With the advances in scientific foundations and technological implementations,optical metrology has become versatile problem-solving backbones in manufacturing,fundamental research,and engineering applications,such as...With the advances in scientific foundations and technological implementations,optical metrology has become versatile problem-solving backbones in manufacturing,fundamental research,and engineering applications,such as quality control,nondestructive testing,experimental mechanics,and biomedicine.In recent years,deep learning,a subfield of machine learning,is emerging as a powerful tool to address problems by learning from data,largely driven by the availability of massive datasets,enhanced computational power,fast data storage,and novel training algorithms for the deep neural network.It is currently promoting increased interests and gaining extensive attention for its utilization in the field of optical metrology.Unlike the traditional,,physics-basedH approach,deep-learning-enabled optical metrology is a kind of,/data-drivenw approach,which has already provided numerous alternative solutions to many challenging problems in this field with better performances.In this review,we present an overview of the current status and the latest progress of deep-learning technologies in the field of optical metrology.We first briefly introduce both traditional image-processing algorithms in optical metrology and the basic concepts of deep learning,followed by a comprehensive review of its applications in various optical metrology tasks,such as fringe denoising,phase retrieval,phase unwrapping,subset correlation,and error compensation.The open challenges faced by the current deep-learning approach in optical metrology are then discussed.Finally,the directions for future research are outlined.展开更多
While originally designed for natural language processing tasks,the self-attention mechanism has recently taken various computer vision areas by storm.However,the 2D nature of images brings three challenges for applyi...While originally designed for natural language processing tasks,the self-attention mechanism has recently taken various computer vision areas by storm.However,the 2D nature of images brings three challenges for applying self-attention in computer vision:(1)treating images as 1D sequences neglects their 2D structures;(2)the quadratic complexity is too expensive for high-resolution images;(3)it only captures spatial adaptability but ignores channel adaptability.In this paper,we propose a novel linear attention named large kernel attention(LKA)to enable self-adaptive and long-range correlations in self-attention while avoiding its shortcomings.Furthermore,we present a neural network based on LKA,namely Visual Attention Network(VAN).While extremely simple,VAN achieves comparable results with similar size convolutional neural networks(CNNs)and vision transformers(ViTs)in various tasks,including image classification,object detection,semantic segmentation,panoptic segmentation,pose estimation,etc.For example,VAN-B6 achieves 87.8%accuracy on ImageNet benchmark,and sets new state-of-the-art performance(58.2%PQ)for panoptic segmentation.Besides,VAN-B2 surpasses Swin-T 4%mloU(50.1%vs.46.1%)for semantic segmentation on ADE20K benchmark,2.6%AP(48.8%vs.46.2%)for object detection on COCO dataset.It provides a novel method and a simple yet strong baseline for the community.The code is available at https://github.com/Visual-Attention-Network.展开更多
In wireless sensor network,virtual backbone is a cost effective broadcasting method.Connected dominating set formation is proposed to construct a virtual backbone.However,it is NP-Hard to find a minimum connected domi...In wireless sensor network,virtual backbone is a cost effective broadcasting method.Connected dominating set formation is proposed to construct a virtual backbone.However,it is NP-Hard to find a minimum connected dominating set in an arbitrary graph.In this paper,based on cross-entropy method,we present a novel backbone formulation algorithm(BFA-CE)in wireless sensor network.In BFA-CE,a maximal independent set is got at first and nodes in the independent set are required to get their action sets.Based on those action sets,a backbone is generated with the cross-entropy method.Simulation results show that our algorithm can effectively reduce the size of backbone network within a reasonable message overhead,and it has lower average node degree.This approach can be potentially used in designing efficient broadcasting strategy or working as a backup routing of wireless sensor network.展开更多
基金National Natural Science Foundation of China(U21B2033,62075096,62005121)Leading Technology of Jiangsu Basic Research Plan(BK20192003)+3 种基金"333 Engineering"Research Projea of Jiangsu Province(BRA2016407)Jiangsu Provincial"One belt and one road"innovation cooperation project(BZ2020007)Fundamental Research Funds for the Central Universities(30921011208,30919011222,30920032101)Open Research Fund of Jiangsu Key Laboratory of Spearal Imaging&Intelligent Sense(JSGP202105).
文摘With the advances in scientific foundations and technological implementations,optical metrology has become versatile problem-solving backbones in manufacturing,fundamental research,and engineering applications,such as quality control,nondestructive testing,experimental mechanics,and biomedicine.In recent years,deep learning,a subfield of machine learning,is emerging as a powerful tool to address problems by learning from data,largely driven by the availability of massive datasets,enhanced computational power,fast data storage,and novel training algorithms for the deep neural network.It is currently promoting increased interests and gaining extensive attention for its utilization in the field of optical metrology.Unlike the traditional,,physics-basedH approach,deep-learning-enabled optical metrology is a kind of,/data-drivenw approach,which has already provided numerous alternative solutions to many challenging problems in this field with better performances.In this review,we present an overview of the current status and the latest progress of deep-learning technologies in the field of optical metrology.We first briefly introduce both traditional image-processing algorithms in optical metrology and the basic concepts of deep learning,followed by a comprehensive review of its applications in various optical metrology tasks,such as fringe denoising,phase retrieval,phase unwrapping,subset correlation,and error compensation.The open challenges faced by the current deep-learning approach in optical metrology are then discussed.Finally,the directions for future research are outlined.
基金supported by National Key R&D Program of China(Project No.2021ZD0112902)the National Natural Science Foundation of China(Project No.62220106003)Tsinghua-Tencent Joint Laboratory for Internet Innovation Technology.
文摘While originally designed for natural language processing tasks,the self-attention mechanism has recently taken various computer vision areas by storm.However,the 2D nature of images brings three challenges for applying self-attention in computer vision:(1)treating images as 1D sequences neglects their 2D structures;(2)the quadratic complexity is too expensive for high-resolution images;(3)it only captures spatial adaptability but ignores channel adaptability.In this paper,we propose a novel linear attention named large kernel attention(LKA)to enable self-adaptive and long-range correlations in self-attention while avoiding its shortcomings.Furthermore,we present a neural network based on LKA,namely Visual Attention Network(VAN).While extremely simple,VAN achieves comparable results with similar size convolutional neural networks(CNNs)and vision transformers(ViTs)in various tasks,including image classification,object detection,semantic segmentation,panoptic segmentation,pose estimation,etc.For example,VAN-B6 achieves 87.8%accuracy on ImageNet benchmark,and sets new state-of-the-art performance(58.2%PQ)for panoptic segmentation.Besides,VAN-B2 surpasses Swin-T 4%mloU(50.1%vs.46.1%)for semantic segmentation on ADE20K benchmark,2.6%AP(48.8%vs.46.2%)for object detection on COCO dataset.It provides a novel method and a simple yet strong baseline for the community.The code is available at https://github.com/Visual-Attention-Network.
基金supported partially by the science and technology project of CQ CSTC(No.cstc2012jjA40037)
文摘In wireless sensor network,virtual backbone is a cost effective broadcasting method.Connected dominating set formation is proposed to construct a virtual backbone.However,it is NP-Hard to find a minimum connected dominating set in an arbitrary graph.In this paper,based on cross-entropy method,we present a novel backbone formulation algorithm(BFA-CE)in wireless sensor network.In BFA-CE,a maximal independent set is got at first and nodes in the independent set are required to get their action sets.Based on those action sets,a backbone is generated with the cross-entropy method.Simulation results show that our algorithm can effectively reduce the size of backbone network within a reasonable message overhead,and it has lower average node degree.This approach can be potentially used in designing efficient broadcasting strategy or working as a backup routing of wireless sensor network.
