systems The University of Melbourne Australia

Quantum computing is a novel method of computation that uses the principles of quantum mechanics to handle highly challenging situations in a very short amount of time. Quantum technology has the ability to significantly impact worldwide advancement, even prior to the complete deployment of quantum machines. Quantum technology for communication, computation, and sensors has the capacity to revolutionise many industries, and several nations are making investments in this promising field. This includes research investments from both the public and commercial sectors. This article delves into the recent quantum computing advancements and the potential opportunities made possible by quantum technology in the next few decades. We outline a vision and scientific innovation for embracing the quantum age, as well as explore the pioneering applications of quantum computing. We also highlight software tools and platforms for quantum programming to unlock the power of computing and revolutionize the world. Finally, we identify the groundbreaking impacts of quantum computing on next-generation research and discuss the benefits of unleashing its revolutionary capabilities.

关键词： Quantum computing Quantum Technology Quantum Artificial Intelligence Quantum Machine Learning Quantum cloud computing Quantum Applications Quantum Programming Quantum Simulations Quantum Supermacy

来源：评论

学校读者我要写书评

暂无评论

Efficient Parameter Learning of Bayesian Network with Latent Variables from High-Dimensional Data

Efficient Parameter Learning of Bayesian Network with Latent...

引用

IEEE International Conference on Artificial Intelligence Circuits and systems (AICAS)

作者： Xinran Wu Xiang Chen Kun Yue School of Information Science and Engineering Yunnan University Kunming China Yunnan Key Laboratory of Intelligent Systems and Computing Yunnan University Kunming China

Bayesian network with latent variables (BNLV) plays an important role in the representation of dependence relations and inference of uncertain knowledge with unobserved variables. The variables with large cardinalities in high-dimensional data make it challenging to efficiently learn the large-scaled probability parameters as the conditional probability distributions (CPDs) of BNLV. In this paper, we first propose the multinomial parameter network to parameterize the CPDs w.r.t. latent variables. Then, we extend the M-step of the classic EM algorithm and give the efficient algorithm for parameter learning of BNLV. Experimental results show that our proposed method outperforms some state-of-the-art competitors.

关键词：

来源：评论

学校读者我要写书评

暂无评论

RoSAS: Deep Semi-supervised Anomaly Detection with Contamination-resilient Continuous Supervision

arXiv

引用

arXiv 2023年

作者： Xu, Hongzuo Wang, Yijie Pang, Guansong Jian, Songlei Liu, Ning Wang, Yongjun National Key Laboratory of Parallel and Distributed Computing China College of Computer National University of Defense Technology Hunan Changsha410073 China School of Computing and Information Systems Singapore Management University Singapore178902 Singapore College of Information and Communications National University of Defense Technology Hubei Wuhan430010 China

Semi-supervised anomaly detection methods leverage a few anomaly examples to yield drastically improved performance compared to unsupervised models. However, they still suffer from two limitations: 1) unlabeled anomalies (i.e., anomaly contamination) may mislead the learning process when all the unlabeled data are employed as inliers for model training;2) only discrete supervision information (such as binary or ordinal data labels) is exploited, which leads to suboptimal learning of anomaly scores that essentially take on a continuous distribution. Therefore, this paper proposes a novel semi-supervised anomaly detection method, which devises contamination-resilient continuous supervisory signals. Specifically, we propose a mass interpolation method to diffuse the abnormality of labeled anomalies, thereby creating new data samples labeled with continuous abnormal degrees. Meanwhile, the contaminated area can be covered by new data samples generated via combinations of data with correct labels. A feature learning-based objective is added to serve as an optimization constraint to regularize the network and further enhance the robustness w.r.t. anomaly contamination. Extensive experiments on 11 real-world datasets show that our approach significantly outperforms state-of-the-art competitors by 20%-30% in AUC-PR and obtains more robust and superior performance in settings with different anomaly contamination levels and varying numbers of labeled anomalies. The source code is available at https://***/xuhongzuo/rosas/. © 2023, CC BY.

关键词： Contamination

来源：评论

学校读者我要写书评

暂无评论

Automatic modeling learner’s personality using learning analytics approach in an intelligent Moodle learning platform

引用

Interactive Learning Environments 2023年第5期31卷 2529-2543页

作者： Tlili, Ahmed Denden, Mouna Essalmi, Fathi Jemni, Mohamed Chang, Maiga Kinshuk Chen, Nian-Shing Smart Learning Institute of Beijing Normal University Beijing China Research laboratory of Technologies of Information and Communication & Electrical Engineering (LaTICE) Tunis higher school of engineering (ENSIT) University of Tunis Tunis Tunisia School of Computing and Information Systems Athabasca University Athabasca Canada University of North Texas Denton TX United States Department of Applied Foreign Languages National Yunlin University of Science and Technology Douliou Taiwan

The ability of automatically modeling learners’ personalities is an important step in building adaptive learning environments. Several studies showed that knowing the personality of each learner can make the learning interaction with the provided learning contents and activities within learning systems more effective. However, the traditional method of modeling personality is using self-reports, such as questionnaire, which is subjective and with several limitations. Therefore, this study presents a new unobtrusive method to model the learners’ personalities in an intelligent Moodle (iMoodle) using Learning Analytic (LA) approach with Bayesian network. To evaluate the accuracy of the proposed approach, an experiment was conducted with one hundred thirty-nine learners in a public university. Results showed that recall, precision, F-measure and accuracy values are in acceptance range for three personality dimensions including extraversion, openness, and neuroticism. Moreover, the results showed that the LA approach has a fair agreement with the Big Five Inventory (BFI) in modeling these three personality dimensions. Finally, this study provides several recommendations which can help researchers and practitioners develop effective smart learning environments for both learning and modeling. For example, it is needed to help identify more features of the hardest personality traits, such as agreeableness, using gamification courses. © 2019, © 2019 Informa UK Limited, trading as Taylor & Francis Group.

关键词： assessment learner modeling learning analytics Moodle Personality smart learning

来源：评论

学校读者我要写书评

暂无评论

BFP-Net: Boundary Feature Pyramid for Medical Image Segmentation

BFP-Net: Boundary Feature Pyramid for Medical Image Segmenta...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Shiquan Min Xiang Zhang Shunfang Wang School of Information Science and Engineering Yunnan University Kunming China Yunnan Key Laboratory of Intelligent Systems and Computing Yunnan University Kunming China

In this paper, we propose a novel method, namely boundary feature pyramid network (BFP-Net), which can effectively segment targets with blurred boundaries. Specifically, we first propose a global feature fusion module (GFFM) at the top of BFP-Net to fuse feature maps within different scales. It can learn more global region localization of the target and help the learning of boundaries more effectively. Then, we propose a series of boundary enhancement modules (BEMs) at the decoder to effectively extract and integrate boundary information during the upsampling process, thereby enhancing the ability to capture fine details (such as the boundaries). Furthermore, we introduce a boundary-enhanced composite loss function to effectively segment both the regions and their boundaries within different scales. Finally, extensive experiments on two widely-used datasets demonstrate that BFP-Net is more effective in fusing contextual information and guiding feature map boundaries compared to previous competitive methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Investigating the Performance of ECA-YOLOv5n Model for Appearance Quality Detection in Air Conditioner External Units

Investigating the Performance of ECA-YOLOv5n Model for Appea...

引用

IEEE Conference on Industrial Electronics and Applications (ICIEA)

作者： Zihao Guo Dongyang Li Dongfeng Yuan School of Computing and Information Systems University of Melbourne Melbourne Australia Shandong Key Laboratory of Wireless Communication Technologies Shandong University Jinan China

In an era of rapid technological advancements, keeping up with the iterative updates of factory technology in Intelligent manufacturing presents a daunting challenge. Against this backdrop, this paper investigates the performance of the ECA-YOLOv5n model, a novel approach for appearance quality detection in air conditioner external units. Building upon an open-source dataset, ECA-YOLOv5n model integrates the ECA-Net attention mechanism into the YOLOv5-nano model. ECA-Net effectively captures channel-wise dependencies and studies discriminative features, allowing for seamless integration into the convolutional neural networks of the YOLOv5 architecture without the need for extensive modifications. Furthermore, the efficient channel attention mechanism of ECA-Net demands fewer parameters and computations in comparison to other attention mechanisms, conferring a significant advantage in terms of computational efficiency. Experimental results show that the newly proposed model achieves approximately 98% precision, 99% recall, and 99% mAP on the dataset. The ECA-YOLOv5n model reduces storage usage and minorly increases detection speed in comparison to other YOLO models.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Verify All Traffic: Towards Zero-Trust In-Network Intrusion Detection against Multipath Routing

引用

IEEE Journal on Selected Areas in Communications 2025年第6期43卷 2155-2171页

作者： Zhao, Ziming Li, Zhaoxuan Xie, Xiaofei Liu, Zhipeng Li, Tingting Yu, Jiongchi Zhang, Fan Chen, Binbin School of Software Technology Zhejiang University Ningbo315100 China College of Computer Science and Technology Zhejiang University Hangzhou310027 China ZJU-Hangzhou Global Scientific and Technological Innovation Center 311200 China Key Laboratory of Blockchain and Cyberspace Governance of Zhejiang Province 310027 China Jiaxing Research Institute Zhejiang University 314000 China Zhengzhou Xinda Institute of Advanced Technology Zhengzhou450001 China Singapore State Key Laboratory of Information Security Institute of Information Engineering Chinese Academy of Sciences Beijing100093 China School of Cyber Security UCAS Beijing100049 China School of Computing and Information Systems Singapore Management University Singapore188065 Singapore Advanced Digital Sciences Center Singapore138632 Singapore Singapore University of Technology and Design SingaporeB96049 Singapore

With the popularity of encryption protocols, machine learning (ML)-based traffic analysis technologies have attracted widespread attention. To adapt to modern high-speed bandwidth, recent research is dedicated to advancing zero-trust intrusion detection by offloading feature extraction and model inference into the network dataplane. Especially, with the rise of programmable switches, achieving line-speed ML inference becomes promising. However, existing research only considers a single switch node as a relay to conduct evaluation. This is far from real-world deployments involving multiple switches (given that zero-trust security assumes that threats can originate from anywhere, including within the network), particularly the multi-path routing phenomenon that exists in practice. In this paper, we reveal practical challenges in the context of enabling line-speed model inference in the network dataplane. Furthermore, we propose FCPlane, the forwarding and computing integrated dataplane for zero-trust intrusion detection that aims to enable efficient load balancing while providing reliable traffic analysis results, even against multipath routing. The core idea is to reconcile forwarding and computation to the flowlet level, for which a tailor-made Markov chain model is designed. Based on two public traffic datasets, we evaluate seven state-of-the-art in-network traffic analysis models deployed in four types of topologies (three with multipath routing and one without) to explore performance impact and demonstrate the effectiveness of our proposal. © 1983-2012 IEEE.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

QFaaS: A Serverless Function-as-a-Service Framework for Quantum computing

arXiv

引用

arXiv 2022年

作者： Nguyen, Thanh Hoa Usman, Muhammad Buyya, Rajkumar Laboratory School of Computing and Information Systems The University of Melbourne Australia School of Physics The University of Melbourne Australia

Recent breakthroughs in quantum hardware are creating opportunities for its use in many applications. However, quantum software engineering is still in its infancy with many challenges, especially dealing with the diversity of quantum programming languages and hardware platforms. To alleviate these challenges, we propose QFaaS, a novel Quantum Function-as-a-Service framework, which leverages the advantages of the serverless model and the state-of-the-art software engineering approaches to advance practical quantum computing. Our framework provides essential components of a quantum serverless platform to simplify the software development and adapt to the quantum cloud computing paradigm, such as combining hybrid quantum-classical computation, containerizing functions, and integrating DevOps features. We design QFaaS as a unified quantum computing framework by supporting well-known quantum languages and software development kits (Qiskit, Q#, Cirq, and Braket), executing the quantum tasks on multiple simulators and quantum cloud providers (IBM Quantum and Amazon Braket). This paper proposes architectural design, principal components, the life cycle of hybrid quantum-classical function, operation workflow, and implementation of QFaaS. We present two practical use cases and perform the evaluations on quantum computers and simulators to demonstrate our framework's ability to ease the burden on traditional engineers to expedite the ongoing quantum software transition. © 2022, CC BY.

关键词： Software design

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：