检索结果-内蒙古大学图书馆

2025 Design, Automation and Test in Europe Conference, DATE 2025

作者： Liu, Zhouquan Huang, Libo Yang, Ling Chen, Gang Liu, Wei Lai, Mingche Wang, Yongwen College of Computer Science and Technology National University of Defense Technology Changsha China Key Laboratory of Advanced Microprocessor Chips and Systems Changsha China School of Computer Science and Engineering Sun Yat-Sen University Guangzhou China

ISBN: (纸本)9783982674100

Mamba overcomes the quadratic complexity problem inherent in Transformer models while maintaining comparable contextual modeling capabilities. However, Mamba-based foundation models encounter challenges in achieving efficient inference on resource-constrained devices, primarily due to their considerable size. Model compression techniques, such as linear quantization, offer a viable solution to this problem. Nevertheless, the introduction of significant outliers during Mamba's past-state forgetting process can lead to a notable decrease in accuracy when employing linear quantization. To overcome these challenges, this paper introduces the Aggressive Forgetting Strategy (AFS), an innovative and efficient algorithm designed to mitigate the quantization issues caused by outliers in the state forgetting mechanism. AFS incorporates a computation-free approach for handling outliers, facilitating both efficient and accurate linear quantization for Mamba, which is essential for applications in resource-constrained scenarios. By leveraging the AFS strategy, Mamba can perform more efficient inference, while significantly improving the accuracy by up to 21.5× compared to conventional methods. © 2025 EDAA.

关键词： Linearization

来源：评论

学校读者我要写书评

暂无评论

Late Breaking Results: AFS: Improving Accuracy of Quantized Mamba via Aggressive Forgetting Strategy

Late Breaking Results: AFS: Improving Accuracy of Quantized ...

引用

Design, Automation and Test in Europe Conference and Exhibition

作者： Zhouquan Liu Libo Huang Ling Yang Gang Chen Wei Liu Mingche Lai Yongwen Wang College of Computer Science and Technology National University of Defense Technology Changsha China Key Laboratory of Advanced Microprocessor Chips and Systems Changsha China School of Computer Science and Engineering Sun Yat-Sen University Guangzhou China

ISBN: (数字)9783982674100

ISBN: (纸本)9798331534646

关键词： Performance evaluation Quantization (signal) Accuracy Foundation models Logic gates Transformers Inference algorithms Complexity theory Standards Context modeling

来源：评论

学校读者我要写书评

暂无评论

PGNeXt: High-Resolution Salient Object Detection via Pyramid Grafting Network

arXiv

引用

arXiv 2024年

作者： Xia, Changqun Xie, Chenxi He, Zhentao Yu, Tianshu Li, Jia The Peng Cheng Laboratory Shenzhen518055 China The State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing100191 China

We present an advanced study on more challenging high-resolution salient object detection (HRSOD) from both dataset and network framework perspectives. To compensate for the lack of HRSOD dataset, we thoughtfully collect a large-scale high resolution salient object detection dataset, called UHRSD, containing 5,920 images from real-world complex scenarios at 4K-8K resolutions. All the images are finely annotated in pixel-level, far exceeding previous low-resolution SOD datasets. Aiming at overcoming the contradiction between the sampling depth and the receptive field size in the past methods, we propose a novel one-stage framework for HR-SOD task using pyramid grafting mechanism. In general, transformer-based and CNN-based backbones are adopted to extract features from different resolution images independently and then these features are grafted from transformer branch to CNN branch. An attention-based Cross-Model Grafting Module (CMGM) is proposed to enable CNN branch to combine broken detailed information more holistically, guided by different source feature during decoding process. Moreover, we design an Attention Guided Loss (AGL) to explicitly supervise the attention matrix generated by CMGM to help the network better interact with the attention from different branches. Comprehensive experiments on UHRSD and widely-used SOD datasets demonstrate that our method can simultaneously locate salient object and preserve rich details, outperforming state-of-the-art methods. To verify the generalization ability of the proposed framework, we apply it to the camouflaged object detection (COD) task. Notably, our method performs superior to most state-of-the-art COD methods without bells and whistles. © 2024, CC BY.

关键词： Grafting (chemical)

来源：评论

学校读者我要写书评

暂无评论

Strong Stabilization of the Acrobot at the Down–Up Equilibrium Point ⋆

引用

IFAC-PapersOnLine 2023年第2期56卷 9167-9172页

作者： Ziyu Wang Xin Xin Yannian Liu School of Automation Southeast University and Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Nanjing 210096 China Faculty of Computer Science and Systems Engineering Okayama Prefectural University Okayama 719-1197 Japan

In this paper, the strong stabilization of the Acrobot at the Down-Up equilibrium point is addressed, with the first link being downward and the second link being upright. By converting the strong stabilization of the Acrobot at the Down–Up equilibrium point equivalently to the existence and design of a stable stabilizing controller for a fourth-order single-input single-output linear plant with adjustable zeros, a pair of poles on the imaginary axis, and a pair of real poles located symmetrically with respect to the origin, this paper has three main contributions. Firstly, the existence of a stable stabilizing controller for any Acrobot which is linearly controllable at the Down–Up equilibrium point is proved by showing the range of the adjustable zero via adjusting a parameter of the output signal. Secondly, a necessary and sufficient condition on the mechanical parameters of the Acrobot is provided to guarantee the existence of a second-order stable stabilizing controller for the Acrobot around its Down– Up equilibrium point. Thirdly, a direct method is presented to design a second-order stable controller, whose transfer function is preset with three parameters. By utilizing the Liénard– Chipart criterion for a fourth-order polynomial, the necessary and sufficient conditions on these parameters for achieving the strong stabilization are obtained, which are expressed in a cascade form for obtaining these parameters conveniently. A numerical example is presented to validate the effectiveness of the proposed method.

关键词： Robust control strong stabilization underactuated mechanical systems reduced-order controller linear systems

来源：评论

学校读者我要写书评

暂无评论

A Recurrent Neural Network Based Bicriteria Repetitive Motion Collision Avoidance Scheme for Motion Planning of Dual Redundant Manipulators 13

A Recurrent Neural Network Based Bicriteria Repetitive Motio...

引用

13th International Conference on Intelligent Control and Information Processing, ICICIP 2025

作者： Chen, Shirui Gao, Huanli Hu, Shaolin Zhang, Zhijun The School of Automation Science and Engineering South China University of Technology Guangzhou510640 China The School of Automation Guangdong University of Petrochemical Technology Maoming Guangzhou525000 China The Guangzhou Key Laboratory of Brain-Computer Interaction and Applications Guangzhou China The Key Library of Autonomous Systems and Network Control Ministry of Education The School of Automation Science and Engineering South China University of Technology Guangzhou510640 China Guangzhou510555 China The Jiangxi Thousand Talents Plan Nanchang University Nanchang330031 China The College of Computer Science and Engineering Jishou University Jishou416000 China Guangzhou510335 China The Shaanxi Provincial Key Laboratory of Industrial Automation School of Mechanical Engineering Shaanxi University of Technology Hanzhong723001 China The School of Information Science and Engineering Changsha Normal University Changsha410100 China The School of Automation Science and Engineering Maoming525000 China The Institute of Artificial Intelligence and Automation Guangdong University of Petrochemical Technology Maoming525000 China

ISBN: (纸本)9798331516147

To achieve low joint-angle drift and avoid mutual collision between dual redundant manipulators (DRMs) when they are doing collaboration works, a recurrent neural network based bicriteria repetitive motion collision avoidance (BRMCA) scheme is proposed for motion planning of DRMs. By designing a combined optimization objective encompassing both repetitive motion criterion and collision avoidance criterion, the BRMCA scheme has larger feasible region and less constraint contradiction issues compared with traditional inequality constraints based method. Furthermore, by incorporating velocity-level kinematic model and physical limits of DRMs into the scheme, a time varying quadratic programming (TVQP) problem is formulated. The linear variational inequality-based primal–dual neural network (LVI-PDNN) is used to solve the proposed scheme due to the high accuracy and low computation complexity. Finally, through comparison simulations of tracking Circle-shape and C-shape trajectories between BRMCA scheme and minimum velocity norm (MVN) scheme, it exhibits that the proposed BRMCA scheme can achieve low joint-angle drift, collision avoidance and high tracking accuracy when DRMs are doing cooperative tasks. © 2025 IEEE.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

A Synchronous Parallel Method with Parameters Communication Prediction for Distributed Machine Learning 19th

A Synchronous Parallel Method with Parameters Communication...

引用

19th EAI International Conference on Collaborative Computing: Networking, Applications and Worksharing, CollaborateCom 2023

作者： Zeng, Yanguo Xue, Meiting Xu, Peiran Shi, Yukun Zeng, Kaisheng Zhang, Jilin Yue, Lupeng School of Computer Science and Technology Hangzhou Dianzi University Hangzhou310018 China Key Laboratory for Modeling and Simulation of Complex Systems Ministry of Education Hangzhou310018 China Data Security Governance Zhejiang Engineering Research Center Hangzhou310018 China National University of Defense Technology Changsha China School of Cyberspace HangZhou Dianzi University Hangzhou China Department of Computer Science and Technology Tsinghua University Beijing China

ISBN: (纸本)9783031545306

With the development of machine learning technology in various fields, such as medical care, smart manufacturing, etc., the data has exploded. It is a challenge to train a deep learning model for different application domains with large-scale data and limited resources of a single device. The distributed machine-learning technology, which uses a parameter server and multiple clients to train a model collaboratively, is an excellent method to solve this problem. However, it needs much communication between different devices with limited communication resources. The stale synchronous parallel method is a mainstream communication method to solve this problem, but it always leads to high synchronization delay and low computing efficiency as the inappropriate delay threshold value set by the user based on experience. This paper proposes a synchronous parallel method with parameters communication prediction for distributed machine learning. It predicts the optimal timing for synchronization, which can solve the problem of long synchronization waiting time caused by the inappropriate threshold settings in the stale synchronous parallel method. Moreover, it allows fast nodes to continue local training while performing global synchronization, which can improve the resource utilization of work nodes. Experimental results show that compared with the delayed synchronous parallel method, the training time and quality, and resource usage of our method are both significantly improved. © ICST Institute for computer sciences, Social Informatics and Telecommunications engineering 2024.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Text-guided attention is all you need for zero-shot robustness in vision-language models 24

Text-guided attention is all you need for zero-shot robustne...

引用

Proceedings of the 38th International Conference on Neural Information Processing systems

作者： Lu Yu Haiyang Zhang Changsheng Xu School of Computer Science and Engineering Tianjin University of Technology State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation University of Chinese Academy of Sciences

ISBN: (纸本)9798331314385

Due to the impressive zero-shot capabilities, pre-trained vision-language models (e.g. CLIP), have attracted widespread attention and adoption across various domains. Nonetheless, CLIP has been observed to be susceptible to adversarial examples. Through experimental analysis, we have observed a phenomenon wherein adversarial perturbations induce shifts in text-guided attention. Building upon this observation, we propose a simple yet effective strategy: Text-Guided Attention for Zero-Shot Robustness (TGA-ZSR). This framework incorporates two components: the Attention Refinement module and the Attention-based Model Constraint module. Our goal is to maintain the generalization of the CLIP model and enhance its adversarial robustness: The Attention Refinement module aligns the text-guided attention obtained from the target model via adversarial examples with the text-guided attention acquired from the original model via clean examples. This alignment enhances the model's robustness. Additionally, the Attention-based Model Constraint module acquires text-guided attention from both the target and original models using clean examples. Its objective is to maintain model performance on clean samples while enhancing overall robustness. The experiments validate that our method yields a 9.58% enhancement in zero-shot robust accuracy over the current state-of-the-art techniques across 16 datasets. Our code is available at https://***/zhyblue424/TGA-ZSR.

关键词：

来源：评论

学校读者我要写书评

暂无评论

UDT:U-shaped deformable transformer for subarachnoid haemorrhage image segmentation

引用

CAAI Transactions on Intelligence Technology 2024年第3期9卷 756-768页

作者： Wei Xie Lianghao Jin Shiqi Hua Hao Sun Bo Sun Zhigang Tu Jun Liu Hubei Provincial Key Laboratory of Artificial Intelligence and Smart Learning Central China Normal UniversityWuhanChina School of Computer Science Central China Normal UniversityWuhanChina National Language Resources Monitoring and Research Center for Network Media Central China Normal UniversityWuhanChina The First Affiliated Hospital of Dalian Medical University DalianChina State Key Laboratory of Information Engineering in Surveying Mapping and Remote SensingWuhan UniversityWuhanChina Information Systems Technology and Design Pillar Singapore University of Technology and DesignSingaporeSingapore

Subarachnoid haemorrhage(SAH),mostly caused by the rupture of intracranial aneu-rysm,is a common disease with a high fatality *** lesions are generally diffusely distributed,showing a variety of scales with irregular *** complex characteristics of lesions make SAH segmentation a challenging *** cope with these difficulties,a u-shaped deformable transformer(UDT)is proposed for SAH ***,first,a multi-scale deformable attention(MSDA)module is exploited to model the diffuseness and scale-variant characteristics of SAH lesions,where the MSDA module can fuse features in different scales and adjust the attention field of each element dynamically to generate discriminative multi-scale ***,the cross deformable attention-based skip connection(CDASC)module is designed to model the irregular edge char-acteristic of SAH lesions,where the CDASC module can utilise the spatial details from encoder features to refine the spatial information of decoder ***,the MSDA and CDASC modules are embedded into the backbone Res-UNet to construct the proposed *** experiments are conducted on the self-built SAH-CT dataset and two public medical datasets(GlaS and MoNuSeg).Experimental results show that the presented UDT achieves the state-of-the-art performance.

关键词： image segmentation medical image processing

来源：评论

学校读者我要写书评

暂无评论

A Lightweight Encoder-Decoder Framework for Carpooling Route Planning

引用

IEEE Transactions on Mobile Computing 2025年

作者： Gao, Yucen Ma, Li Yu, Zhemeng Zhang, Songjian Gao, Hui Fang, Jun Gao, Xiaofeng Shanghai Jiao Tong University Shanghai Key Laboratory of Scalable Computing and Systems College of Computer Science and Engineering Shanghai200240 China Didi Global Inc. Beijing100190 China

Carpooling Route Planning (CRP) has become an important issue with the growth of low-carbon traffic systems. We investigate a novel, meaningful and challenging scenario for CRP in industry, called Multi-Candidate Carpooling Route Planning (MCRP) problem, where each passenger may have several potential positions to get on and off the car. We surprisingly notice that this problem can be easily generalized for similar services such as express, takeout, or crowdsensing services, which means MCRP is a new fundamental combinatorial optimization problem. Traditional graph search algorithms or indexing methods are usually time and space consuming or perform poorly, which are not suitable for solving the problem. In this paper, we propose an end-to-end encoder-decoder model to plan a route for each many-to-one carpooling order with various data-driven mechanisms such as graph partitioning and feature crossover. The encoder is a filter-integrated Graph Convolution Network with external information fusion combining a supervised pre-training classification task, while the latter mimics a pointer network with a rule-based mask mechanism and a domain feature crossover module. We validate the effectiveness and efficiency of our model based on both synthetic and real-world datasets. Our code is available at https://***/GaoYucen/Lite-GD © 2002-2012 IEEE.

关键词： Network coding

来源：评论

学校读者我要写书评

暂无评论

CREAI 2022 - Preface to the First Workshop on Artificial Intelligence and Creativity 1

CREAI 2022 - Preface to the First Workshop on Artificial Int...

引用

1st Workshop on Artificial Intelligence and Creativity, CREAI 2022

作者： De Filippo, Allegra Milano, Michela Presutti, Valentina Saffiotti, Alessandro Department of Computer Science and Engineering University of Bologna Italy Department of Modern Languages Literature and Cultures University of Bologna Italy AASS Cognitive Robotic Systems Laboratory Örebro University Sweden

In recent years, Artificial Intelligence (AI) has gained increasing popularity in the area of art creation, by demonstrating its great potential. Research in this topic has developed AI systems able to generate creative outputs in fields such as music, painting, games, design and scientific discovery, either autonomously or in collaboration with humans. Therefore, AI also helped to analyze and study the mechanisms of creativity from a broader perspective: from the socio-anthropological to psychological, as well as cognitive impact of the autonomous creative processes of artificial intelligence. These advances are leading to new opportunities research perspectives, while also posing challenging questions related to authorship, integrity, bias and evaluation of AI artistic outputs. CREAI, the workshop on AI and creativity, tries to address these research lines and aims to provide a forum for the AI community to discuss problems, challenges and innovative approaches in the various sub-fields of AI and creativity. © 2021 Copyright for this paper by its authors.

关键词： Artificial intelligence

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：