云南高校图书馆联盟文献共享服务平台- FEW

FEW: 作品数：513被引量：542H指数：10; 导出分析报告; 相关领域：医药卫生更多>>; 相关作者：孙善长刘天键蒋汉祥张廷波赵秀华更多>>; 相关机构：兰州理工大学中国科学技术大学西安电子科技大学四川师范大学更多>>; 相关期刊：更多>>; 相关基金：国家自然科学基金国家重点基础研究发展计划中国博士后科学基金天津市自然科学基金更多>>

A Category-Agnostic Hybrid Contrastive Learning Method for Few-Shot Point Cloud Object Detection: 《Computers, Materials & Continua》2025年第5期1667-1681,共15页Xuejing Li; Few-shot point cloud 3D object detection(FS3D)aims to identify and locate objects of novel classes within point clouds using knowledge acquired from annotated base classes and a minimal number of samples from the nove...; 关键词：Contrastive learning few-shot learning point cloud object detection

Two-Stage Category-Guided Frequency Modulation for Few-Shot Semantic Segmentation: 《Computers, Materials & Continua》2025年第5期1707-1726,共20页Yiming Tang Yanqiu Chen; Semantic segmentation of novel object categories with limited labeled data remains a challenging problem in computer vision.Few-shot segmentation methods aim to address this problem by recognizing objects from specifi...; 关键词：Few-shot semantic segmentation frequency feature category representation

Bottom-up approaches to form superatom-assembled 2D few-layered borophanes and carborophanes and 3Dα-B_(12),γ-B_(28),and B_(4)C based on icosahedral B_(12) and CB_(11): 《Nano Research》2025年第4期625-632,共8页Qiao-Qiao Yan Wen-Yan Zan Yue-Wen Mu Si-Dian Li; supported by the National Natural Science Foundation of China(No.22373061).; Using the experimentally known aromatic icosahedral I_(h) B_(12)H_(12)^(2-)and C_(5v)B_(11)CH_(12)-as building blocks and based on extensive density functional theory calculations,we present herein bottom-up approache...; 关键词：boron nanomaterials bottom-up approaches density functional theory Wade’s rule borophanes carborophanes

TiO_(2)-supported Ni_(4) quadruple-atom catalyst:A promising few-atom catalyst with high atomic utilization: 《Nano Research》2025年第4期645-657,共13页Furui Chen Guangce Zhao Gang Zhou; supported by the National Natural Science Foundation of China(No.52272199).; Using density functional theory calculations,we investigate the growth habit and structural stability of Ni_(4) tetramer on TiO_(2)(Ni_(4)/TiO_(2)),which acts as a representative of oxide-supported few-atom catalysts(...; 关键词：few-atom catalysts quadruple-atom atomic utilization density functional theory hydrogen production TiO_(2)-supported Ni_(4)

Gate-controlled multistate modulation in few-layer graphene via layer-by-layer ion intercalation: 《Science China(Physics,Mechanics & Astronomy)》2025年第4期1-8,共8页Siyi Zhou Shaorui Li Yongchao Wang Chenglin Yu Yayu Wang Jinsong Zhang; supported by the National Natural Science Foundation of China(Grant Nos.12274252,and 12350404);the Basic Science Center Project of NSFC(Grant No.52388201);the Innovation Program for Quantum Science and Technology(Grant No.2021ZD0302502)。; The simultaneous modulation of electric and optical properties in graphene is essential for advancing high-performance applications in optoelectronics.However,achieving in-situ control of multiple electric and optical...; 关键词：GRAPHENE gate control ion intercalation multistate modulation

CAMSNet:Few-Shot Semantic Segmentation via Class Activation Map and Self-Cross Attention Block: 《Computers, Materials & Continua》2025年第3期5363-5386,共24页Jingjing Yan Xuyang Zhuang Xuezhuan Zhao Xiaoyan Shao Jiaqi Han; supported by funding from the following sources:National Natural Science Foundation of China(U1904119);Research Programs of Henan Science and Technology Department(232102210033,232102210054);Chongqing Natural Science Foundation(CSTB2023NSCQ-MSX0070);Henan Province Key Research and Development Project(231111212000);Aviation Science Foundation(20230001055002);supported by Henan Center for Outstanding Overseas Scientists(GZS2022011).; The key to the success of few-shot semantic segmentation(FSS)depends on the efficient use of limited annotated support set to accurately segment novel classes in the query set.Due to the few samples in the support set...; 关键词：Few-shot semantic segmentation semantic segmentation meta learning

Few-shot anomaly detection with adaptive feature transformation and descriptor construction: 《Chinese Journal of Aeronautics》2025年第3期491-504,共14页Zhengnan HU Xiangrui ZENG Yiqun LI Zhouping YIN Erli MENG Leyan ZHU Xianghao KONG; supported by the National Natural Science Foundation of China(No.52188102).; Anomaly Detection (AD) has been extensively adopted in industrial settings to facilitate quality control of products. It is critical to industrial production, especially to areas such as aircraft manufacturing, which ...; 关键词：Industrial applications Anomaly detection Learning algorithms Feature extraction Feature selection

Federated Learning and Optimization for Few-Shot Image Classification: 《Computers, Materials & Continua》2025年第3期4649-4667,共19页Yi Zuo Zhenping Chen Jing Feng Yunhao Fan; supported by Suzhou Science and Technology Plan(Basic Research)Project under Grant SJC2023002;Postgraduate Research&Practice Innovation Program of Jiangsu Province under Grant KYCX23_3322.; Image classification is crucial for various applications,including digital construction,smart manu-facturing,and medical imaging.Focusing on the inadequate model generalization and data privacy concerns in few-shot im...; 关键词：Federated learning contrastive learning few-shot differential privacy data augmentation

A Comprehensive Survey of Few-shot Information Networks: 《Machine Intelligence Research》2025年第1期60-78,共19页Xinxin Zheng Feihu Che Jianhua Tao; Information networks store rich information in the nodes and edges,which benefit many downstream tasks,such as recommender systems and knowledge graph completion.Information networks contain homogeneous information,he...; 关键词：Few-shot learning META-LEARNING homogeneous information networks heterogeneous information networks knowledge graphs

Machine learning strategies for small sample size in materials science: 《Science China Materials》2025年第2期387-405,共19页Qiuling Tao JinXin Yu Xiangyu Mu Xue Jia Rongpei Shi Zhifu Yao Cuiping Wang Haijun Zhang Xingjun Liu; supported by the National Natural Science Foundation of China (52371007 and 52301042);the National Key R&D Program of China (2020YFB0704503);the Guangdong Basic and Applied Basic Research Foundation (2021B1515120071);the Key-Area Research and Development Program of Guangdong Province (2023B0909050001)。; Machine learning (ML) has been widely used todesign and develop new materials owing to its low computational cost and powerful predictive capabilities. In recentyears, the shortcomings of ML in materials science have ...; 关键词：material design machine learning small sample size few-shot learning material domain knowledge

FEW