检索结果-内蒙古大学图书馆

Woodpecker: hallucination correction for multimodal large language models

science China(Information sciences) 2024年第12期67卷 52-64页

作者： Shukang YIN Chaoyou FU Sirui ZHAO Tong XU Hao WANG Dianbo SUI Yunhang SHEN Ke LI Xing SUN Enhong CHEN School of Artificial Intelligence and Data Science University of Science and Technology of China State Key Laboratory for Novel Software Technology Nanjing University School of Intelligence Science and Technology Nanjing University Institute of Automation Chinese Academy of Sciences YouTu

Hallucinations is a big shadow hanging over the rapidly evolving multimodal large language models(MLLMs), referring to that the generated text is inconsistent with the image content. To mitigate hallucinations, existing studies mainly resort to an instruction-tuning manner that requires retraining the models with specific data. In this paper, we pave a different way, introducing a training-free method named Woodpecker. Like woodpeckers heal trees, it picks out and corrects hallucinations from the generated text. Concretely, Woodpecker consists of five stages: key concept extraction, question formulation, visual knowledge validation, visual claim generation, and hallucination correction. Implemented in a post-remedy manner, Woodpecker can easily serve different MLLMs, while being interpretable by accessing intermediate outputs of the five stages. We evaluate Woodpecker both quantitatively and qualitatively and show the huge potential of this new paradigm. On the POPE benchmark, our method obtains a 30.66%/24.33% improvement in accuracy over the baseline MiniGPT-4/mPLUG-Owl. The source code is released at https://***/BradyFU/Woodpecker.

关键词： multimodal learning multimodal large language models hallucination correction large language models vision and language

来源：评论

学校读者我要写书评

暂无评论

Transverse Velocity Field Measurement of Solar High-resolution Images Based on Unsupervised Deep Learning

引用

Research in Astronomy and Astrophysics 2025年第3期25卷 236-248页

作者： Zhen-Hong Shang Long Chen Zhen-Ping Qiang Yi Bi Run-Xin Li Faculty of Information Engineering and Automation Kunming University of Science and Technology Yunnan Key Laboratory of Artificial Intelligence Kunming University of Science and Technology College of Big Data and Intelligent Engineering Southwest Forestry University Yunnan Observatories Chinese Academy of Sciences

Measuring the transverse velocity field in high-resolution solar images is essential for understanding solar *** paper introduces an innovative unsupervised deep learning optical flow model designed to calculate the transverse velocity field,addressing the challenges of missing optical flow labels and the limited accuracy of velocity field measurements in high-resolution solar *** proposed method converts the transverse velocity field computation problem into an optical flow computation problem,using two forward propagations of features to get rid of the reliance on optical flow ***,it reduces the impact of the“Brightness Consistency”constraint on optical flow accuracy by identifying and handling optical flow *** apply this method to compute the transverse velocity fields of high-resolution solar image sequences from the Hαand TiO bands,observed by the New Vacuum Solar *** experiments with several wellestablished optical flow methods,including those based on supervised deep learning models,show that our approach outperforms the comparison methods according to key evaluation metrics such as Residual Map Mean,Residual Map Variance,Cross Correlation,and Structural Similarity Index ***,since optical flow captures the fundamental motion information in image sequences,the proposed method can be applied to a variety of research areas,including solar image registration,sequence alignment,image super-resolution,magnetic field calibration,and solar activity *** code is available at https://***/jackie-willianm/Transverse-Velocity-Field-Measurement-of-Solar-High-Resolution-Images.

关键词： methods: data analysis techniques: image processing Sun: fundamental parameters

来源：评论

学校读者我要写书评

暂无评论

Distributionally Robust Chance Constrained Trajectory Optimization for Mobile Robots within Uncertain Safe Corridor

Distributionally Robust Chance Constrained Trajectory Optimi...

引用

2024 IEEE International Conference on Robotics and automation, ICRA 2024

作者： Xu, Shaohang Ruan, Haolin Zhang, Wentao Wang, Yian Zhu, Lijun Ho, Chin Pang Huazhong University of Science and Technology School of Artificial Intelligence and Automation China City University of Hong Kong School of Data Science Hong Kong

ISBN: (纸本)9798350384574

Safe corridor-based Trajectory Optimization (TO) presents an appealing approach for collision-free path planning of autonomous robots, because its convex formulation can guarantee global optimality. The safe corridor is constructed based on the obstacle map, however, the non-ideal perception induces uncertainty, which is rarely considered in the context of trajectory generation. In this paper, we propose Distributionally Robust Safe Corridor Constraints (DRSCCs) to consider the uncertainty of the safe corridor. Then, we integrate DRSCCs into the trajectory optimization framework using Bernstein basis polynomials. Theoretically, we rigorously prove that the proposed trajectory optimization problem is equivalent to a convex quadratic program, which is computationally efficient to deploy onto real robots. The simulation results show that our method enhances navigation safety by significantly reducing the infeasible motions compared to the baseline. Moreover, the proposed approach is validated through two robotic applications, a micro Unmanned Aerial Vehicle (UAV) and a quadruped robot Unitree A1. © 2024 IEEE.

关键词： Microrobots

来源：评论

学校读者我要写书评

暂无评论

A Discrete-Time Collaborative Neurodynamic Approach to Distributed Global Optimization 13

A Discrete-Time Collaborative Neurodynamic Approach to Distr...

引用

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

作者： Huang, Haoen Zeng, Zhigang Wang, Jun School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China Department of Computer Science Department of Data Science City University of HongKong Kowloon Hong Kong

ISBN: (纸本)9798331516147

In this paper, a discrete-time projection neural network with an adaptive step size (DPNN) is proposed for distributed global optimization. The DPNN is proven to be convergent to a Karush-Kuhn-Tucker point. Several DPNNs are utilized in a collaborative neurodynamic framework for solving distributed global optimization problem. The efficacy of the collaborative neurodynamic approach with DPNNs is demonstrated through simulation results. © 2025 IEEE.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

Multi-scale detector optimized for small target

引用

Optoelectronics Letters 2024年第4期20卷 243-248页

作者： ZHU Yongchang YANG Sen TONG Jigang WANG Zenghui School of Electrical Engineering and Automation Tianjin University of TechnologyTianjin 300384China Center of Artificial Intelligence and Data Science University of South AfricaFlorida 1709South Africa Department of Electrical Engineering University of South AfricaFlorida 1709South Africa

The effectiveness of deep learning networks in detecting small objects is limited,thereby posing challenges in addressing practical object detection *** this research,we propose a small object detection model that operates at multiple *** model incorporates a multi-level bidirectional pyramid structure,which integrates deep and shallow networks to simultaneously preserve intricate local details and augment global ***,a dedicated multi-scale detection head is integrated into the model,specifically designed to capture crucial information pertaining to small *** comprehensive experimentation,we have achieved promising results,wherein our proposed model exhibits a mean average precision(mAP)that surpasses that of the well-established you only look once version 7(YOLOv7)model by 1.1%.These findings validate the improved performance of our model in both conventional and small object detection scenarios.

关键词： networks details thereby

来源：评论

学校读者我要写书评

暂无评论

Gradient-based Learning in State-based Potential Games for Self-Learning Production Systems 50

Gradient-based Learning in State-based Potential Games for S...

引用

50th Annual Conference of the IEEE Industrial Electronics Society, IECON 2024

作者： Yuwono, Steve Löppenberg, Marlon Schwung, Andreas Schwung, Dorothea South Westphalia University of Applied Sciences Soest Germany Artificial Intelligence and Data Science in Automation Technology Hochschule Düsseldorf University of Applied Sciences Düsseldorf Germany

ISBN: (纸本)9781665464543

In this paper, we introduce novel gradient-based optimization methods for state-based potential games (SbPGs) within self-learning distributed production systems. SbPGs are recognised for their efficacy in enabling self-optimizing distributed multi-agent systems and offer a proven convergence guarantee, which facilitates collaborative player efforts towards global objectives. Our study strives to replace conventional ad-hoc random exploration-based learning in SbPGs with contemporary gradient-based approaches, which aim for faster convergence and smoother exploration dynamics, thereby shortening training duration while upholding the efficacy of SbPGs. Moreover, we propose three distinct variants for estimating the objective function of gradient-based learning, each developed to suit the unique characteristics of the systems under consideration. To validate our methodology, we apply it to a laboratory testbed, namely Bulk Good Laboratory Plant, which represents a smart and flexible distributed multi-agent production system. The incorporation of gradient-based learning in SbPGs reduces training times and achieves more optimal policies than its baseline. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Demystifying the Role of Big data Analytics in IIoT-Based Connected Railways 3

Demystifying the Role of Big Data Analytics in IIoT-Based Co...

引用

3rd International Conference on Advancement in Electronics and Communication Engineering, AECE 2023

作者： Gupta, Navya Narwal, Bhawna Batra, Shivangi Gera, Pooja Bhati, Pooja Department of Artificial Intelligence and Data Science Delhi India Department of Information Technology Delhi India Department of Mechanical and Automation Engineering Delhi India

ISBN: (纸本)9798350330724

Recent advances in sensors, networks, and hardware/software platforms have facilitated the development of Industrial Internet of Things (IIoT) applications in railway transportation. Nevertheless, the limited coverage and battery life of IIoT devices remain significant hurdles in realizing realistic service implementations. Against this backdrop, this study aims to scrutinize the impact of Industry 4.0 and big data analytics on railway engineering, considering factors such as post-COVID requisites and the security and privacy of rail users. Additionally, the research investigates the application of these ideas in India, which presents a challenging environment, and examines potential avenues for future research. © 2023 IEEE.

关键词： Big data

来源：评论

学校读者我要写书评

暂无评论

Distributed Optimal Coordination Control for Nonlinear Multi-Agent Systems Under Dos Attack 42

Distributed Optimal Coordination Control for Nonlinear Multi...

引用

42nd Chinese Control Conference, CCC 2023

作者： Wang, Zhirui Zheng, Xiaoyuan Fan, Sha School of Artificial Intelligence and Data Science Hebei University of Technology Tianjian300401 China School of Automation East China University of Science and Technology Shanghai200237 China

ISBN: (纸本)9789887581543

This paper is concerned with the distributed optimal coordination control of nonlinear multi-agent systems (NMASs) under the denial of service (DoS) attacks. The purpose of this paper is to design a distributed control rate for an unknown nonlinear multi-agent system with power interval and time-varying packet loss probability under Dos attack that accurately simulates the impact of DoS attack on NMASs. Then adaptive dynamic programming (ADP) algorithm is used to solve the coupled Hamilton-Jacobi-Bellman (HJB) equation. In order to realize the proposed method, the critic neural network(NN) and actor neural network are used to approximate value functions and control policy. Finally the NN actor-critic policy for optimal control of NMASs under DoS attack with power interval is found. It is proved that the weight estimation error and local neighborhood coordination error are uniformly ultimately bounded (UUB). Finally, the simulation results show the effectiveness of the coordinated control. © 2023 Technical Committee on Control Theory, Chinese Association of automation.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

A Domain Generalization Model Based on Multilevel Domain Adversarial Invariant Representation Learning 8

A Domain Generalization Model Based on Multilevel Domain Adv...

引用

8th International Conference on Intelligent Computing and Signal Processing, ICSP 2023

作者： Liu, Kun Wang, Ding Yang, Ying Wang, Jingkai Mao, Jingkun Hebei University of Technology School of Artificial Intelligence and Data Science Tianjin China Tianjin University of Technology School of Electrical Engineering and Automation Tianjin China

ISBN: (纸本)9798350302455

Due to the influence of various factors such as cross-scene shooting height, shooting time, imaging angle of view, weather, etc., the performance of the defect detection model degrades in cross-scene situations. In this paper, we proposed a domain generalization model based on multilevel domain adversarial invariant representation learning, which included the designed defect space feature and channel feature enhancement modules. Among them, the defect space feature enhancement module uses the shallow feature invariance score to guide the model to extract cross-scene invariant representations, and at the same time, design and use the defect importance information in the shallow features to enhance the representation of defects in the shallow features. The channel feature enhancement module assigns learning weights to different channels of each sample according to the similarity between the sample and the whole, and the importance of different feature channels to defects, so as to better guide the model to extract cross-scene invariant representations. The experimental verification on the photovoltaic cell data set collected in outdoor natural scenes shows that, proposed model has stronger generalization ability than existed domain generalization methods. © 2023 IEEE.

关键词： Defects

来源：评论

学校读者我要写书评

暂无评论

Multi-View Dynamic Kernelized Evidential Clustering

引用

IEEE/CAA Journal of Automatica Sinica 2024年第12期11卷 2435-2450页

作者： Jinyi Xu Zuowei Zhang Ze Lin Yixiang Chen Weiping Ding the Software Engineering Institute East China Normal UniversityShanghai 200062 Shanghai Key Laboratory of Trustworthy Computing East China Normal UniversityShanghai 200062China IEEE the School of Automation Northwestern Polytechnical UniversityXi’an 710072China the School of Artificial Intelligence and Computer Science Nantong UniversityNantong 226019 the Faculty of Data Science City University of MacaoMacao 999078China

It is challenging to cluster multi-view data in which the clusters have overlapping *** multi-view clustering methods often misclassify the indistinguishable objects in overlapping areas by forcing them into single clusters,increasing clustering *** solution,the multi-view dynamic kernelized evidential clustering method(MvDKE),addresses this by assigning these objects to meta-clusters,a union of several related singleton clusters,effectively capturing the local imprecision in overlapping *** offers two main advantages:firstly,it significantly reduces computational complexity through a dynamic framework for evidential clustering,and secondly,it adeptly handles non-spherical data using kernel techniques within its objective *** on various datasets confirm MvDKE's superior ability to accurately characterize the local imprecision in multi-view non-spherical data,achieving better efficiency and outperforming existing methods in overall performance.

关键词： Evidential clustering imprecision characterizing kernel technique multi-view clustering

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：