检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Wang, Zhicheng Xiao, Liwen Cao, Zhiguo Lu, Hao 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

Class-agnostic counting (CAC) aims to count objects of interest from a query image given few exemplars. This task is typically addressed by extracting the features of query image and exemplars respectively and then matching their feature similarity, leading to an extract-then-match paradigm. In this work, we show that CAC can be simplified in an extract- and-match manner, particularly using a vision transformer (ViT) where feature extraction and similarity matching are executed simultaneously within the self-attention. We reveal the rationale of such simplification from a decoupled view of the self-attention. The resulting model, termed CACViT, simplifies the CAC pipeline into a single pretrained plain ViT. Further, to compensate the loss of the scale and the order-of-magnitude information due to resizing and normalization in plain ViT, we present two effective strategies for scale and magnitude embedding. Extensive experiments on the FSC147 and the CARPK datasets show that CACViT significantly outperforms state-of-the-art CAC approaches in both effectiveness (23.60% error reduction) and generalization, which suggests CACViT provides a concise and strong baseline for CAC. Code will be available. Copyright © 2023, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Defocus to focus: photo-realistic bokeh rendering by fusing defocus and radiance priors

arXiv

引用

arXiv 2023年

作者： Luo, Xianrui Peng, Juewen Xian, Ke Wu, Zijin Cao, Zhiguo 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

We consider the problem of realistic bokeh rendering from a single all-in-focus image. Bokeh rendering mimics aesthetic shallow depth-of-field (DoF) in professional photography, but these visual effects generated by existing methods suffer from simple flat background blur and blurred in-focus regions, giving rise to unrealistic rendered results. In this work, we argue that realistic bokeh rendering should i) model depth relations and distinguish in-focus regions, ii) sustain sharp in-focus regions, and iii) render physically accurate Circle of Confusion (CoC). To this end, we present a Defocus to Focus (D2F) framework to learn realistic bokeh rendering by fusing defocus priors with the all-in-focus image and by implementing radiance priors in layered fusion. Since no depth map is provided, we introduce defocus hallucination to integrate depth by learning to focus. The predicted defocus map implies the blur amount of bokeh and is used to guide weighted layered rendering. In layered rendering, we fuse images blurred by different kernels based on the defocus map. To increase the reality of the bokeh, we adopt radiance virtualization to simulate scene radiance. The scene radiance used in weighted layered rendering reassigns weights in the soft disk kernel to produce the CoC. To ensure the sharpness of in-focus regions, we propose to fuse upsampled bokeh images and original images. We predict the initial fusion mask from our defocus map and refine the mask with a deep network. We evaluate our model on a large-scale bokeh dataset. Extensive experiments show that our approach is capable of rendering visually pleasing bokeh effects in complex scenes. In particular, our solution receives the runner-up award in the AIM 2020 Rendering Realistic Bokeh Challenge. © 2023, CC BY-NC-ND.

关键词： Image fusion

来源：评论

学校读者我要写书评

暂无评论

Fixed-time extended state observer-based trajectory tracking control for autonomous underwater vehicles

Fixed-time extended state observer-based trajectory tracking...

引用

作者： Zheng, Jiaqi Song, Lei Liu, Lingya Yu, Wenbin Zhu, Shanying Wang, Yiyin Chen, Cailian Department of Automation Shanghai Jiao Tong University Shanghai China Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai China Shanghai Engineering Research Center of Intelligent Control and Management Shanghai Jiao Tong University Shanghai China

In this paper, we investigate the trajectory tracking control problem for autonomous underwater vehicles (AUVs) with time-varying external disturbances of currents and waves in the sea. To solve the problem, a fixed-time extended state observer (FTESO)-based tracking controller is proposed. Firstly, by using the extended state observer, the FTESO is proposed for estimating the external disturbances and the velocities of the AUV within the fixed convergence time. Based on the FTESO, the fixed-time controller is proposed for reducing the tracking errors and improving robustness performance. Theoretical analysis is given, which shows that the unknown external disturbances can be compensated and tracking error can converge to zero within the fixed time. Simulation results show that the proposed FTESO controller not only guarantees the fixed-time convergence but also reduces the trajectory tracking errors of the AUV. © 2021 Chinese Automatic control Society and John Wiley & Sons Australia, Ltd.

关键词： Autonomous underwater vehicles

来源：评论

学校读者我要写书评

暂无评论

Thermal Safety Analysis and Dynamic control Strategy for Mode Switching Process of Reversible Solid Oxide Cell System

Thermal Safety Analysis and Dynamic Control Strategy for Mod...

引用

Chinese control Conference (CCC)

作者： Wei Zhao Guoqiang Liu Zexin Li Xi Li Key Laboratory of Image Processing and Intelligent Control of Education Ministry School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan Hubei China

Reversible solid oxide cells (rSOC) can operate in both electrolysis mode and in fuel cell mode with high efficiency and reduced cost using the same device for both functions. When used in dynamic operation with intermittent electrical power sources, rSOC system switches from the fuel cell (SOFC) to electrolyzer (SOEC) and vice versa depending on load and grid peculiarities. This can lead to temperature profiles within the stack that can potentially lead to the failure of the stack and eventually the system. In the present work, a system-level dynamic model of rSOC is established and validated against experimental data. Subsequently, detailed dynamic thermal behavior of stack during the switching between the two modes is analyzed, and a temperature management controller based on Model Predict control method (MPC) is proposed. Gas flow and temperature at the stack inlet are controlled by air flow and bypass valves, avoiding problems associated with temperature overshoot during transient operation. The simulation results show that the temperature controller has the ability to follow fast thermal changes while maintaining thermal safety, which indicates the competitiveness of the controller.

关键词：

来源：评论

学校读者我要写书评

暂无评论

When Epipolar Constraint Meets Non-local Operators in Multi-View Stereo

arXiv

引用

arXiv 2023年

作者： Liu, Tianqi Ye, Xinyi Zhao, Weiyue Pan, Zhiyu Shi, Min Cao, Zhiguo 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

Learning-based multi-view stereo (MVS) method heavily relies on feature matching, which requires distinctive and descriptive representations. An effective solution is to apply non-local feature aggregation, e.g., Transformer. Albeit useful, these techniques introduce heavy computation overheads for MVS. Each pixel densely attends to the whole image. In contrast, we propose to constrain non-local feature augmentation within a pair of lines: each point only attends the corresponding pair of epipolar lines. Our idea takes inspiration from the classic epipolar geometry, which shows that one point with different depth hypotheses will be projected to the epipolar line on the other view. This constraint reduces the 2D search space into the epipolar line in stereo matching. Similarly, this suggests that the matching of MVS is to distinguish a series of points lying on the same line. Inspired by this point-to-line search, we devise a line-to-point non-local augmentation strategy. We first devise an optimized searching algorithm to split the 2D feature maps into epipolar line pairs. Then, an Epipolar Transformer (ET) performs non-local feature augmentation among epipolar line pairs. We incorporate the ET into a learning-based MVS baseline, named ET-MVSNet. ET-MVSNet achieves state-of-the-art reconstruction performance on both the DTU and Tanks-and-Temples benchmark with high efficiency. Code is available at https://***/TQTQliu/ET-MVSNet. Copyright © 2023, The Authors. All rights reserved.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Multiple Unmanned Surface Vehicle Coverage control in Dynamic Environments

Multiple Unmanned Surface Vehicle Coverage Control in Dynami...

引用

Neuromorphic Computing (ICNC), International Conference on

作者： Hong Chen Dingxin He Huantao Mao Yong Yang Zhi-Wei Liu School of Artificial Intelligence and Automation Key Laboratory of Image Processing and Intelligent Control of Education Ministry of China Huazhong University of Science and Technology Wuhan China

This paper investigates the area coverage problem for multiple Unmanned Surface Vehicles (USVs) in dynamic environments. Multiple USVs are employed to execute the coverage task using the Voronoi Partition method for task allocation. Parameter adaptive laws are employed to estimate the parameters of the sensing function and the Voronoi cell centroids for updating the target positions in dynamic environments. Additionally, considering the influence of water surface disturbances, a nonholonomic underactuated model analysis is conducted for the USV under non-full constraints, resulting in a motion strategy for USVs. This enables the multiple USVs to effectively cover the task area. Finally, simulation results are presented to validate the effectiveness of the coverage scheme designed in this paper and the ability of USVs to effectively cover dynamic environments.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Non-contact Detection of Vital Sign Based on ICCEMDAN-SpEn Combined with Wavelet Threshold Denoising

Non-contact Detection of Vital Sign Based on ICCEMDAN-SpEn C...

引用

International Conference on Microwave and Millimeter Wave Technology Proceedings

作者： Wan Li Binkun Liu Chunhua Zhu Key Laboratory of Grain Information Processing and Control Henan University of Technology Ministry of Education Henan Key Laboratory of Grain Photoelectric Detection and Control Henan University of Technology Henan Engineering Laboratory of Grain Condition Intelligent Detection and Application Henan University of Technology Zhengzhou China

ISBN: (数字)9798350389968

ISBN: (纸本)9798350389975

The detection of vital signs, especially respiratory rate and heartbeat rate, is of great significance for clinical diagnosis, daily health assessment and disaster rescue. In recent years, millimeter wave based non-contact vital sign detection has become a research hotspot. Aiming to overcome the noise influence of the target signal on the detection accuracy, one improved ICEEMDAN based on sample entropy (ICCEMDAN-SpEn) combined with wavelet threshold denoising is proposed. Firstly, the adaptive noise extraction ability of ICEEMDAN is analyzed to isolate all intrinsic mode function (IMF) components of the noisy target signals, and the sample entropy is introduced as the threshold to select the main IMFs; then wavelet threshold denoising is proposed to relieve the noise adaptively, which can better deal with the nonlinear and non-stationary signal; finally, IMFs after wavelet threshold denoising are reconstructed to attain target signals. The experimental results show that the proposed method can effectively relieve the noise contained in the vital sign signals and estimate the respiratory rate and heartbeat rate of human body accurately.

关键词： Heart beat Noise reduction Noise Millimeter wave technology Millimeter wave measurements Wavelet analysis Entropy

来源：评论

学校读者我要写书评

暂无评论

Mixture-of-Experts for Open Set Domain Adaptation: A Dual-Space Detection Approach

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2025年

作者： Du, Zhenbang An, Jiayu Tu, Yunlu Hong, Jiahao Wu, Dongrui Key Laboratory of the Ministry of Education for Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China

Open Set Domain Adaptation (OSDA) copes with the distribution and label shifts between the source and target domains simultaneously, performing accurate classification for known classes while identifying unknown class samples in the target domain. Most existing OSDA approaches, depending on the final image feature space of deep models, require manually-tuned thresholds, and may easily misclassify unknown samples as known classes. Mixture-of-Experts (MoE) could be a remedy. Within an MoE, different experts handle distinct input features, producing unique expert routing patterns for various classes in a routing feature space. As a result, unknown class samples may display different expert routing patterns to known classes. This paper proposes Dual-Space Detection, which exploits the inconsistencies between the image feature space and the routing feature space to detect unknown class samples without any threshold. A Graph Router is further introduced to better make use of the spatial information among the image patches. Experiments on three datasets validated the effectiveness and superiority of our approach. © 2020 IEEE.

关键词： Mixture-of-Experts Open Set Domain Adaptation Routing Feature

来源：评论

学校读者我要写书评

暂无评论

Research on Explanation of CAM-Based CNNs

Research on Explanation of CAM-Based CNNs

引用

IEEE International Conference on Power, intelligent Computing and Systems (ICPICS)

作者： Shuzhi Yang Chunhua Zhu Xue Li Key Laboratory of Grain Information Processing and Control (Henan University of Technology) Ministry of Education Henan Key Laboratory of Grain Photoelectric Detection and Control Henan University of Technology Henan Engineering Laboratory of Grain Condition Intelligent Detection and Application Henan University of Technology Zhengzhou China

ISBN: (数字)9798350374315

ISBN: (纸本)9798350374322

Class activation mapping (CAM) is a post-hoc explanation method for Convolutional neural networks (CNNs), aiming to visually explain the decision-making process of CNNs. CAM demonstrates superior categorical discrimination capabilities compared to visual explanation methods rooted in backpropagation and perturbation. Five CAM methods have been comprehensively analyzed and discussed, revealing their applications in explaining CNN decision-making. Additionally, the evaluation principles and metrics for CAM and other explainable methods are summarized. A comparative analysis highlights their characteristics, applicability, and inherent limitations. Finally, the challenges faced by CAM methods in the field of explainable research are explored, and future development trends are anticipated.

关键词： Measurement Backpropagation Visualization Perturbation methods Decision making Market research Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Two-Stage Robust Optimization Under Decision Dependent Uncertainty

引用

IEEE/CAA Journal of Automatica Sinica 2022年第7期9卷 1295-1306页

作者： Yunfan Zhang Feng Liu Yifan Su Yue Chen Zhaojian Wang João P.S.Catalão State Key Laboratory of Power System and Generation Equipment the Department of Electrical EngineeringTsinghua UniversityBeijing 100084China Department of Mechanical and Automation Engineering the Chinese University of Hong KongHong Kong SARChina Ministry of Education Key Laboratory of System Control and Information Processing the Department of AutomationShanghai Jiao Tong Universityand also with Shanghai Engineering Research Center of Intelligent Control and ManagementShanghai 200240China Faculty of Engineering of the University of Porto and Institute for Systems and Computer Engineering Technology and Science(INESC TEC)Porto 4200-465Portugal IEEE

In the conventional robust optimization(RO)context,the uncertainty is regarded as residing in a predetermined and fixed uncertainty *** many applications,however,uncertainties are affected by decisions,making the current RO framework *** paper investigates a class of two-stage RO problems that involve decision-dependent *** introduce a class of polyhedral uncertainty sets whose right-hand-side vector has a dependency on the here-and-now decisions and seek to derive the exact optimal wait-and-see decisions for the second-stage problem.A novel iterative algorithm based on the Benders dual decomposition is proposed where advanced optimality cuts and feasibility cuts are designed to incorporate the uncertainty-decision *** computational tractability,robust feasibility and optimality,and convergence performance of the proposed algorithm are guaranteed with theoretical *** motivating application examples that feature the decision-dependent uncertainties are ***,the proposed solution methodology is verified by conducting case studies on the pre-disaster highway investment problem.

关键词： Benders decomposition decision-dependent uncertainty endogenous uncertainty robust optimization(RO)

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：