检索结果-内蒙古大学图书馆

Peer is Your Pillar: A Data-unbalanced Conditional GANs for Few-shot Image Generation

学校读者我要写书评

暂无评论

arXiv

arXiv 2023年

作者： Li, Ziqiang Wang, Chaoyue Rui, Xue Xue, Chao Leng, Jiaxu Li, Bin Big Data and Decision Lab University of Science and Technology of China China The University of Sydney Australia JD Explore Academic China School of computer science Chongqing University of Posts and Telecommunications China CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System China

Few-shot image generation aims to train generative models using a small number of training images. When there are few images available for training (e.g. 10 images), Learning From Scratch (LFS) methods often generate images that closely resemble the training data while Transfer Learning (TL) methods try to improve performance by leveraging prior knowledge from GANs pre-trained on large-scale datasets. However, current TL methods may not allow for sufficient control over the degree of knowledge preservation from the source model, making them unsuitable for setups where the source and target domains are not closely related. To address this, we propose a novel pipeline called Peer is your Pillar (PIP), which combines a target few-shot dataset with a peer dataset to create a data-unbalanced conditional generation. Our approach includes a class embedding method that separates the class space from the latent space, and we use a direction loss based on pre-trained CLIP to improve image diversity. Experiments on various few-shot datasets demonstrate the advancement of the proposed PIP, especially reduces the training requirements of few-shot image generation. © 2023, CC BY.

关键词： Large dataset

Compact Ld Side-Pumped Nd:Yag Oscillator at 100 Hz Without Water-Cooling

学校读者我要写书评

暂无评论

SSRN 2023年

作者： Yang, Zeqi Cong, Zhenhua Meng, Jun Wang, Shang Zhao, Zhigang Liu, Gaoyou Liu, Zhaojun Key Laboratory of Laser and Infrared System Integration Technology Ministry of Education Shandong University Qingdao266237 China The School of Information Science and Engineering Shandong University Qingdao266237 China Shandong Provincial Key Laboratory of Laser Technology and Application Shandong University Qingdao266237 China Center for Optics Research and Engineering Shandong University Qingdao266237 China

A high-repetition-frequency side-pumped electro-optical (E-O) Q-switched Nd:YAG laser without water cooling is reported. A 100 Hz laser module without water-cooling was designed and the related parameters of crystal are simulated. The crystal is annularly pumped in both ends and is conductively cooled in the middle. The heat generated by crystal and laser diode is dissipated by thermoelectric cooler (TEC), fins and fan. The 1064 nm maximum output energy is 68 mJ with a pulse width of 31 ns and a repetition rate of 100 Hz. The optical-optical conversion efficiency is 10.6%. To the best of our knowledge, this is the first report of 100 Hz repetition rate operation for a E-O Q-switched Nd:YAG rod laser without water-cooling. © 2023, The Authors. All rights reserved.

关键词： Yttrium aluminum garnet

Satellite-observed changes in terrestrial vegetation growth trends across the Asia-Pacific region associated with land cover and climate from 1982 to 2011

学校读者我要写书评

暂无评论

International Journal of Digital Earth 2016年第11期9卷 1055-1076页

作者： Baozhang Chen Guang Xu Nicholas C.Coops Philippe Ciais Ranga B.Myneni Key Laboratory of Soil and Water Conservation and Desertification Combating Ministry of EducationBeijing Forestry UniversityBeijingPeople’s Republic of China School of Environment Science and Spatial Informatics China University of Mining and TechnologyXuzhouPeople’s Republic of China Jiangsu Center for Collaborative Innovation in Geographic Information Resource Development and Application NanjingPeople’s Republic of China State Key Laboratory of Resources and Environmental Information System Institute of Geographic Sciences and Natural Resources ResearchChinese Academy of SciencesBeijingPeople’s Republic of China University of Chinese Academy of Sciences BeijingPeople’s Republic of China Department of Forest Resource Management University of British ColumbiaVancouverBCCanada Laboratoire des Sciences du Climat et de l’Environnement UnitéMixte de Recherche Commissariatàl’Energie AtomiqueCentre National de la Recherche ScientifiqueUniversitéde Versailles Saint-Quentin-en-YvelinesGif-sur-YvetteFrance Department of Earth and Environment Boston UniversityBostonMAUSA

The Asia-Pacific(AP)region has experienced faster warming than the global average in recent decades and has experienced more climate extremes,however little is known about the response of vegetation growth to these *** updated Global Inventory Modeling and Mapping Studies third-generation global satellite Advanced Very High Resolution Radiometer Normalized Difference Vegetation Index dataset and gridded reanalysis climate data were used to investigate the spatiotemporal changes in both trends of vegetation dynamic indicators and climatic *** then further analyzed their relations associated with land cover across the AP *** main findings are threefold:(1)at continental scales the AP region overall experienced a gradual and significant increasing trend in vegetation growth during the last three decades,and this NDVI trend corresponded with an insignificant increasing trend in temperature;(2)vegetation growth was negatively and significantly correlated with the Pacific Decadal Oscillation index and the El Niño/Southern Oscillation(ENSO)in AP;and(3)at pixel scales,except for Australia,both vegetation growth and air temperature significantly increased in the majority of study regions and vegetation growth spatially correlated with temperature;In Australia and other water-limited regions vegetation growth positively correlated with precipitation.

关键词： Vegetation dynamics NDVI climate change land cover Asia-Pacific region

K-Wise Multi-Graph Matching

学校读者我要写书评

暂无评论

SSRN 2023年

作者： Zhu, Xinwen Zhu, Liangliang Geng, Xiurui Aerospace Information Research Institute Chinese Academy of Sciences Beijing100864 China School of Electronic Electrical and Communication Engineering University of Chinese Academy of Sciences Beijing100049 China Key Laboratory of Technology in Geo-Spatial Information Processing and Application System Chinese Academy of Sciences Beijing100864 China

Multi-graph matching, which aims to find the correspondences of multiple graphs, is an extension of conventional two-graph matching. There are mainly two categories of multi-graph matching methods, i.e., the pairwise-based methods and the tensor-based methods. Both of them try to find the correspondences between graphs by maximizing the values of the similarities between the corresponding features, e.g., nodes, edges, and so on. The difference is that for a set of features from different graphs to be matched, the pairwise-based methods consider the similarities of every two features, while the tensor-based methods directly consider the whole similarity among them. Therefore, the measurement of similarities in the tensor-based methods is usually much more flexible than that in the pairwise-based methods. However, the time and space complexities of the tensor-based methods grow geometrically as the number of graphs to be matched increases. In this paper, through a comprehensive investigation, we propose a k-wise multi-graph matching method which includes the aforementioned two kinds of methods as special cases. Generally, by choosing different value of k, it could be found that the proposed algorithm can strike a balance between flexible similarity measurement and low computational complexity. In addition, a factorization of k-wise global affinity matrix is proposed to save the computational cost of our method. Experiments with synthetic and real data demonstrate the superiority of our method. © 2023, The Authors. All rights reserved.

关键词： Tensors

Understanding the Long-Distance Travel Mobility of Passengers Based on Big Railway Data: Travel Network and Motif Perspectives

学校读者我要写书评

暂无评论

SSRN 2022年

作者： Xu, Jin Song, Haonan Lu, Zhaoyang Department of Information System & Operation Management School of Economics and Management Southwest Jiaotong University Sichuan Chengdu China National Engineering Laboratory of Integrated Transportation Big Data Application Technology Sichuan Chengdu China Service Science and Innovation Key Laboratory of Sichuan Province Sichuan Chengdu China

With the booming construction of new railway lines and stations in China, the number of railway passengers is increasing. The large railway population shows certain mobility characteristics that we are interested in clarifying. Based on the theory of complex networks, this paper proposes a novel method to identify travel patterns from big railway data, which associates travel motifs with travel networks. This paper derives some meaningful results from the data analysis of more than three million railway travel records of a city in China. These results illustrate that higher motif complexity leads to a narrower travel radius for motif-based subnets. The higher the stability of the travel sequence is, the shorter the average length of the sequence. Four types of travel patterns are identified and classified by analyzing the motif of travel activities, i.e., labor, tourism, surrounding and commuting. The methodology and findings presented in this paper contribute to a better understanding of the long-distance travel mobility of railway passengers. The method designed in this paper can also be used to analyze traffic data from airlines, buses, subways, etc. © 2022, The Authors. All rights reserved.

关键词： Complex networks

Red edge characteristics and leaf area index estimation model using hyperspectral data for rape

学校读者我要写书评

暂无评论

Rengong Jingti Xuebao/Journal of Synthetic Crystals 2006年第4期35卷 22-26页

作者： Huang, Jingfeng Wang, Yuan Wang, Fumin Liu, Zhanyu Institute of Agricultural Remote Sensing and Information Application Center of Agricultural Information Science and Technology Zhejiang University Key Laboratory of Agricultural Remote Sensing and Information System Application Hangzhou 310029 China

The hyperspectral reflectances for rape canopies consisting of five cultivars and three nitrogen levels were measured in 2003~2004 growth period by an ASD FieldSpec Pro FR [trademark] . The corresponding leaf area indices were observed. The red edge parameters were extracted using the spectral reflectances of the rape canopies. There exist 'two peak' phenomena for the red edge of rape canopy spectra. The position of red edge λred is located between 690 nm and 720 nm. There is a 'platform of red edge' at the bloom stage of rape. The red edge shift was detected before flowering stage and blue shift after flowering stage. The relationship between red edge parameters and the leaf area index (LAI) was investigated during 8 development periods. Results were not consistently significant at any wavelengths. The leaf area indices were significantly correlative to the red edge parameters λred, Dλred and Sred of the canopy spectra before flowering stage, whereas the correlation coefficient showed very low r values that were in significant after flowering stage. So the red edge parameters of rape canopies before the flowering stage can be used to estimate the leaf area indices. The results for different stages, linear and non-linear regression models were compared and the optimum model for LAI before flowering stage was recommended.

关键词：

A Simplified Process for Freestanding Diffractive Spiral Photon Sieves in Extreme Ultraviolet

学校读者我要写书评

暂无评论

SSRN 2022年

作者： Mu, Chengyang Chen, Yifang Zhang, Junyong Cui, Huaiyu Zhao, Yongpeng Nanolithography and Application Research Group State Key Laboratory of ASIC and System School of Information Science and Engineering Fudan University Shanghai200433 China Joint Laboratory on High Power Laser and Physics Shanghai Institute of Optics and Fine Mechanics Chinese Academy of Science Shanghai201800 China National Key Laboratory of Science and Technology on Tunable Laser Harbin Institute of Technology Harbin150080 China

Spiral zone plates in the form of photon sieves are one of the important phase modulation devices, being well developed in both visible lights and X-rays for mode conversion from Gaussian beam to vortex one. However, in extreme ultraviolet (EUV) region as a diffractive focusing lens, spiral photon sieves in freestanding SiNx membrane with through-holes to avoid significant absorptions of EUV light by the membrane material, still remain a big challenge in manufacturing. In this work, a simplified nanofabrication process using electron beam lithography directly followed by reactive ion etch, was developed. The fabricated spiral photon sieves involve two layers of SiNx/ZEP520A with the focusing efficiency estimated to be 23%. Optical characterization of the converted vortex beam by using a typical imprint technique was carried out using a 46.9 nm EUV laser. Donut-shaped ablation pattern by EUV laser was observed on the exposed PMMA (polymethyl methacrylate), proving the phase modulation functionality of the fabricated freestanding spiral photon sieves. The developed fabrication process greatly simplifies the manufacturing of freestanding zone plates/photon sieves as well as other freestanding nanometer structures, and should be applicable in the production in large volume. © 2022, The Authors. All rights reserved.

关键词： Gaussian beams

Building area extraction from the high spatial resolution remote sensing imagery

学校读者我要写书评

暂无评论

Earth Science Informatics 2018年第1期12卷 19-29页

作者： Shi, Wenzao Mao, Zhengyuan Liu, Jinqing Fujian Provincial Engineering Technology Research Center of Photoelectric Sensing Application Fujian Normal University Fuzhou People’s Republic of China Key Laboratory of OptoElectronic Science and Technology for Medicine of Ministry of Education Fujian Provincial Key Laboratory for Photonics Technology Fujian Normal University Fuzhou People’s Republic of China College of Photonic and Electronic Engineering Fujian Normal University Fuzhou China Key Lab of Spatial Data Mining & Information Sharing of Ministry of Education Fuzhou University Fuzhou People’s Republic of China National Engineering Research Centre of Geospatial Information Technology Fuzhou University Fuzhou People’s Republic of China Spatial Information Engineering Research Centre of Fujian Province Fuzhou University Fuzhou People’s Republic of China

An approach to building area extraction from high-resolution remote sensing imagery is proposed based on the local gradient orientation density function (LGODF) and the bimodal density function (BDF). Firstly, the LGODF is calculated by moving the window of 35 × 35 based on the gradient magnitude and the gradient direction of each pixel in the image. Then, the BDF is obtained by multiplying the movable bimodal Gaussian mixture function and LGODF in each window. Finally, peaks with difference of 90° are searched for in the BDF, and the central point of the corresponding windows are determined as building pixels. For the validity of the proposed method, seven representative sub-images from PLEIADES images covering Shenzhen China are selected. Experimental results reveal that the precision achieve 94.08% and the recall up to 96.70%.

关键词：

Rpsa: Riemannian Principal Skewness Analysis

学校读者我要写书评

暂无评论

SSRN 2023年

作者： Geng, Xiurui Gao, Jingyu Aerospace Information Research Institute Chinese Academy of Sciences Beijing100864 China School of Electronic Electrical and Communication Engineering University of Chinese Academy of Sciences Beijing100049 China Key Laboratory of Technology in Geo-Spatial Information Processing and Application System Chinese Academy of Sciences Beijing100864 China

By transforming the determination of the principal skewness direction of data into the solution of the eigenpair (eigenvalue and eigenvector) of its coskewness tensor, the principal skewness analysis (PSA) has been introduced into the blind source separation (BSS) community. Different from the eigenpair problem of a matrix which has been extensively and thoroughly studied, the solution of the eigenpairs of a coskewness tensor is a recently emerging research topic and can only be obtained by means of optimization at present. Generally, the iteration direction and the iteration step size are the two most critical factors in optimization methods. As the iteration direction, the conventional gradient has been widely used to solve the eigenpairs of a coskewness tensor in the existing methods. However, in this paper, we have found that compared with the conventional gradient, Riemannian gradient as the search direction is more conducive to avoid the current eigenvector converging to the ones that have been obtained. In addition, in order to obtain the rest locally maximal eigenpairs of a coskewness tensor, a new step-size adjustment strategy is also designed in this study. Experiments on simulated and real data demonstrate the effectiveness and superiority of the presented method. © 2023, The Authors. All rights reserved.

关键词： Tensors