检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Zhang, Boshen Li, Yuxi Tu, Yuanpeng Peng, Jinlong Wang, Yabiao Wu, Cunlin Xiao, Yang Zhao, Cairong YouTu Lab Tencent Shanghai China Tongji University Shanghai China Key Laboratory of Image Processing and Intelligent Control Ministry of Education School of Artificial Intelligence and Automation Huazhong University of Science and Technology China

Training deep neural network (DNN) with noisy labels is practically challenging since inaccurate labels severely degrade the generalization ability of DNN. Previous efforts tend to handle part or full data in a unified denoising flow via identifying noisy data with a coarse small-loss criterion to mitigate the interference from noisy labels, ignoring the fact that the difficulties of noisy samples are different, thus a rigid and unified data selection pipeline cannot tackle this problem well . In this paper, we first propose a coarse-to-fine robust learning method called CREMA, to handle noisy data in a divide-and-conquer manner. In coarse-level, clean and noisy sets are firstly separated in terms of credibility in a statistical sense. Since it is practically impossible to categorize all noisy samples correctly, we further process them in a fine-grained manner via modeling the credibility of each sample. Specifically, for the clean set, we deliberately design a memory-based modulation scheme to dynamically adjust the contribution of each sample in terms of its historical credibility sequence during training, thus alleviating the effect from noisy samples incorrectly grouped into the clean set. Meanwhile, for samples categorized into the noisy set, a selective label update strategy is proposed to correct noisy labels while mitigating the problem of correction error. Extensive experiments are conducted on benchmarks of different modality, including image classification (CIFAR, Clothing1M etc) and text recognition (IMDB), with either synthetic or natural semantic noises, demonstrating the superiority and generality of CREMA. © 2022, CC BY.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Memory Analysis for Memristors and Memristive Recurrent Neural Networks

引用

IEEE/CAA Journal of Automatica Sinica 2020年第1期7卷 96-105页

作者： Gang Bao Yide Zhang Zhigang Zeng Key Laboratory of Cascaded Hydropower Stations Operation and Control Electrical Engineering and New EnergyChina Three Gorges UniversityYichang 443002and Hubei Key Laboratory of Applied Mathematics(Hubei University)Wuhan 430074China Department of Medical Engineering California Institute of TechnologyPasadenaCalifornia 91125 USA School of Artificial Intelligence and Automation Huazhong University of Science and Technologyand also with the Key Laboratory of Image Processing and Intelligent Control of Education Ministry of ChinaWuhan 430074China

Traditional recurrent neural networks are composed of capacitors, inductors, resistors, and operational *** neural networks are constructed by replacing resistors with memristors. This paper focuses on the memory analysis,i.e. the initial value computation, of memristors. Firstly, we present the memory analysis for a single memristor based on memristors’ mathematical models with linear and nonlinear ***, we present the memory analysis for two memristors in series and parallel. Thirdly, we point out the difference between traditional neural networks and those that are memristive. Based on the current and voltage relationship of memristors, we use mathematical analysis and SPICE simulations to demonstrate the validity of our methods.

关键词： Dopant drift memory memristive neural networks memristor

来源：评论

学校读者我要写书评

暂无评论

CrossGLG: LLM Guides One-shot Skeleton-based 3D Action Recognition in a Cross-level Manner

arXiv

引用

arXiv 2024年

作者： Yan, Tingbing Zeng, Wenzheng Xiao, Yang Tong, Xingyu Tan, Bo Fang, Zhiwen Cao, Zhiguo Zhou, Joey Tianyi Key Laboratory of Image Processing and Intelligent Control Ministry of Education School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China School of Biomedical Engineering Southern Medical University Guangzhou510515 China Department of Rehabilitation Medicine Zhujiang Hospital Southern Medical University Guangzhou510280 China Singapore Singapore Singapore Singapore

Most existing one-shot skeleton-based action recognition focuses on raw low-level information (e.g., joint location), and may suffer from local information loss and low generalization ability. To alleviate these, we propose to leverage text description generated from large language models (LLM) that contain high-level human knowledge, to guide feature learning, in a global-local-global way. Particularly, during training, we design 2 prompts to gain global and local text descriptions of each action from an LLM. We first utilize the global text description to guide the skeleton encoder focus on informative joints (i.e.,global-tolocal). Then we build non-local interaction between local text and joint features, to form the final global representation (i.e., local-to-global). To mitigate the asymmetry issue between the training and inference phases, we further design a dual-branch architecture that allows the model to perform novel class inference without any text input, also making the additional inference cost neglectable compared with the base skeleton encoder. Extensive experiments on three different benchmarks show that CrossGLG consistently outperforms the existing SOTA methods with large margins, and the inference cost (model size) is only 2.8% than the previous SOTA. CrossGLG can also serve as a plug-and-play module that can substantially enhance the performance of different SOTA skeleton encoders with a neglectable cost during inference. The source code will be released soon. © 2024, CC BY.

关键词： Signal encoding

来源：评论

学校读者我要写书评

暂无评论

Minimal-time Deadbeat Consensus and Individual Disagreement Degree Prediction for High-order Linear Multi-agent Systems

arXiv

引用

arXiv 2023年

作者： Hu, Fu-Long Zhang, Hai-Tao Xu, Bowen Hu, Zhe Ren, Wei School of Artificial Intelligence and Automation Key Laboratory of Image Processing and Intelligent Control The State Key Laboratory of Digital Manufacturing Equipment and Technology Huazhong University of Science and Technology Wuhan430074 China School of Artificial Intelligence Optics and Electronics Northwestern Polytechnical University Xi’an710072 China Department of Electrical and Computer Engineering University of California Riverside92521 United States

In this paper, a Hankel matrix-based fully distributed algorithm is proposed to address a minimal-time deadbeat consensus prediction problem for discrete-time high-order multi-agent systems (MASs). Therein, each agent can predict the consensus value with the minimum number of observable historical outputs of its own. Accordingly, compared to most existing algorithms only yielding asymptotic convergence, the present method can attain deadbeat consensus instead. Moreover, based on the consensus value prediction, instant individual disagreement degree value of MASs can be calculated in advance as well. Sufficient conditions are derived to guarantee both the minimal-time deadbeat consensus and the instant individual disagreement degree prediction. Finally, both the effectiveness and superiority of the proposed deadbeat consensus algorithm are substantiated by numerical simulations. Copyright © 2023, The Authors. All rights reserved.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

Model-Based and Data-Driven Contingency Filtering for Real-Time Corrective Security-Constrained Economic Dispatch

Model-Based and Data-Driven Contingency Filtering for Real-T...

引用

IEEE Conference on Energy Internet and Energy System Integration (EI2)

作者： Donghai Han Yaowen Yu Dingxin He Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China

ISBN: (纸本)9781665434263

Security-constrained economic dispatch (SCED) is one of the most important problems in power system operations. Corrective SCED (CSCED) is a type of SCED that considers corrective capabilities of the power system and adjusts base case decisions according to post-contingency states. Because of the large scale of the CSCED problem, it is difficult for purely model-based approaches to meet the time limits in real-time practical operations. To leverage historical operation data, this paper develops a novel hybrid model-based and data-driven framework to accelerate the solution process of CSCED. In the offline stage, our previous model-based contingency filtering approach is utilized to label active statuses of contingencies against historical net load samples. In the online stage, a multi-label classifier based on the K-Nearest Neighbor (KNN) algorithm quickly generates an active contingency set corresponding to the real-time net load. This active contingency set can be used to calculate the economic dispatch decisions in one shot. In addition, the accuracy of our framework can be further improved by adding an optional contingency filtering procedure at the end. Numerical testing results on the IEEE RTS-96 system demonstrate the accuracy and computational efficiency of the hybrid framework as compared to a purely model-based approach.

关键词： Economics Renewable energy sources Filtering Computational modeling System integration Real-time systems Numerical models

来源：评论

学校读者我要写书评

暂无评论

What Matters for 3D Scene Flow Network

arXiv

引用

arXiv 2022年

作者： Wang, Guangming Hu, Yunzhe Liu, Zhe Zhou, Yiyang Tomizuka, Masayoshi Zhan, Wei Wang, Hesheng Department of Automation Key Laboratory of System Control and Information Processing of Ministry of Education Key Laboratory of Marine Intelligent Equipment and System of Ministry of Education Shanghai Jiao Tong University China MoE Key Lab of Artificial Intelligence Shanghai Jiao Tong University China Mechanical Systems Control Laboratory University of California Berkeley United States

3D scene flow estimation from point clouds is a low-level 3D motion perception task in computer vision. Flow embedding is a commonly used technique in scene flow estimation, and it encodes the point motion between two consecutive frames. Thus, it is critical for the flow embeddings to capture the correct overall direction of the motion. However, previous works only search locally to determine a soft correspondence, ignoring the distant points that turn out to be the actual matching ones. In addition, the estimated correspondence is usually from the forward direction of the adjacent point clouds, and may not be consistent with the estimated correspondence acquired from the backward direction. To tackle these problems, we propose a novel all-to-all flow embedding layer with backward reliability validation during the initial scene flow estimation. Besides, we investigate and compare several design choices in key components of the 3D scene flow network, including the point similarity calculation, input elements of predictor, and predictor & refinement level design. After carefully choosing the most effective designs, we are able to present a model that achieves the state-of-the-art performance on FlyingThings3D and KITTI Scene Flow datasets. Our proposed model surpasses all existing methods by at least 38.2% on FlyingThings3D dataset and 24.7% on KITTI Scene Flow dataset for EPE3D metric. We release our codes at https://***/IRMVLab/3DFlow. Copyright © 2022, The Authors. All rights reserved.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

6-DOF grasp planning of manipulator combined with self-supervised learning

6-DOF grasp planning of manipulator combined with self-super...

引用

第33届中国控制与决策会议

作者： Zhenyu Ren Gang Peng Jin Yang Hao Wang School of Artificial Intelligence and Automation Huazhong University of Science and Technology Key Laboratory of Image Processing and Intelligent Control Ministry of Education

To realize a robust robotic grasping system for unknown objects in an unstructured environment,large amounts of grasp data and 3D model data for the object are *** reduce the time cost of data acquisition and labeling and increase the rate of successful grasps,we developed a self-supervised learning mechanism to control grasp tasks performed by ***,a manipulator automatically collects the point cloud for the objects from multiple perspectives to increase the efficiency of data *** complete point cloud for the objects is obtained by utilizing the hand-eye vision of the manipulator,and the TSDF ***,the point cloud data for the objects is used to generate a series of six-degrees-of-freedom grasp poses,and the force-closure decision algorithm is used to add the grasp quality label to each grasp pose to realize the automatic labeling of grasp ***,the point cloud in the gripper closing area corresponding to each grasp pose is obtained;it is then used to train the grasp-quality classification model for the *** results of performing actual grasping experiments demonstrate that the proposed self-supervised learning method can increase the rate of successful grasps for the manipulator.

关键词： Manipulator Grasping Self-Supervised Learning 3D Reconstruction

来源：评论

学校读者我要写书评

暂无评论

Transition in collective motion decision making

引用

Physical Review E 2022年第1期106卷 014611-014611页

作者： Biao Wang Yue Wu Guangwei Wang Lan Liu Guanrong Chen Hai-Tao Zhang School of Artificial Intelligence and Automation Key Laboratory of Image Processing and Intelligent Control State Key Laboratory of Digital Manufacturing Equipment and Technology Huazhong University of Science and Technology Wuhan 430074 China National Engineering Laboratory for Educational Big Data Central China Normal University Wuhan 430079 China Department of Electrical Engineering City University of Hong Kong Hong Kong SAR China

Collective decision making in a biological motion group requires fast and robust transmission of information. Typically, directional switching information propagation across the whole group obeys a linear dispersion law. However, conventional dynamic collective motion models, such as the Vicsek model and the Couzin model did not take into account ultrafast directional synchronous motions. In the present paper, a multiparticle model is proposed based on inertial spin self-propel action, which can provide adequate description of such group motion. By considering both spin mechanism and collision avoidance, the proposed self-propelled particle spin model can nicely describe collective motion with fast directional switching. By analyzing the order parameter of the group-velocity synchronization, a mechanism of group decision making is revealed, which is based on the difference between two clusters of divergent leaders, showing a transition from the compromising phase (i.e., following the group average) to the preferred phase (i.e., aligning to a leader cluster). The finding provides new insight to the decision-making process of followers when they face with divergent leaders in group motion.

关键词： Collective behavior in networks Network phase transitions Pattern formation Self-organized systems

来源：评论

学校读者我要写书评

暂无评论

Watch the Speakers: A Hybrid Continuous Attribution Network for Emotion Recognition in Conversation With Emotion Disentanglement

arXiv

引用

arXiv 2023年

作者： Lei, Shanglin Wang, Xiaoping Dong, Guanting Li, Jiang Liu, Yingjian School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China Key Laboratory of Image Processing and Intelligent Control Education Ministry of China Wuhan430074 China Wuhan430074 China School of Artificial Intelligence Beijing University of Posts and Telecommunications Beijing100876 China

Emotion Recognition in Conversation (ERC) has attracted widespread attention in the natural language processing field due to its enormous potential for practical applications. Existing ERC methods face challenges in achieving generalization to diverse scenarios due to insufficient modeling of context, ambiguous capture of dialogue relationships and overfitting in speaker modeling. In this work, we present a Hybrid Continuous Attributive Network (HCAN) to address these issues in the perspective of emotional continuation and emotional attribution. Specifically, HCAN adopts a hybrid recurrent and attention-based module to model global emotion continuity. Then a novel Emotional Attribution Encoding (EAE) is proposed to model intra- and inter-emotional attribution for each utterance. Moreover, aiming to enhance the robustness of the model in speaker modeling and improve its performance in different scenarios, A comprehensive loss function emotional cognitive loss LEC is proposed to alleviate emotional drift and overcome the overfitting of the model to speaker modeling. Our model achieves state-of-the-art performance on three datasets, demonstrating the superiority of our work. Another extensive comparative experiments and ablation studies on three benchmarks are conducted to provided evidence to support the efficacy of each module. Further exploration of generalization ability experiments shows the plug- and-play nature of the EAE module in our method. © 2023, CC BY-SA.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Cooperative Label-Free Moving Target Fencing for Second-Order Multi-Agent Systems with Rigid Formation

arXiv

引用

arXiv 2023年

作者： Hu, Bin-Bin Zhang, Hai-Tao Shi, Yang School of Artificial Intelligence Automation Key Laboratory of Image Processing Intelligent Control State Key Lab of Digital Manufacturing Equipment and Technology Huazhong University of Science and Technology Wuhan430074 China Department of Mechanical Engineering University of Victoria VictoriaBCV8W 2Y2 Canada

This paper proposes a label-free controller for a second-order multi-agent system to cooperatively fence a moving target of variational velocity into a convex hull formed by the agents whereas maintaining a rigid formation. Therein, no label is predetermined for a specified agent. To attain a rigid formation with guaranteed collision avoidance, each controller consists of two terms: a dynamic regulator with an internal model to drive agents towards the moving target merely by position information feedback, and a repulsive force between each pair of adjacent agents. Significantly, sufficient conditions are derived to guarantee the asymptotic stability of the closed-loop systems governed by the proposed fencing controller. Rigorous analysis is provided to eliminate the strong nonlinear couplings induced by the label-free property. Finally, the effectiveness of the controller is substantiated by numerical simulations. Copyright © 2023, The Authors. All rights reserved.

关键词： Multi agent systems

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：