检索结果-内蒙古大学图书馆

SRIF: Data-Free Knowledge Distillation via Stable Regulation and Input Filtering

IEEE Transactions on Multimedia 2025年

作者： Zhang, Zherui Xu, Rongtao Wang, Changwei Xu, Shibiao Zhou, Jie Xu, Wenhao Gao, Longxiang Xu, Wenbo Guo, Li Beijing University of Posts and Telecommunications School of Artificial Intelligence Beijing China Chinese Academy of Sciences State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Beijing China Qilu University of Technology Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Jinan China Shandong Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing Jinan China

Data-free knowledge distillation (DFKD) enables knowledge transfer from a pre-trained teacher to a student network without accessing the real dataset. However, generator-based DFKD methods struggle to ensure that the synthetic images accurately reflect the real dataset distribution. The update of the generator network relies heavily on teacher category guidance, but varying teacher prediction accuracy across categories leads to inconsistent synthetic image quality. Such variations introduce a distribution shift between synthetic and real datasets, negatively impacting student network performance during knowledge distillation. To address this challenge, we propose the SRIF, comprising two components: Student-Driven Flexible Filtering (SDFF) and Re-weighting for Independent Regularization (RIR). SDFF filters out synthetic images affected by the category distribution shift during data generation, producing a more reliable dataset. RIR, applied during distillation, encourages the student to learn stable causal relationships through sample reweighting. Both components flexibly integrate into existing DFKD frameworks, improving performance while reducing training costs. © 1999-2012 IEEE.

关键词： Photointerpretation

来源：评论

学校读者我要写书评

暂无评论

Extending the Quantitative Pattern-Matching Paradigm

arXiv

引用

arXiv 2024年

作者： Alves, Sandra Kesner, Delia Ramos, Miguel DCC FCUP - Faculty of Sciences The University of Porto Portugal CRACS INESC-TEC Center of Advanced Computing Systems Université Paris Cité IRIF CNRS France LIACC - Artificial Intelligence and Computer Science Laboratory Portugal

We show how (well-established) type systems based on non-idempotent intersection types can be extended to characterize termination properties of functional programming languages with pattern matching features. To model such programming languages, we use a (weak and closed) λ-calculus integrating a pattern matching mechanism on algebraic data types (ADTs). Remarkably, we also show that this language not only encodes Plotkin’s CBV and CBN λ-calculus as well as other subsuming frameworks, such as the bang-calculus, but can also be used to interpret the semantics of effectful languages with exceptions. After a thorough study of the untyped language, we introduce a type system based on intersection types, and we show through purely logical methods that the set of terminating terms of the language corresponds exactly to that of well-typed terms. Moreover, by considering non-idempotent intersection types, this characterization turns out to be quantitative, i.e. the size of the type derivation of a term t gives an upper bound for the number of evaluation steps from t to its normal form. © 2024, CC BY-NC-ND.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Multiscale Bilateral Attention Fusion Network for Pansharpening

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第11期5卷 5828-5843页

作者： Guo, Zhongyuan Li, Jiawei Lei, Jia Liu, Jinyuan Zhou, Shihua Wang, Bin Kasabov, Nikola K. Dalian University Key Laboratory of Advanced Design and Intelligent Computing Ministry of Education School of Software Engineering Dalian116622 China University of the Science and Technology Beijing School of Computer and Communication Engineering Beijing100083 China Dalian University of Technology School of Mechanical Engineering Dalian116024 China Auckland University of Technology Knowledge Engineering and Discovery Research Institute Auckland1061 New Zealand University of Ulster Intelligent Systems Research Center LondonderryBT48 7JL United Kingdom Bulgarian Academy of Sciences IICT Sofia1000 Bulgaria

High-resolution multispectral (HRMS) images combine spatial and spectral information originating from panchromatic (PAN) and reduced-resolution multispectral (LRMS) images. Pansharpening performs well and is widely used to obtain HRMS images. However, most pansharpening approaches determine the ratio of PAN and LRMS images through direct interpolation, which may introduce artifacts and distort the color of the fused results. To address this issue, an unsupervised progressive pansharpening framework, MSBANet, is proposed, which adopts a multistage fusion strategy. Each stage contains an attention interactive extraction module (AIEM) and a multiscale bilateral fusion module (MBFM). The AIEM extracts spatial and spectral features from input images and captures the correlations between features. The MBFM can efficiently integrate information from the AIEM and improve MSBANet context awareness. We design a hybrid loss function that enhances the ability of the fusion network to store spectral and texture details. In qualitative and quantitative experimental studies on four datasets, MSBANet outperformed state-of-the-art pansharpening techniques. The code will be released. © 2024 IEEE.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

Nonblocking execution in GraphBLAS

Nonblocking execution in GraphBLAS

引用

IEEE International Symposium on Parallel and Distributed Processing Workshops and Phd Forum (IPDPSW)

作者： Aristeidis Mastoras Sotiris Anagnostidis Albert– Jan N. Yzelman Computing Systems Laboratory Zurich Research Center Huawei Technologies Switzerland Data Analytics Laboratory Department of Computer Science ETH Zurich Switzerland

ISBN: (数字)9781665497473

ISBN: (纸本)9781665497480

GraphBLAS is a recent standard that allows the expression of graph algorithms in the language of linear algebra and enables automatic code parallelization and optimization. GraphBLAS operations are executed either in blocking or in non-blocking mode. Although there exist multiple implementations of GraphBLAS for efficient blocking execution on both shared-and distributed-memory systems, none of these implementations supports full nonblocking execution to improve data locality. In this paper, we present a preliminary evaluation for two algorithms, Pagerank and Conjugate Gradient, that confirms the importance of nonblocking execution, by showing promising speedups over the corresponding blocking execution.

关键词： Analytical models Distributed processing Heuristic algorithms Instruction sets Distributed databases Manuals Linear algebra

来源：评论

学校读者我要写书评

暂无评论

DU-DARTS: Decreasing the Uncertainty of Differentiable Architecture Search 32

DU-DARTS: Decreasing the Uncertainty of Differentiable Archi...

引用

32nd British Machine Vision Conference, BMVC 2021

作者： Lu, Shun Hu, Yu Yang, Longxing Sun, Zihao Mei, Jilin Zeng, Yiming Li, Xiaowei Research Center for Intelligent Computing Systems Institute of Computing Technology Chinese Academy of Sciences China State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences China School of Computer Science and Technology University of Chinese Academy of Sciences China Tecent ADlab China

Differentiable Neural Architecture Search (DARTS) recently attracts a lot of research attention because of its high efficiency. However, the competition of candidate operations in DARTS introduces high uncertainty for selecting the truly important operation, thus leading to serious performance collapse. In this work, we decrease the uncertainty of differentiable architecture search (DU-DARTS) by enforcing the distribution of architecture parameters to approach the one-hot categorical distribution and by replacing the zero operation with a gate switch. Without any extra search cost, our method achieves state-of-the-art performance with 2.32%, 16.74%, and 24.1% test error on CIFAR-10, CIFAR-100, and ImageNet datasets, respectively. Moreover, DU-DARTS can robustly find an excellent architecture on NAS-Bench-1Shot1 and NAS-Bench-201, which further demonstrates the effectiveness of our method. The source code is available at https://***/ShunLu91/DU-DARTS. © 2021. The copyright of this document resides with its authors.

关键词： computer vision

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

TeFF: Tracking-enhanced Forgetting-free Few-shot 3D LiDAR Semantic Segmentation

TeFF: Tracking-enhanced Forgetting-free Few-shot 3D LiDAR Se...

引用

IEEE/RSJ International Conference on Intelligent Robots and systems (IROS)

作者： Junbao Zhou Jilin Mei Pengze Wu Liang Chen Fangzhou Zhao Xijun Zhao Yu Hu Research Center for Intelligent Computing Systems Institute of Computing Technology Chinese Academy of Sciences Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China China North Artificial Intelligence & Innovation Research Institute Collective Intelligence & Collaboration Laboratory (CIC)

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

In autonomous driving, 3D LiDAR plays a crucial role in understanding the vehicle’s surroundings. However, the newly emerged, unannotated objects presents few-shot learning problem for semantic segmentation. This paper addresses the limitations of current few-shot semantic segmentation by exploiting the temporal continuity of LiDAR data. Employing a tracking model to generate pseudo-ground-truths from a sequence of LiDAR frames, our method significantly augments the dataset, enhancing the model’s ability to learn on novel classes. However, this approach introduces a data imbalance biased to novel data that presents a new challenge of catastrophic forgetting. To mitigate this, we incorporate LoRA, a technique that reduces the number of trainable parameters, thereby preserving the model’s performance on base classes while improving its adaptability to novel classes. This work represents a significant step forward in few-shot 3D LiDAR semantic segmentation for autonomous driving. Our code is available at https://***/BowmanChow/Track-no-forgetting.

关键词： Adaptation models Laser radar Three-dimensional displays Codes Semantic segmentation Few shot learning Autonomous vehicles Intelligent robots

来源：评论

学校读者我要写书评

暂无评论

csl-MTFL: Multi-task Feature Learning with Joint Correlation Structure Learning for Alzheimer’s Disease Cognitive Performance Prediction 9th

csl-MTFL: Multi-task Feature Learning with Joint Correlatio...

引用

19th International Conference on Advanced Data Mining and Applications, ADMA 2023

作者： Liang, Wei Zhang, Kai Cao, Peng Liu, Xiaoli Yang, Jinzhu Zaiane, Osmar R. Computer Science and Engineering Northeastern University Shenyang China Key Laboratory of Intelligent Computing in Medical Image of Ministry of Education Northeastern University Shenyang China National Frontiers Science Center for Industrial Intelligence and Systems Optimization Shenyang110819 China DAMO Academy Alibaba Group Hangzhou China Alberta Machine Intelligence Institute University of Alberta EdmontonAB Canada

ISBN: (纸本)9783031466700

Alzheimer’s disease (AD) is a common chronic neurodegenerative disease and the accurate prediction of the clinical cognitive performance is important for diagnosis and treatment. Recently, multi-task feature learning (MTFL) methods with sparsity-inducing regularization have been widely investigated on cognitive performance prediction tasks. Although they have proved to achieve improved performance compared with single-task learning, the major challenges are still not fully resolved. They involve how to capture the non-linear correlation among the tasks or features, and how to introduce the learned correlation for guiding the MTFL learning. To resolve these challenges, we introduce a correlation structure learning method through self-attention learning and sequence learning for jointly capturing the complicated but more flexible relationship for features and tasks, respectively. Moreover, we develop a dual graph regularization to encode the inherent correlation and an efficient optimization algorithm for solving the nonsmooth objective function. Extensive results on the ADNI dataset demonstrate that the proposed joint training framework outperforms existing methods and achieves state-of-the-art prediction performance of AD. Specifically, the proposed algorithm achieves an nMSE (normalized Mean Squared Error)/wR (weighted R-value) of 3.808/0.438, obtaining a relative improvement of 3.84 % /7.35 % compared with the MTFL method. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： Neurodegenerative diseases

来源：评论

学校读者我要写书评

暂无评论

Knowledge Graph Enhanced Large Language Model Editing

arXiv

引用

arXiv 2024年

作者： Zhang, Mengqi Ye, Xiaotian Liu, Qiang Ren, Pengjie Wu, Shu Chen, Zhumin School of Computer Science and Technology Shandong University China School of Computer Science Beijing University of Posts and Telecommunications China Center for Research on Intelligent Perception and Computing State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences China

Large language models (LLMs) are pivotal in advancing natural language processing (NLP) tasks, yet their efficacy is hampered by inaccuracies and outdated knowledge. Model editing emerges as a promising solution to address these challenges. However, existing editing methods struggle to track and incorporate changes in knowledge associated with edits, which limits the generalization ability of post-edit LLMs in processing edited knowledge. To tackle these problems, we propose a novel model editing method that leverages knowledge graphs for enhancing LLM editing, namely GLAME. Specifically, we first utilize a knowledge graph augmentation module to uncover associated knowledge that has changed due to editing, obtaining its internal representations within LLMs. This approach allows knowledge alterations within LLMs to be reflected through an external graph structure. Subsequently, we design a graph-based knowledge edit module to integrate structured knowledge into the model editing. This ensures that the updated parameters reflect not only the modifications of the edited knowledge but also the changes in other associated knowledge resulting from the editing process. Comprehensive experiments conducted on GPT-J and GPT-2 XL demonstrate that GLAME significantly improves the generalization capabilities of post-edit LLMs in employing edited knowledge. Copyright © 2024, The Authors. All rights reserved.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

A Data-Driven Framework for TCP to Achieve Flexible QoS Control in Mobile Data Networks 31

A Data-Driven Framework for TCP to Achieve Flexible QoS Cont...

引用

31st IEEE/ACM International Symposium on Quality of Service, IWQoS 2023

作者： Yao, Jiaqi Liu, Ke Liang, Ting Benson, Theophilus A. Lee, Jack Y. B. Aggarwal, Vaneet Bao, Yungang Chen, Mingyu Henan Institute of Advanced Technology Zhengzhou University China Institute of Computing Technology Cas State Key Lab of Processors Research Center for Advanced Computer Systems China Zhongguancun Laboratory China University of Chinese Academy of Sciences China Carnegie Mellon University United States The Chinese University of Hong Kong Hong Kong Purdue University United States

ISBN: (纸本)9798350399738

Learning-based approaches have shown their great potential to adapt themselves to various environments (e.g., PCC and Sprout). Unfortunately, they do not consistently achieve superior QoS across different network conditions and configurations in mobile networks. Furthermore, although they can offer multiple application objectives by adjusting a preference weight vector, it is challenging for users to accurately express an application objective with a weight vector. In this work, we argue that, if configured correctly, the delay-based TCP scheme can outperform learned ones, and allow users to directly specify their objectives. To this end, we propose Post-QoS Analysis (PQSA), a data-driven framework that trains the key QoS-impacting parameters of the scheme to capture the statistical correlations between QoS objectives, network conditions, and configurations, thereby determining the optimal parameter-set that meets the user-defined QoS objective under different network conditions and configurations. To support this, we enhance conventional delay-based TCP design to develop a Generalized TCP-like Rate controller (GR) by exporting three key parameters. Extensive evaluations show that PQSA-optimized GR outperforms existing schemes in different scenarios consistently, and enables service providers to control the QoS flexibly. © 2023 IEEE.

关键词： Transmission control protocol

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：