Page 119 - 《武汉大学学报(信息科学版)》2025年第9期
P. 119

第 50 卷第 9 期            虞   欣等:遥感影像场景识别的贝叶斯共轭批次归一化方法                                  1847


                    puter Vision (ICCV), Seoul, Korea, 2019.         A  Review  for  Sample  Datasets  of  Remote  Sensing
               [33]  JIA S H, CHEN D J, CHEN H T.  Instance-Level    Imagery[J].   National  Remote  Sensing  Bulletin,
                    Meta Normalization[C]//Computer Vision and Pat⁃  2022, 26(4): 589-605.
                    tern  Recognition (CVPR),  Long  Beach,  USA,   [44]  胡翔云, 张觅, 张祖勋, 等 .  遥感影像智能解译系
                    2019.                                           统 EasyFeature 的关键技术及应用[J].  武汉大学学
               [34]  GÜLÇEHRE  Ç,  BENGIO  Y.   Knowledge  Mat⁃     报 ( 信息科学版), 2025, 50(3): 554-561.
                    ters:  Importance  of  Prior  Information  for  Optimiza⁃  HU Xiangyun, ZHANG Mi, ZHANG Zuxun, et al.
                    tion[J].   Journal  of  Machine  Learning  Research,   Key Technologies and Applications of EasyFeature—
                    2016, 17(8): 1-8.                               An  Intelligent  Interpretation  System  for  Remote
               [35]  ARPIT  D,  ZHOU  Y  B,  KOTA  B  U,  et  al.   Nor⁃  Sensing  Images[J].   Geomatics  and  Information
                    malization Propagation: A Parametric Technique for   Science  of  Wuhan  University,  2025,  50(3):  554-
                    Removing Internal Covariate Shift in Deep Networks  561.
                    [EB/OL].  [2016-10-25]  https://arxiv. org/abs/  [45]  钟守熠, 肖青, 闻建光, 等 .  测绘地物波谱本底数
                    1603. 01431v6.                                   据库[J].  遥感学报, 2020, 24(6): 701-716.
               [36]  REN M Y, LIAO R J, URTASUN R, et al.  Nor⁃      ZHONG Shouyi, XIAO Qing, WEN Jianguang, et
                    malizing the Normalizers: Comparing and Extending   al.   Design  and  Realization  of  Ground  Object  Back⁃
                    Network Normalization Schemes[EB/OL].  [2016-    ground  Spectral  Library  for  Surveying  and  Mapping
                    08-18] https://arxiv. org/abs/1611. 04520v2.    [J].   Journal  of  Remote  Sensing,  2020,  24(6):
               [37]  GONG  X  Y,  CHEN  W  Y,  CHEN  T  L,  et  al.    701-716.
                    Sandwich Batch Normalization: A Drop-in Replace⁃  [46]  XIA G S, HU J W, HU F, et al.  AID: A Bench⁃
                    ment  for  Feature  Distribution  Heterogeneity[C]//  mark Data Set for Performance Evaluation of Aerial
                    Conference  on  Applications  of  Computer  Vision   Scene Classification[J].  IEEE Transactions on Geo⁃
                    (WACV), Waikoloa, USA, 2022.                     science  and  Remote  Sensing,  2017,  55(7):  3965-
               [38]  MIYATO  T,  KATAOKA  T,  KOYAMA  M,  et         3981.
                    al.  Spectral Normalization for Generative Adversari⁃  [47]  HELBER  P,  BISCHKE  B,  DENGEL  A,  et  al.
                    al  Networks[EB/OL].  [2018-12-09]  https://arx⁃  EuroSAT:  A  Novel  Dataset  and  Deep  Learning
                    iv. org/abs/1802. 05957v1.                       Benchmark for Land Use and Land Cover Classifica⁃
               [39]  LIAO  Q  L,  KAWAGUCHI  K,  POGGIO  T.          tion[J].   IEEE  Journal  of  Selected  Topics  in  Ap⁃
                    Streaming  Normalization:  Towards  Simpler  and   plied  Earth  Observations  and  Remote  Sensing,
                    More  Biologically-Plausible  Normalizations  for  On⁃  2019, 12(7): 2217-2226.
                    line  and  Recurrent  Learning[EB/OL].  [2016-19-  [48]  BASU  S,  GANGULY  S,  MUKHOPADHYAY
                    15] https://arxiv. org/abs/1610. 06160v1.        S, et al.  DeepSat: A Learning Framework for Satel⁃
               [40]  LUO  P ,  PENG  Z  L ,  REN  J  M ,  et  al.   Do  Nor⁃  lite Imagery[C]//The 23rd SIGSPATIAL Interna⁃
                    malization Layers in a Deep ConvNet Really Need to   tional  Conference  on  Advances  in  Geographic  Infor⁃
                    Be  Distinct [EB/OL].  [2018-07-23]  https://arx⁃  mation Systems, Seattle, USA, 2015.
                    iv. org/abs/1811. 07727v1.                  [49]  DENG  J,  DONG  W,  SOCHER  R,  et  al.   Image-
               [41]  SALIMANS T, KINGMA D P.  Weight Normaliza⁃      Net:  A  Large-Scale  Hierarchical  Image  Database
                    tion:  A  Simple  Reparameterization  to  Accelerate   [C]//Computer  Vision  and  Pattern  Recognition,
                    Training  of  Deep  Neural  Networks [EB/OL].    Miami, USA, 2009.
                    [2016-05-19] https//arxiv. org/abs/1602. 07868.  [50]  陶超, 阴紫薇, 朱庆, 等 .  遥感影像智能解译: 从监
               [42]  茆 诗 松 , 汤 银 才 .  贝 叶 斯 统 计(第 2 版) [M].  北       督学习到自监督学习[J].  测绘学报, 2021, 50(8):
                    京: 中国统计出版社, 2012.                                1122-1134.
                    MAO  Shisong,  TANG  Yincai.   Bayesian  Statistics    TAO Chao, YIN Ziwei, ZHU Qing, et al.  Remote
                    [M]. 2nd ed.  Beijing: China Statistics Press, 2012.  Sensing  Image  Intelligent  Interpretation:  From  Su⁃
               [43]  冯权泷, 陈泊安, 李国庆, 等 .  遥感影像样本数据集                   pervised  Learning  to  Self-Supervised  Learning[J].
                    研究综述[J].  遥感学报, 2022, 26(4): 589-605.            Acta Geodaetica et Cartographica Sinica, 2021, 50
                    FENG Quanlong, CHEN Boan, LI Guoqing, et al.    (8): 1122-1134.
   114   115   116   117   118   119   120   121   122   123   124