检索结果-内蒙古大学图书馆

Gradient-Based Differential kWTA Network With Application to Competitive Coordination of Multiple Robots

IEEE/CAA Journal of Automatica Sinica 2022年第8期9卷 1452-1463页

作者： Mei Liu Xiaoyan Zhang Mingsheng Shang Long Jin School of Information Science and Engineering Lanzhou UniversityLanzhou 730000 State Key Laboratory of Tibetan Intelligent Information Processing and Application Xining 810016China Chongqing Key Laboratory of Big Data and Intelligent Computing Chongqing Institute of Green and Intelligent TechnologyChinese Academy of SciencesChongqing 400714China Shenzhen Research Institute Lanzhou UniversityShenzhen 518063China

Aiming at the k-winners-take-all(kWTA)operation,this paper proposes a gradient-based differential kWTA(GDk WTA)*** obtaining the network,theorems and related proofs are provided to guarantee the exponential convergence and noise resistance of the proposed GD-kWTA ***,numerical simulations are conducted to substantiate the preferable performance of the proposed network as compared with the traditional ***,the GD-k WTA network,backed with a consensus filter,is utilized as a robust control scheme for modeling the competition behavior in the multi-robot coordination,thereby further demonstrating its effectiveness and feasibility.

关键词： Consensus filter k-winners-take-all(kWTA) multirobot coordination noise resistance

来源：评论

学校读者我要写书评

暂无评论

In-Context Compositional Generalization for Large Vision-Language Models

In-Context Compositional Generalization for Large Vision-Lan...

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Li, Chuanhao Jing, Chenchen Li, Zhen Zhai, Mingliang Wu, Yuwei Jia, Yunde Beijing Key Laboratory of Intelligent Information Technology School of Computer Science & Technology Beijing Institute of Technology China Guangdong Laboratory of Machine Perception and Intelligent Computing Shenzhen MSU-BIT University China School of Computer Science Zhejiang University Hangzhou China

ISBN: (纸本)9798891761643

Recent work has revealed that in-context learning for large language models exhibits compositional generalization capacity, which can be enhanced by selecting in-context demonstrations similar to test cases to provide contextual information. However, how to exhibit in-context compositional generalization (ICCG) of large vision-language models (LVLMs) is non-trival. Due to the inherent asymmetry between visual and linguistic modalities, ICCG in LVLMs faces an inevitable challenge-redundant information on the visual modality. The redundant information affects in-context learning from two aspects: (1) Similarity calculation may be dominated by redundant information, resulting in sub-optimal demonstration selection. (2) Redundant information in in-context demonstrations brings misleading contextual information to in-context learning. To alleviate these problems, we propose a demonstration selection method to achieve ICCG for LVLMs, by considering two key factors of demonstrations: content and structure, from a multimodal perspective. Specifically, we design a diversity-coverage-based matching score to select demonstrations with maximum coverage, and avoid selecting demonstrations with redundant information via their content redundancy and structural complexity. We build a GQA-ICCG dataset to simulate the ICCG setting, and conduct experiments on GQA-ICCG and the VQA v2 dataset. Experimental results demonstrate the effectiveness of our method. © 2024 Association for Computational Linguistics.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

Controlled-source electromagnetic noise attenuation via a deep convolutional neural network and high-quality sounding curve screening mechanism

引用

Geophysics 2025年第3期90卷 WA125-WA140页

作者： Liu, Yecheng Li, Diquan Li, Jin Zhang, Xian Central South University Monitoring Ministry of Education Key Laboratory of Metallogenic Prediction of Nonferrous Metals and Geological Environment Changsha China Hunan Provincial Key Laboratory of Non-ferrous Resources and Geological Hazard Detection Changsha China Central South University School of Geoscience and Info-physics Changsha China Hunan Normal University College of Information Science and Engineering Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing Changsha China Hunan University of Finance and Economics School of Information Technology and Management Hunan Provincial Key Laboratory of Finance & Economics Big Data Science and Technology Changsha China

Strong noise is one of the biggest challenges in controlled-source electromagnetic (CSEM) exploration, which severely affects the quality of the recorded signal. We develop a novel and effective CSEM noise attenuation method that integrates a deep convolutional neural network (DCNN) with a high-quality sounding curve screening mechanism. This method first uses a DCNN to learn the large-scale noise characteristics of CSEM measured data and build a DCNN denoising model for attenuating the noise. Because some impulse noise remains after DCNN denoising, the high-quality sounding curve screening mechanism is innovatively applied to optimize the DCNN denoised data. The core of this method is the smoothness value (SV), which quantitatively evaluates the smoothness of the sounding curve (apparent resistivity curve). In effect, the mechanism segments the overall DCNN denoised data and calculates the corresponding sounding curve and its SV for each segment. The highest-quality sounding curve can be screened out by comparing the SVs of all curves as well as obtaining the highest-quality data segment present in the overall DCNN denoised data. Finally, our method is validated with synthetic and field data, demonstrating its feasibility and effectiveness in attenuating large-scale CSEM noise. The quality of CSEM data, which is heavily affected by noise, is significantly improved after processing by our method. © 2025 Society of Exploration Geophysicists. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

From Missing Pieces to Masterpieces: Image Completion with Context-Adaptive Diffusion

引用

IEEE Transactions on Pattern Analysis and Machine Intelligence 2025年第07期47卷 6073-6087页

作者： Shamsolmoali, Pourya Zareapoor, Masoumeh Zhou, Huiyu Felsberg, Michael Tao, Dacheng Li, Xuelong University of York Department of Computer Science United Kingdom University of Leicester School of Computing and Mathematical Sciences United Kingdom Linkoping University Computer Vision Laboratory Sweden Nanyang Technological University College of Computing & Data Science Singapore China Northwestern Polytechnical University Key Laboratory of Intelligent Interaction and Applications Ministry of Industry and Information Technology Xi'an China

Image completion is a challenging task, particularly when ensuring that generated content seamlessly integrates with existing parts of an image. While recent diffusion models have shown promise, they often struggle with maintaining coherence between known and unknown (missing) regions. This issue arises from the lack of explicit spatial and semantic alignment during the diffusion process, resulting in content that does not smoothly integrate with the original image. Additionally, diffusion models typically rely on global learned distributions rather than localized features, leading to inconsistencies between the generated and existing image parts. In this work, we propose ConFill, a novel framework that introduces a Context-Adaptive Discrepancy (CAD) model to ensure that intermediate distributions of known and unknown regions are closely aligned throughout the diffusion process. By incorporating CAD, our model progressively reduces discrepancies between generated and original images at each diffusion step, leading to contextually aligned completion. Moreover, ConFill uses a new Dynamic Sampling mechanism that adaptively increases the sampling rate in regions with high reconstruction complexity. This approach enables precise adjustments, enhancing detail and integration in restored areas. Extensive experiments demonstrate that ConFill outperforms current methods, setting a new benchmark in image completion. © 1979-2012 IEEE.

关键词： Computer aided design

来源：评论

学校读者我要写书评

暂无评论

Speculative Decoding with CTC-based Draft Model for LLM Inference Acceleration 38

Speculative Decoding with CTC-based Draft Model for LLM Infe...

引用

38th Conference on Neural information Processing Systems, NeurIPS 2024

作者： Wen, Zhuofan Gui, Shangtong Feng, Yang Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China State Key Lab of Processors Institute of Computing Technology Chinese Academy of Sciences China Key Laboratory of Al Safety Chinese Academy of Sciences China University of Chinese Academy of Sciences Beijing China

Inference acceleration of large language models (LLMs) has been put forward in many application scenarios and speculative decoding has shown its advantage in addressing inference acceleration. Speculative decoding usually introduces a draft model to assist the base LLM where the draft model produces drafts and the base LLM verifies the draft for acceptance or rejection. In this framework, the final inference speed is decided by the decoding speed of the draft model and the acceptance rate of the draft provided by the draft model. Currently the widely used draft models usually generate draft tokens for the next several positions in a non-autoregressive way without considering the correlations between draft tokens. Therefore, it has a high decoding speed but an unsatisfactory acceptance rate. In this paper, we focus on how to improve the performance of the draft model and aim to accelerate inference via a high acceptance rate. To this end, we propose a CTC-based draft model which strengthens the correlations between draft tokens during the draft phase, thereby generating higher-quality draft candidate sequences. Experiment results show that compared to strong baselines, the proposed method can achieve a higher acceptance rate and hence a faster inference speed. © 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

3D reconstruction and defect pattern recognition of bonding wire based on stereo vision

引用

CAAI Transactions on Intelligence technology 2024年第2期9卷 348-364页

作者： Naigong Yu Hongzheng Li Qiao Xu Ouattara Sie Essaf Firdaous Faculty of Information Technology Beijing University of TechnologyBeijingChina Beijing Key Laboratory of Computing Intelligence and Intelligent System Beijing University of TechnologyBeijingChina Engineering Research Center of Digital Community Ministry of EducationBeijingChina College of Robotic UniversitéFélix Houphouët‐BoignyAbidjanCôte d’Ivoire

Non-destructive detection of wire bonding defects in integrated circuits(IC)is critical for ensuring product quality after ***-processing-based methods do not provide a detailed evaluation of the three-dimensional defects of the bonding ***,a method of 3D reconstruction and pattern recognition of wire defects based on stereo vision,which can achieve non-destructive detection of bonding wire defects is *** contour features of bonding wires and other electronic components in the depth image is analysed to complete the 3D reconstruction of the bonding *** to filter the noisy point cloud and obtain an accurate point cloud of the bonding wire surface,a point cloud segmentation method based on spatial surface feature detection(SFD)was *** can extract more distinct features from the bonding wire surface during the point cloud segmentation ***,in the defect detection process,a directional discretisation descriptor with multiple local normal vectors is designed for defect pattern recognition of bonding *** descriptor combines local and global features of wire and can describe the spatial variation trends and structural features of *** experimental results show that the method can complete the 3D reconstruction and defect pattern recognition of bonding wires,and the average accuracy of defect recognition is 96.47%,which meets the production requirements of bonding wire defect detection.

关键词： bonding wire defect detection point cloud point cloud segmentation

来源：评论

学校读者我要写书评

暂无评论

Environmental Features Assessment Network Aided Deep Reinforcement Learning for Quadrupedal Locomotion in Tough Terrain

Environmental Features Assessment Network Aided Deep Reinfor...

引用

2023 China Automation Congress, CAC 2023

作者： Zuo, Guoyu Wang, Yong Huang, Gao Yu, Shuangyue Beijing University of Technology Faculty of Information Technology Beijing100124 China Beijing Key Laboratory of Computing Intelligence and Intelligent Systems Beijing100124 China

ISBN: (纸本)9798350303759

Quadrupedal robots have more powerful locomotion capabilities compared to other types of mobile robots. However, the complexity of their controllers and the need to adapt to a wide variety of terrains poses a huge difficulty in the design of the controllers. Recently, deep reinforcement learning (DRL) has been widely used in quadruped robot controller design but still relies on complex and reliable sensing frameworks. In this paper, we propose a motion controller training framework. The framework includes an Environmental Feature Assessment Network (EFANet) to guide the action output of the policy network, and an asymmetric actor-critic structure to help the policy network infer terrain features. We also introduce a strategic trajectory generator into our framework to prevent the robot from generating abnormal gaits. The proposed framework for learning quadrupedal locomotion allows quadrupedal robots to traverse challenging terrains with limited sensors. Finally, the proposed approach is tested and evaluated in a simulation environment using the A1 quadruped robot model. © 2023 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Repetitive Path Planning with Experience-Based Bidirectional RRT 1

引用

International Conference on Robots for Space Applications in Orbital Stations, TORVEASTRO 2023

作者： Zuo, Guoyu Wu, Chun Huang, Gao Beijing Key Laboratory of Computing Intelligence and Intelligent Systems Beijing100124 China Faculty of Information Technology Beijing University of Technology Beijing100124 China

ISBN: (数字)9783031284472

ISBN: (纸本)9783031284465

Repetitive motion planning in semi-structured environments is involved in many robotics applications, such as manufacturing and in-orbit service of spatial robotic arms. In these scenarios, the environment is mainly static, but it may contain some movable obstacles that the robot needs to avoid, and the planning problems that the robot will encounter are very similar. However, most current sampling-based motion planning methods ignore the correlation among tasks, and instead plan each task instance from scratch, or assume that the environment is highly structured. In order to overcome this problem, this paper proposes an experience-based bidirectional rapidly-exploring random trees* (EBRRT*) for repetitive path planning in semi-structured environments. First, an adaptive sampler learned from the demonstration paths by a Gaussian mixture model (GMM) is constructed, which can guide the planner to generate samples in task-related regions. Second, an experience graph is proposed to capture the exploration of configuration space by previous similar tasks. Subsequent tasks can retrieve locally valuable information from the graph to avoid exploring the configuration space repeatedly. In addition, the validity of edges contained in the experience graph is lazily verified during the planning process so that the experience graph can adapt to small environmental changes. Finally, the proposed method is verified in a 2D simulation environment and a 7-DOF manipulator scene. Experimental results show that the proposed method can return a high-quality path in less time than other state-of-the-art sample-based motion planning for repetitive path planning in semi-structured environments. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

A graph reasoning method for multi-object unordered stacking scenarios

A graph reasoning method for multi-object unordered stacking...

引用

2023 IEEE International Conference on Real-Time computing and Robotics, RCAR 2023

作者： Zuo, Guoyu Wang, Zihao Gong, Daoxiong Huang, Gao Beijing University of Technology Faculty of Information Technology Beijing100124 China Beijing Key Laboratory of Computing Intelligence and Intelligent Systems Beijing100124 China

ISBN: (纸本)9798350327182

In order to enable the robot to safely pick the target object from it in the face of a scene with multiple objects stacked in a disorderly manner. It is of great importance for intelligent robot grasping to get the operation order by obtaining the position relationship between the target object and other objects in space. In this paper, an end-to-end detection inference network is proposed, in which features are extracted from the input RGB information by EfficientNet-B0 combined with BiFPN in terms of feature extraction, and in terms of operation relationships, object pairs without up-down position relationships are first eliminated to reduce the amount of operations, and graph attention networks (GAT) are later used to reason about the positions between objects. The network model is trained and tested on the VMRD dataset, and the experiments show that this model has good results in inference of object spatial position relationships for multi-object unordered stacked scenes. © 2023 IEEE.

关键词： intelligent robots

来源：评论

学校读者我要写书评

暂无评论

A Novel Approach for State of Health Estimation and Remaining Useful Life Prediction of Supercapacitors Using an Improved Honey Badger Algorithm Assisted Hybrid Neural Network

引用

Protection and Control of Modern Power Systems 2024年第6期9卷 1-18页

作者： Zhenxiao Yi Shi Wang Zhaoting Li Licheng Wang Kai Wang the School of Electrical Engineering Qingdao UniversityQingdao 266071Chinaand the State Key Laboratory of Reliability and Intelligence of Electrical EquipmentHebei University of TechnologyTianjin 300130China the Key Laboratory of Intelligent Information Processing Institute of Computing TechnologyChinese Academy of SciencesBeijing 100190China the School of Engineering Brown UniversityProvidenceRhode Island 02912USA the School of Information Engineering Zhejiang University of TechnologyHangzhou 310014China the School of Electrical Engineering Qingdao UniversityQingdao 266071China

Supercapacitors(SCs)are widely recognized as excellent clean energy storage *** state of health(SOH)estimation and remaining useful life(RUL)prediction are essential for ensuring their safe and reliable *** paper introduces a novel method for SOH estimation and RUL prediction,based on a hybrid neural network optimized by an improved honey badger algorithm(HBA).The method combines the advantages of convolutional neural network(CNN)and bidirectional long-short-term memory(BiLSTM)neural *** HBA optimizes the hyperparameters of the hybrid neural *** CNN automatically extracts deep features from time series data and reduces dimensionality,which are then used as input for the ***,recurrent dropout is introduced in the recurrent layer to reduce overfitting and facilitate the learning *** approach not only improves the accuracy of estimates and forecasts but also significantly reduces data processing *** under different working conditions are used to validate the proposed *** results show that the proposed hybrid model effectively extracts features,enriches local details,and enhances global perception *** proposed hybrid model outperforms single models,reducing the root mean square error to below 1%,and offers higher prediction accuracy and robustness compared to other methods.

关键词： Supercapacitors state of health remaining useful life honey badger algorithm recurrent dropout.

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：