检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Lyu, Shuchang Zhao, Qi Cheng, Guangliang He, Yiwei Zhou, Zheng Wang, Guangbiao Shi, Zhenwei School of Electronics and Information Engineering Beihang University Beijing100191 China Image Processing Center School of Astronautics Beihang University Beijing100191 China Department of Computer Science University of Liverpool LiverpoolL69 3BX United Kingdom

Unsupervised Domain Adaptation for Remote Sensing Semantic Segmentation (UDA-RSSeg) addresses the challenge of adapting a model trained on source domain data to target domain samples, thereby minimizing the need for annotated data across diverse remote sensing scenes. This task presents two principal challenges: (1) severe inconsistencies in feature representation across different remote sensing domains, and (2) a domain gap that emerges due to the representation bias of source domain patterns when translating features to predictive logits. To tackle these issues, we propose a joint-optimized adversarial network incorporating the "Segment Anything Model (SAM)" (SAM-JOANet) for UDA-RSSeg. Our approach integrates SAM to leverage its robust generalized representation capabilities, thereby alleviating feature inconsistencies. We introduce a finetuning decoder designed to convert SAM-Encoder features into predictive logits. Additionally, a feature-level adversarial-based prompted segmentor is employed to generate class-agnostic maps, which guide the finetuning decoder's feature representations. The network is optimized end-to-end, combining the prompted segmentor and the finetuning decoder. Extensive evaluations on benchmark datasets, including ISPRS (Potsdam/Vaihingen) and CITY-OSM (Paris/Chicago), demonstrate the effectiveness of our method. The results, supported by visualization and analysis, confirm the method's interpretability and robustness. The code of this paper is available at https: //***/CV-ShuchangLyu/SAM-JOANet/. Copyright © 2024, The Authors. All rights reserved.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Self-supervised denoising for multimodal structured illumination microscopy enables long-term super-resolution live-cell imaging

引用

PhotoniX 2024年第1期5卷 654-675页

作者： Xingye Chen Chang Qiao Tao Jiang Jiahao Liu Quan Meng Yunmin Zeng Haoyu Chen Hui Qiao Dong Li Jiamin Wu Department of Automation Tsinghua UniversityBeijing 100084China Research Institute for Frontier Science Beihang UniversityBeijing 100083China Institute for Brain and Cognitive Sciences Tsinghua UniversityBeijing 100084China National Laboratory of Biomacromolecules New Cornerstone Science LaboratoryCAS Center for Excellence in BiomacromoleculesInstitute of BiophysicsChinese Academy of SciencesBeijing 100101China College of Life Sciences University of Chinese Academy of SciencesBeijing 100049China Laboratory of Image Processing and Intelligent Control of Ministry of Education of China School of Artificial Intelligence and AutomationHuazhong University of Science and TechnologyWuhan 430074China

Detection noise significantly degrades the quality of structured illumination microscopy(SIM)images,especially under low-light *** supervised learning based denoising methods have shown prominent advances in eliminating the noise-induced artifacts,the requirement of a large amount of high-quality training data severely limits their *** we developed a pixel-realignmentbased self-supervised denoising framework for SIM(PRS-SIM)that trains an SIM image denoiser with only noisy data and substantially removes the reconstruction *** demonstrated that PRS-SIM generates artifact-free images with 20-fold less fluorescence than ordinary imaging conditions while achieving comparable super-resolution capability to the ground truth(GT).Moreover,we developed an easy-to-use plugin that enables both training and implementation of PRS-SIM for multimodal SIM platforms including 2D/3D and linear/nonlinear *** PRS-SIM,we achieved longterm super-resolution live-cell imaging of various vulnerable bioprocesses,revealing the clustered distribution of Clathrin-coated pits and detailed interaction dynamics of multiple organelles and the cytoskeleton.

关键词： Super-resolution microscopy Structured illumination microscopy Deep learning Self-supervised learning Live-cell imaging

来源：评论

学校读者我要写书评

暂无评论

Wearable and interactive multicolored photochromic fiber display

引用

Light(science & Applications) 2024年第3期13卷 454-465页

作者： Pan Li Yuwei Wang Xiaoxian He Yuyang Cui Jingyu Ouyang Ju Ouyang Zicheng He Jiayu Hu Xiaojuan Liu Hang Wei Yu Wang Xiaoling Lu Qian Ji Xinyuan Cai Li Liu Chong Hou Ning Zhou Shaowu Pan Xiangru Wang Huamin Zhou Cheng-Wei Qiu Yan-Qing Lu Guangming Tao State Key Laboratory of Material Processing and Die&Mould Technology School of Materials Science and Engineering and Wuhan National Laboratory for OptoelectronicsHuazhong University of Science and TechnologyWuhan 430074China Key Laboratory of Vascular Aging(HUST) Ministry of EducationWuhan 430030China School of Optoelectronic Science and Engineering University of Electronic Science and Technology of ChinaChengdu 611731China Department of Electrical and Computer Engineering National University of SingaporeSingapore 117583Singapore National Laboratory of Solid State Microstructures Key Laboratory of Intelligent Optical Sensing and ManipulationCollege of Engineering and Applied Sciencesand Collaborative Innovation Center of Advanced MicrostructuresNanjing UniversityNanjing 210023China School of Performing Arts Wuhan Conservatory of MusicWuhan 430060China School of Mechanical Science and Engineering Huazhong University of Science and TechnologyWuhan 430074China School of Architecture and Urban Planning Huazhong University of Science and TechnologyWuhan 430074China School of Fashion Beijing Institute of Fashion TechnologyBeijing 100029China School of Optical and Electronic Information Huazhong University of Science and TechnologyWuhan 430074China Tongji Medical College Huazhong University of Science and TechnologyWuhan 430074China State Key Laboratory for Modification of Chemical Fibers and Polymer Materials College of Materials Science and EngineeringDonghua UniversityShanghai 201620China

Endowing flexible and adaptable fiber devices with light-emitting capabilities has the potential to revolutionize the current design philosophy of intelligent,wearable interactive ***,significant challenges remain in developing fiber devices when it comes to achieving uniform and customizable light effects while utilizing lightweight ***,we introduce a mass-produced,wearable,and interactive photochromic fiber that provides uniform multicolored light *** designed independent waveguides inside the fiber to maintain total internal reflection of light as it traverses the *** impact of excessive light leakage on the overall illuminance can be reduced by utilizing the saturable absorption effect of fluorescent materials to ensure light emission uniformity along the transmission *** addition,we coupled various fluorescent composite materials inside the fiber to achieve artificially controllable spectral radiation of multiple color systems in a single *** prepared fibers on mass-produced kilometer-long using the thermal drawing *** fibers can be directly integrated into daily wearable devices or clothing in various patterns and combined with other signal input components to control and display patterns as *** work provides a new perspective and inspiration to the existing field of fiber display interaction,paving the way for future human–machine integration.

关键词： fiber interactive colored

来源：评论

学校读者我要写书评

暂无评论

On Ambiguity in Linear Inverse Problems: Entrywise Bounds on Nearly Data-Consistent Solutions and Entrywise Condition Numbers

arXiv

引用

arXiv 2022年

作者： Haldar, Justin P. The Signal and Image Processing Institute Ming Hsieh Department of Electrical and Computer Engineering University of Southern California Los AngelesCA90089 United States

Ill-posed linear inverse problems appear frequently in various signal processing applications. It can be very useful to have theoretical characterizations that quantify the level of ill-posedness for a given inverse problem and the degree of ambiguity that may exist about its solution. Traditional measures of ill-posedness, such as the condition number of a matrix, provide characterizations that are global in nature. While such characterizations can be powerful, they can also fail to provide full insight into situations where certain entries of the solution vector are more or less ambiguous than others. In this work, we derive novel theoretical lower- and upper-bounds that apply to individual entries of the solution vector, and are valid for all potential solution vectors that are nearly data-consistent. These bounds are agnostic to the noise statistics and the specific method used to solve the inverse problem, and are also shown to be tight. In addition, our results also lead us to introduce an entrywise version of the traditional condition number, which provides a substantially more nuanced characterization of scenarios where certain elements of the solution vector are less sensitive to perturbations than others. Our results are illustrated in an application to magnetic resonance imaging reconstruction, and we include discussions of practical computation methods for large-scale inverse problems, connections between our new theory and the traditional Cramér-Rao bound under statistical modeling assumptions, and potential extensions to cases involving constraints beyond just data-consistency. Copyright © 2022, The Authors. All rights reserved.

关键词： Inverse problems

来源：评论

学校读者我要写书评

暂无评论

Z-Face Sketch: Automatic Placement of Face Composites for Composite Sketches 1

Z-Face Sketch: Automatic Placement of Face Composites for Co...

引用

1st International Conference on Digital Government Technology and Innovation, DGTi-Con 2022

作者： Bholsithi, Wisarut Wongwaen, Nonlapas Sinthanayothin, Chanjira Chumpu, Romrawin Nitiphat, Police Colonel Burana, Police Colonel Chaiwat National Electronics and Computer Technology Center Image Processing and Understanding Research Team Artificial Intelligence Research Group Pathum Thani Thailand Thammasat University Sirindhorn International Institute of Technology Department of Common and Graduate Studies Pathum Thani Thailand Royal Thai Police Kittirakshakula Criminal Records Division Office of Forensic Science Bangkok Thailand Royal Thai Police Criminal Records Division Office of Forensic Science Bangkok Thailand

ISBN: (数字)9781665495554

ISBN: (纸本)9786168001226

The face composite sketching has been in use as the substitute as well as the complement to the forensic sketches by law enforcement artists. However, it requires manual methods to make proper placements for the various types of face composites which is a time-consuming process. This paper has introduced the Z-Face Sketch for the automatic positioning and scaling of face composites. The mechanics of Z-Face Sketch has taken the proportions and the positions of face composites relative with other types of face composites with human anatomy data into account. Z-Face Sketch also allows the users to readjust the positions of face composites as needed by users. Z-Face sketch has been designed as web application to be used on-line on PC or mobile devices. The image results from Z-Face Sketch are comparable with the photographs of volunteers and the manual results. © 2022 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Constrained Energy Minimization (CEM) for Hyperspectral Target Detection: Theory and Generalizations

引用

IEEE Transactions on Geoscience and Remote Sensing 2024年 62卷

作者： Chang, Chein-I. Information and Technology College Dalian116026 China University of Maryland Baltimore County Remote Sensing Signal and Image Processing Laboratory Department of Computer Science and Electrical Engineering BaltimoreMD21250 United States National Cheng Kung University Department of Electrical Engineering Tainan70101 Taiwan

Target detection is a fundamental task of hyperspectral imaging where constrained energy minimization (CEM) has been widely used for subpixel target detection techniques. Due to its effectiveness, CEM has been generalized to various versions, such as kernel CEM (KCEM), kernel target-constrained interference-minimized filter (KTCIMF), ensemble cascaded CEM (ECEM), and hierarchical CEM (HCEM). Unfortunately, these generalizations overlooked the key design rationale behind CEM. This article revisits CEM for hyperspectral target detection (HTD) and proves how and why it works mathematically. Specifically, several new CEM generalizations are derived and particularly noteworthy. By including spatial information in an iterative process, KCEM, ECEM, and HCEM can be generalized to iterative KCEM (IKCEM), iterative KTCIMF (IKTCIMF), iterative ECEM (IECEM), and iterative HCEM (IHCEM). Also, by utilizing an iterative random training sampling (IRTS) to generate the desired target signature to be detected, these algorithms are further generalized to IRTS KCEM (IRTS-KCEM), IRTS ECEM (IRTS-ECEM), and IRTS HCEM (IRTS-HCEM). A comprehensive analysis along with comparative study on these generalizations is conducted through extensive experiments to demonstrate the effectiveness of IKCEM, IHCEM, and IECEM. © 1980-2012 IEEE.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Niobium telluride absorber for a mode-locked vector soliton fiber laser

引用

science China(Physics,Mechanics & Astronomy) 2023年第5期66卷 130-138页

作者： XinXin Shang NanNan Xu Jia Guo Shuo Sun HuaNian Zhang SWageh Ahmed AAl-Ghamdi Han Zhang DengWang Li Shandong Province Key Laboratory of Medical Physics and Image Processing Technology Shandong Provincial Key Laboratory of Optics and Photonic DeviceSchool of Physics and ElectronicsShandong Normal UniversityJinan 250014China Institute of Microscale Optoelectronics Collaborative Innovation Center for Optoelectronic Science&TechnologyKey Laboratory of Optoelectronic Devices and Systems of Ministry of Education and Guangdong ProvinceCollege of Physics and Optoelectronic EngineeringShenzhen Key Laboratory of Micro-Nano Photonic Information TechnologyGuangdong Laboratory of Artificial Intelligence and Digital Economy(SZ)Shenzhen UniversityShenzhen 518060China School of Physics and Optoelectronic Engineering Shandong University of TechnologyZibo 255049China Department of Physics Faculty of ScienceKing Abdulaziz UniversityJeddah 21589Saudi Arabia

Niobium telluride(NbTe_(2)),an emerging transition metal dichalcogenide material,has been theoretically predicted to have nonlinear absorption properties and excellent optical ***,only a few studies of the utilization of NbTe_(2)in ultrafast photonics have been *** this work,a NbTe_(2)-based saturable absorber(SA)was applied in an erbium-doped fiber as a mode-locked device,and a vector soliton based on NbTe_(2)was obtained for the first ***_(2)-PVA film SA was successfully prepared by the liquid-phase exfoliation and spin coating methods,with a modulation depth of up to 10.87%.The nonlinear absorption coefficient of NbTe_(2)-based SA film tested through the open-aperture Z-scan laser measurement is 0.62×10^(−11) m/W.A conventional soliton with a pulse duration of 858 fs was generated using NbTe_(2)-based SA,which was demonstrated to be a kind of polarization-locked vector soliton in further *** experimental results reveal the nonlinear optical properties of NbTe_(2)and broaden its applications in ultrafast photonic devices.

关键词： niobium telluride saturable absorber mode-locked pulse fiber laser

来源：评论

学校读者我要写书评

暂无评论

Patch-CNN: Training data-efficient deep learning for high-fidelity diffusion tensor estimation from minimal diffusion protocols

arXiv

引用

arXiv 2023年

作者： Goodwin-Allcock, Tobias Gong, Ting Gray, Robert Nachev, Parashkev Zhang, Hui Department of Computer Science Centre for Medical Image Computing University College London London United Kingdom Department of Brain Repair & Rehabilitation Institute of Neurology UCL London United Kingdom

We propose a new method, Patch-CNN, for diffusion tensor (DT) estimation from only six-direction diffusion weighted images (DWI). Deep learning-based methods have been recently proposed for dMRI parameter estimation, using either voxel-wise fully-connected neural networks (FCN) or image-wise convolutional neural networks (CNN). In the acute clinical context—where pressure of time limits the number of imaged directions to a minimum—existing approaches either require an infeasible number of training images volumes (image-wise CNNs), or do not estimate the fibre orientations (voxel-wise FCNs) required for tractogram estimation. To overcome these limitations, we propose Patch-CNN, a neural network with a minimal (non-voxel-wise) convolutional kernel (3×3×3). Compared with voxel-wise FCNs, this has the advantage of allowing the network to leverage local anatomical information. Compared with image-wise CNNs, the minimal kernel vastly reduces training data demand. Evaluated against both conventional model fitting and a voxel-wise FCN, Patch-CNN, trained with a single subject is shown to improve the estimation of both scalar dMRI parameters and fibre orientation from six-direction DWIs. The improved fibre orientation estimation is shown to produce improved tractogram. © 2023, CC BY-NC-SA.

关键词： Diffusion

来源：评论

学校读者我要写书评

暂无评论

Neurodynamics-based Iteratively Reweighted Convex Optimization for Sparse Signal Reconstruction 12

Neurodynamics-based Iteratively Reweighted Convex Optimizati...

引用

12th International Conference on Information science and Technology, ICIST 2022

作者： Che, Hangjun Wang, Jun Cichocki, Andrzej College of Electronic and Information Engineering Southwest University Chongqing Key Laboratory of Nonlinear Circuits and Intelligent Information Processing Chongqing400715 China City University of Hong Kong Department of Computer Science and School of Data Science Hong Kong Hong Kong Skolkovo Institute of Science and Technology Moscow143026 Russia

ISBN: (数字)9781665485821

ISBN: (纸本)9781665485821

In this paper, sparse signal reconstruction is for-mulated a q-ratio minimization problem subjecting to linear underdetermined equations. In view of the nonconvexity of the objective function, the q-ratio formulation with q=2 is approximately reformulated as an iteratively reweighted convex optimization problem in the majorization-minimization frame-work. A neurodynamic optimization approach is introduced to solve the formulated problem iteratively. The experimental results on sparse signal reconstruction are discussed to demonstrate the performance of the proposed approach. © 2022 IEEE.

关键词： Convex optimization

来源：评论

学校读者我要写书评

暂无评论

DenseSplat: Densifying Gaussian Splatting SLAM with Neural Radiance Prior

arXiv

引用

arXiv 2025年

作者： Li, Mingrui Liu, Shuhong Deng, Tianchen Wang, Hongyu the Department of Computer Science Dalian University of Technology Dalian China the Department of Mechano-informatics Information Science and Technology The University of Tokyo Tokyo Japan Institute of Medical Robotics Department of Automation Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education China

Gaussian SLAM systems excel in real-time rendering and fine-grained reconstruction compared to NeRF-based systems. However, their reliance on extensive keyframes is impractical for deployment in real-world robotic systems, which typically operate under sparse-view conditions that can result in substantial holes in the map. To address these challenges, we introduce DenseSplat, the first SLAM system that effectively combines the advantages of NeRF and 3DGS. DenseSplat utilizes sparse keyframes and NeRF priors for initializing primitives that densely populate maps and seamlessly fill gaps. It also implements geometry-aware primitive sampling and pruning strategies to manage granularity and enhance rendering efficiency. Moreover, DenseSplat integrates loop closure and bundle adjustment, significantly enhancing frame-to-frame tracking accuracy. Extensive experiments on multiple large-scale datasets demonstrate that DenseSplat achieves superior performance in tracking and mapping compared to current state-of-the-art methods. © 2025, CC BY.

关键词： Real time 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：