检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Ju, Yakun Lam, Kin-Man Xie, Wuyuan Zhou, Huiyu Dong, Junyu Shi, Boxin School of Electrical and Electronic Engineering Nanyang Technological University Singapore The Department of Electrical and Electronic Engineering The Hong Kong Polytechnic University Hong Kong The Research Institute for Future Media Computing Shenzhen University Shenzhen China The Department of Informatics University of Leicester Leicester United Kingdom The Faculty of Information Science and Engineering The Institute for Advanced Ocean Study Ocean University of China Qingdao China The National Key Laboratory for Multimedia Information Processing National Engineering Research Center of Visual Technology School of Computer Science Peking University Beijing China

Photometric stereo recovers the surface normals of an object from multiple images with varying shading cues, i.e., modeling the relationship between surface orientation and intensity at each pixel. Photometric stereo prevails in superior per-pixel resolution and fine reconstruction details. However, it is a complicated problem because of the non-linear relationship caused by non-Lambertian surface reflectance. Recently, various deep learning methods have shown a powerful ability in the context of photometric stereo against non-Lambertian surfaces. This paper provides a comprehensive review of existing deep learning-based calibrated photometric stereo methods utilizing orthographic cameras and directional light sources. We first analyze these methods from different perspectives, including input processing, supervision, and network architecture. We summarize the performance of deep learning photometric stereo models on the most widely-used benchmark data set. This demonstrates the advanced performance of deep learning-based photometric stereo methods. Finally, we give suggestions and propose future research trends based on the limitations of existing models. Copyright © 2022, The Authors. All rights reserved.

关键词： Light sources

来源：评论

学校读者我要写书评

暂无评论

Class-Imbalanced Semi-Supervised Learning for Large-Scale Point Cloud Semantic Segmentation Via Decoupling Optimization

SSRN

引用

SSRN 2023年

作者： Li, Mengtian Lin, Shaohui Wang, Zihan Shen, Yunhang Zhang, Baochang Ma, Lizhuang Visual Media Intelligent Processing Research Group Department of Film and Television Engineering Shanghai University Shanghai200072 China School of Computer Science and Technology East China Normal University Shanghai200062 China Key Laboratory of Advanced Theory and Application in Statistics and Data Science Ministry of Education China School of Automation Science and Electrical Engineering Beihang University Beijing100191 China Youtu Lab Tencent China

Semi-supervised learning (SSL), thanks to the significant reduction of data annotation costs, has been an active research topic for large-scale 3D scene understanding. However, the existing SSL-based methods suffer from severe training bias, mainly due to class imbalance and long-tail distributions of the point cloud data. As a result, they lead to a biased prediction for the tail class segmentation. In this paper, we introduce a new decoupling optimization framework, which disentangles feature representation learning and classifier in an alternative optimization manner to shift the bias decision boundary effectively. In particular, we first employ two-round pseudo-label generation to select unlabeled points across head-to-tail classes. We further introduce multi-class imbalanced focus loss to adaptively pay more attention to feature learning across head-to-tail classes. We fix the backbone parameters after feature learning and retrain the classifier using ground-truth points to update its parameters. Ex-✩Fully documented templates are available in the elsarticle package on CTAN. © 2023, 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

Attention-Guided Multi-scale Interaction Network for Face Super-Resolution

arXiv

引用

arXiv 2024年

作者： Wan, Xujie Li, Wenjie Gao, Guangwei Lu, Huimin Yang, Jian Lin, Chia-Wen The Institute of Advanced Technology Nanjing University of Posts and Telecommunications Nanjing210046 China Key Laboratory of Artificial Intelligence Ministry of Education Shanghai200240 China The Provincial Key Laboratory for Computer Information Processing Technology Soochow University Suzhou215006 China The Pattern Recognition and Intelligent System Laboratory School of Artificial Intelligence Beijing University of Posts and Telecommunications Beijing100080 China The School of Automation Southeast University Nanjing210096 China The School of Computer Science and Technology Nanjing University of Science and Technology Nanjing210094 China The Department of Electrical Engineering National Tsing Hua University Hsinchu30013 Taiwan

Recently, CNN and Transformer hybrid networks demonstrated excellent performance in face super-resolution (FSR) tasks. Since numerous features at different scales in hybrid networks, how to fuse these multi-scale features and promote their complementarity is crucial for enhancing FSR. However, existing hybrid network-based FSR methods ignore this, only simply combining the Transformer and CNN. To address this issue, we propose an attention-guided Multi-scale interaction network (AMINet), which contains local and global feature interactions as well as encoder-decoder phases feature interactions. Specifically, we propose a Local and Global Feature Interaction Module (LGFI) to promote fusions of global features and different receptive fields' local features extracted by our Residual Depth Feature Extraction Module (RDFE). Additionally, we propose a Selective Kernel Attention Fusion Module (SKAF) to adaptively select fusions of different features within LGFI and encoder-decoder phases. Our above design allows the free flow of multi-scale features from within modules and between encoder and decoder, which can promote the complementarity of different scale features to enhance FSR. Comprehensive experiments confirm that our method consistently performs well with less computational consumption and faster inference. Copyright © 2024, The Authors. All rights reserved.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

Prox-DBRO-VR: A Unified Analysis on Byzantine-Resilient Decentralized Stochastic Composite Optimization with Variance Reduction

arXiv

引用

arXiv 2023年

作者： Hu, Jinhui Chen, Guo Li, Huaqing Guo, Xiaoyu Ran, Liang Huang, Tingwen School of Automation Central South University Hunan Changsha410083 China School of Electrical Engineering and Telecommunications University of New South Wales SydneyNSW2052 Australia Department of Mechanical Engineering City University of Hong Kong Kowloon Tong Hong Kong Chongqing Key Laboratory of Nonlinear Circuits and Intelligent Information Processing College of Electronic and Information Engineering Southwest University Chongqing400715 China Faculty of Computer Science and Control Engineering Shenzhen University of Advanced Technology Shenzhen518055 China

Decentralized stochastic gradient algorithms efficiently solve large-scale finite-sum optimization problems when all agents in the network are reliable. However, most of these algorithms are not resilient to adverse conditions, such as malfunctioning agents, software bugs, and cyber attacks. This paper aims to handle a class of general composite optimization problems over multi-agent systems (MASs) in the presence of an unknown number of Byzantine agents. Building on a resilient model-aggregation mechanism and the proximal-gradient mapping method, a Byzantine-resilient decentralized stochastic proximal-gradient algorithmic framework is proposed, dubbed ProxDBRO-VR, which achieves an optimization and control goal using only local computations and communications. To asymptotically reduce the noise variance arising from local gradient estimation and accelerate the convergence, we incorporate two localized variance-reduced (VR) techniques (SAGA and LSVRG) into ProxDBRO-VR to design Prox-DBRO-SAGA and Prox-DBRO-LSVRG. By analyzing the contraction relationships among the gradient-learning error, resilient consensus condition, and convergence error in a unified theoretical framework, it is proved that both Prox-DBRO-SAGA and Prox-DBRO-LSVRG, with a well-designed constant (resp., decaying) step-size, converge linearly (resp., sub-linearly) inside an error ball around the optimal solution to the original problem under standard assumptions. A trade-off between convergence accuracy and Byzantine resilience in both linear and sub-linear cases is also characterized. In numerical experiments, the effectiveness and practicability of the proposed algorithms are manifested via resolving a decentralized sparse machine-learning problem under various Byzantine attacks. Copyright © 2023, The Authors. All rights reserved.

关键词： Autonomous agents

来源：评论

学校读者我要写书评

暂无评论

Angel's girl for blind painters: An efficient painting navigation system validated by multimodal evaluation approach

arXiv

引用

arXiv 2021年

作者： Liu, Hang Hu, Menghan Chen, Yuzhen Li, Qingli Zhai, Guangtao Yang, Simon X. Zhang, Xiao-Ping Yang, Xiaokang The Shanghai Key Laboratory of Multidimensional Information Processing East China Normal University The Key Laboratory of Articial Intelligence Ministry of Education The Advanced Robotics and Intelligent Systems Laboratory School of Engineering University of Guelph The Department of Electrical Computer and Biomedical Engineering Ryerson University

For people who ardently love painting but unfortunately have visual impairments, holding a paintbrush to create a work is a very difficult task. People in this special group are eager to pick up the paintbrush, like Leonardo da Vinci, to create and make full use of their own talents. Therefore, to maximally bridge this gap, we propose a painting navigation system to assist blind people in painting and artistic creation. The proposed system is composed of cognitive system and guidance system. The system adopts drawing board positioning based on QR code, brush navigation based on target detection and bush real-time positioning. Meanwhile, this paper uses human-computer interaction on the basis of voice and a simple but efficient position information coding rule. In addition, we design a criterion to efficiently judge whether the brush reaches the target or not. According to the experimental results, the thermal curves extracted from the faces of testers show that it is relatively well accepted by blindfolded and even blind testers. With the prompt frequency of 1s, the painting navigation system performs best with the completion degree of 89% ± 8.37% and overflow degree of 347% ± 162.14%. Meanwhile, the excellent and good types of brush tip trajectory account for 74%, and the relative movement distance is 4.21 ± 2.51. This work demonstrates that it is practicable for the blind people to feel the world through the brush in their hands. In the future, we plan to deploy "Angle's Eyes" on the phone to make it more portable. The demo video of the proposed painting navigation system is available at: https://***/10.6084/***.9760004.v1. © 2021, CC BY.

关键词： Cognitive systems

来源：评论

学校读者我要写书评

暂无评论

Correction to: Multi-level context-driven interaction modeling for human future trajectory prediction

引用

Neural Computing and Applications 2023年第27期35卷 20441-20441页

作者： He, Zhiquan Sun, Hao Cao, Wenming He, Henry Z. Guangdong Multimedia Information Service Engineering Technology Research Center Shenzhen University Shenzhen China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen China Video Processing and Communication Laboratory Department of Electrical and Computer Engineering University of Missouri Columbia USA

来源：评论

学校读者我要写书评

暂无评论

Photonic Terahertz Phased Array

arXiv

引用

arXiv 2024年

作者： Niu, Li Feng, Xi Zhang, Xueqian Lu, Yongchang Wang, Qingwei Xu, Quan Chen, Xieyu Ma, Jiajun Qiu, Haidi Sha, Wei E.I. Zhang, Shuang Alù, Andrea Zhang, Weili Han, Jiaguang Center for Terahertz Waves College of Precision Instrument and Optoelectronics Engineering The Key Laboratory of Optoelectronics Information and Technology Tianjin University Tianjin300072 China Key Laboratory of Micro-nano Electronic Devices and Smart Systems of Zhejiang Province College of Information Science & Electronic Engineering Zhejiang University Hangzhou310027 China Department of Electrical & Electronic Engineering University of Hong Kong 999077 Hong Kong Photonics Initiative Advanced Science Research Center City University of New York New York10031 United States Physics Program Graduate Center City University of New York New York10016 United States School of Electrical and Computer Engineering Oklahoma State University StillwaterOK74078 United States Guangxi Key Laboratory of Optoelectronic Information Processing School of Optoelectronic Engineering Guilin University of Electronic Technology Guilin541004 China

Phased arrays are crucial in various technologies, such as radar and wireless communications, due to their ability to precisely control and steer electromagnetic waves. This precise control improves signal processing and enhances imaging performance. However, extending phased arrays to the terahertz (THz) frequency range has proven challenging, especially for high-frequency operation, broadband performance, two-dimensional (2D) phase control with large antenna arrays, and strong phase modulation. Here, we introduce a photonic platform to realize a THz phased array that bypasses the above challenges. Our method employs 2D phase coding with 2-bit across a broad THz frequency range from 0.8 to 1.4 THz. The core of our design is a pixelated nonlinear Pancharatnam-Berry metasurface driven by a spatially modulated femtosecond laser, allowing precise phase control of THz signals. We showcase the effectiveness of our method through four proof-of-concept applications: single beamforming, dual beamforming, imaging and vortex beam generation. The realized photonic platform provides a promising pathway for developing broadband phased arrays in the THz regime. Copyright © 2024, The Authors. All rights reserved.

关键词： Terahertz waves

来源：评论

学校读者我要写书评

暂无评论

Weakly-Supervised Semantic Segmentation of Circular-Scan, Synthetic-Aperture-Sonar Imagery

arXiv

引用

arXiv 2024年

作者： Sledge, Isaac J. Byrne, Dominic M. King, Jonathan L. Ostertag, Steven H. Woods, Denton L. Prater, James L. Kennedy, Jermaine L. Marston, Timothy M. Príncipe, José C. The Advanced Signal Processing and Automated Target Recognition Branch Naval Surface Warfare Center Panama CityFL United States The Naval Sea Systems Command United States The Applied Sensing and Processing Branch Naval Surface Warfare Center Panama CityFL United States The Littoral Acoustics and Target Physics Branch Naval Surface Warfare Center Panama CityFL United States The Division Head of the Sensing Sciences and Systems Division Naval Surface Warfare Center Panama CityFL United States The Applied Physics Laboratory University of Washington SeattleWA United States The Department of Electrical and Computer Engineering The Department of Biomedical Engineering University of Florida GainesvilleFL United States The University of Florida United States

We propose a weakly-supervised framework for the semantic segmentation of circular-scan synthetic-aperture-sonar (CSAS) imagery. The first part of our framework is trained in a supervised manner, on image-level labels, to uncover a set of semi-sparse, spatially-discriminative regions in each image. The classification uncertainty of each region is then evaluated. Those areas with the lowest uncertainties are then chosen to be weakly labeled segmentation seeds, at the pixel level, for the second part of the framework. Each of the seed extents are progressively resized according to an unsupervised, information-theoretic loss with structured-prediction regularizers. This reshaping process uses multi-scale, adaptively-weighted features to delineate class-specific transitions in local image content. Content-addressable memories are inserted at various parts of our framework so that it can leverage features from previously seen images to improve segmentation performance for related images. We evaluate our weakly-supervised framework using real-world CSAS imagery that contains over ten seafloor classes and ten target classes. We show that our framework performs comparably to nine fully-supervised deep networks. Our framework also outperforms eleven of the best weakly-supervised deep networks. We achieve state-of-the-art performance when pre-training on natural imagery. The average absolute performance gap to the next-best weakly-supervised network is well over ten percent for both natural imagery and sonar imagery. This gap is found to be statistically significant. © 2024, CC BY.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Mechanically reprogrammable Pancharatnam-Berry metasurface for microwaves

引用

advanced Photonics 2022年第1期4卷 69-79页

作者： Quan Xu Xiaoqiang Su Xueqian Zhang Lijuan Dong Lifeng Liu Yunlong Shi Qiu Wang Ming Kang Andrea Alù Shuang Zhang Jiaguang Han Weili Zhang Tianjin University Center for Terahertz Waves and College of Precision Instrument and Optoelectronics EngineeringKey Laboratory of Optoelectronic Information Technology(Ministry of Education of China)TianjinChina Shanxi Datong University Institute of Solid State Physics and College of Physics and Electronic ScienceShanxi Province Key Laboratory of Microstructure Electromagnetic Functional MaterialsDatongChina Wuhan University of Technology School of Information EngineeringWuhanChina Tianjin Normal University College of Physics and Materials ScienceTianjinChina City University of New York Advanced Science Research CenterPhotonics InitiativeNew YorkUnited States City University of New York Graduate CenterPhysics ProgramNew YorkUnited States University of Hong Kong Faculty of ScienceDepartment of PhysicsHong KongChina University of Hong Kong Department of Electrical and Electronic EngineeringHong KongChina Guilin University of Electronic Technology Guangxi Key Laboratory of Optoelectronic Information ProcessingSchool of Optoelectronic EngineeringGuilinChina Oklahoma State University School of Electrical and Computer EngineeringStillwaterOklahomaUnited States

Metasurfaces have enabled the realization of several optical functionalities over an ultrathin platform,fostering the exciting field of flat *** metasurfaces are achieved by arranging a layout of static meta-atoms to imprint a desired operation on the impinging wavefront,but their functionality cannot be *** and programmability of metasurfaces are the next important step to broaden their impact,adding customized on-demand functionality in which each meta-atom can be individually *** demonstrate a mechanical metasurface platform with controllable rotation at the meta-atom level,which can implement continuous Pancharatnam–Berry phase control of circularly polarized *** the proof-of-concept experiments,we demonstrate metalensing,focused vortex beam generation,and holographic imaging in the same metasurface template,exhibiting versatility and superior *** dynamic control of electromagnetic waves using a single,low-cost metasurface paves an avenue towards practical applications,driving the field of reprogrammable intelligent metasurfaces for a variety of applications.

关键词： reprogrammable metasurfaces Pancharatnam-Berry phase mechanical metasurfaces microwaves

来源：评论

学校读者我要写书评

暂无评论

Contrastive Bayesian Analysis for Deep Metric Learning

arXiv

引用

arXiv 2022年

作者： Kan, Shichao He, Zhiquan Cen, Yigang Li, Yang Mladenovic, Vladimir He, Zhihai School of Computer Science and Engineering Central South University Hunan Changsha410083 China Institute of Information Science School of Computer and Information Technology Beijing Jiaotong University Beijing100044 China Beijing Key Laboratory of Advanced Information Science and Network Technology Beijing100044 China Guangdong Multimedia Information Service Engineering Technology Research Center Shenzhen University 518060 China Department of Electrical Engineering and Computer Science University of Missouri ColumbiaMO65211 United States Faculty of Technical Sciences University of Kragujevac Cacak Serbia Department of Electrical and Electronic Engineering Southern University of Science and Technology Shenzhen China Pengcheng Lab Shenzhen518066 China

Recent methods for deep metric learning have been focusing on designing different contrastive loss functions between positive and negative pairs of samples so that the learned feature embedding is able to pull positive samples of the same class closer and push negative samples from different classes away from each other. In this work, we recognize that there is a significant semantic gap between features at the intermediate feature layer and class labels at the final output layer. To bridge this gap, we develop a contrastive Bayesian analysis to characterize and model the posterior probabilities of image labels conditioned by their features similarity in a contrastive learning setting. This contrastive Bayesian analysis leads to a new loss function for deep metric learning. To improve the generalization capability of the proposed method onto new classes, we further extend the contrastive Bayesian loss with a metric variance constraint. Our experimental results and ablation studies demonstrate that the proposed contrastive Bayesian metric learning method significantly improves the performance of deep metric learning in both supervised and pseudo-supervised scenarios, outperforming existing methods by a large margin. © 2022, CC0.

关键词： Distance education

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：