
浏览全部资源
扫码关注微信
1.北京石油化工学院人工智能研究院,北京,102617
2.武汉大学遥感信息工程学院,湖北 武汉,430079
Received:21 June 2024,
Published:05 September 2025
移动端阅览
虞欣,于家钰,郑肇葆,等.遥感影像场景识别的贝叶斯共轭批次归一化方法[J].武汉大学学报(信息科学版),2025,50(9):1838-1847.
YU Xin,YU Jiayu,ZHENG Zhaobao,et al.Scene Recognition of Remotely Sensed Images Based on Bayes Adjoint Batch Normalization[J].Geomatics and Information Science of Wuhan University,2025,50(9):1838-1847.
虞欣,于家钰,郑肇葆,等.遥感影像场景识别的贝叶斯共轭批次归一化方法[J].武汉大学学报(信息科学版),2025,50(9):1838-1847. DOI:10.13203/j.whugis20220632
YU Xin,YU Jiayu,ZHENG Zhaobao,et al.Scene Recognition of Remotely Sensed Images Based on Bayes Adjoint Batch Normalization[J].Geomatics and Information Science of Wuhan University,2025,50(9):1838-1847. DOI:10.13203/j.whugis20220632
归一化方法作为特征预处理的关键部分,在浅学习和深度学习中都是至关重要的。针对批次归一化方法中存在对批次样本容量依赖较大的问题,当前的优化思路主要是从样本信息的其他维度(如通道、层、时间等)来弥补批次样本容量较小的不足。从贝叶斯理论的角度出发,通过将总体信息、先验信息和样本信息以科学、合理的融合方式来弥补批次样本容量不足的缺陷,从而可以更加准确地估计样本均值和样本方差,使得归一化后的特征落入最佳的非饱和区域,以便更好地反映整个特征空间的原始表征,进而深度学习模型可以达到最佳的特征表达能力。实验与分析表明,所提的贝叶斯共轭批次归一化方法可行且有效,在NWPU-RESISC45数据集上,其分类精度比批次归一化方法高5.64%。得益于总体信息和先验信息,所提方法受样本容量的影响较小。
Objective
2
Normalization method plays an important role in feature preprocessing phase not only in conventional machine learning domain but also in contemporary deep learning domain. Batch normalization (BN) is very successful
but its performance very depends on the sample size. Therefore
many researchers try to improve it when the sample size is inadequate through adding the sample size merely in the sample information space.
Methods
2
This paper utilizes Bayes theory to integrate general information
prior information and sample information
and to offset the inadequate sample information. In this way
the mean value and the variance of sample can be estimated more precisely and more robust especially when the sample size is small
and the normalized feature will better fall into non-saturating region of activation function
which enables deep learning model to better describe original feature space.
Results
2
The Top-1 test classification accuracy in NWPU-RESISC45 dataset is improved by 5.64% than that of BN method. Moreover
with the help of general information and prior information
the Bayes adjoint batch normalization (BABN) method is not sensitive to the sample size.
Conclusions
2
The experiment results show that the proposed BABN method is feasible and effective
and performs better than BN method and other variants in the scene recognition of remote sensing image.
张永军 , 万一 , 史文中 , 等 . 多源卫星影像的摄影测量遥感智能处理技术框架与初步实践 [J]. 测绘学报 , 2021 , 50 ( 8 ): 1068 - 1083 .
ZHANG Yongjun , WAN Yi , SHI Wenzhong , et al . Technical Framework and Preliminary Practices of Photogrammetric Remote Sensing Intelligent Processing of Multi-source Satellite Images [J]. Acta Geodaetica et Cartographica Sinica , 2021 , 50 ( 8 ): 1068 - 1083 .
史文中 , 张敏 . 人工智能用于遥感目标可靠性识别: 总体框架设计、现状分析及展望 [J]. 测绘学报 , 2021 , 50 ( 8 ): 1049 - 1058 .
SHI Wenzhong , ZHANG Min . Artificial Intelligence for Reliable Object Recognition from Remotely Sensed Data: Overall Framework Design, Review and Prospect [J]. Acta Geodaetica et Cartographica Sinica , 2021 , 50 ( 8 ): 1049 - 1058 .
邵振峰 , 孙悦鸣 , 席江波 , 等 . 智能优化学习的高空间分辨率遥感影像语义分割 [J]. 武汉大学学报(信息科学版) , 2022 , 47 ( 2 ): 234 - 241 .
SHAO Zhenfeng , SUN Yueming , XI Jiangbo , et al . Intelligent Optimization Learning for Semantic Segmentation of High Spatial Resolution Remote Sensing Images [J]. Geomatics and Information Science of Wuhan University , 2022 , 47 ( 2 ): 234 - 241 .
龚健雅 , 张展 , 贾浩巍 , 等 . 面向多源数据地物提取的遥感知识感知与多尺度特征融合网络 [J]. 武汉大学学报(信息科学版) , 2022 , 47 ( 10 ): 1546 - 1554 .
GONG Jianya , ZHANG Zhan , JIA Haowei , et al . Multi-source Data Ground Object Extraction Based on Knowledge-Aware and Multi-scale Feature Fusion Network [J]. Geomatics and Information Science of Wuhan University , 2022 , 47 ( 10 ): 1546 - 1554 .
虞欣 , 郑肇葆 , 李林宜 . 适用于训练样本选择的斜交因子模型研究 [J]. 武汉大学学报(信息科学版) , 2022 , 47 ( 11 ): 1870 - 1877 .
YU Xin , ZHENG Zhaobao , LI Linyi . Oblique Factor Model for Selecting Training Samples [J]. Geomatics and Information Science of Wuhan University , 2022 , 47 ( 11 ): 1870 - 1877 .
李彦胜 , 张永军 . 耦合知识图谱和深度学习的新一代遥感影像解译范式 [J]. 武汉大学学报(信息科学版) , 2022 , 47 ( 8 ): 1176 - 1190 .
LI Yansheng , ZHANG Yongjun . A New Paradigm of Remote Sensing Image Interpretation by Coupling Knowledge Graph and Deep Learning [J]. Geomatics and Information Science of Wuhan University , 2022 , 47 ( 8 ): 1176 - 1190 .
周培诚 , 程塨 , 姚西文 , 等 . 高分辨率遥感影像解译中的机器学习范式 [J]. 遥感学报 , 2021 , 25 ( 1 ): 182 - 197 .
ZHOU Peicheng , CHENG Gong , YAO Xiwen , et al . Machine Learning Paradigms in High-Resolution Remote Sensing Image Interpretation [J]. National Remote Sensing Bulletin , 2021 , 25 ( 1 ): 182 - 197 .
刘建伟 , 赵会丹 , 罗雄麟 , 等 . 深度学习批归一化及其相关算法研究进展 [J]. 自动化学报 , 2020 , 46 ( 6 ): 1090 - 1120 .
LIU Jianwei , ZHAO Huidan , LUO Xionglin , et al . Research Progress on Batch Normalization of Deep Learning and Its Related Algorithms [J]. Acta Automatica Sinica , 2020 , 46 ( 6 ): 1090 - 1120 .
KRIZHEVSKY A , SUTSKEVER I , HINTON G E . ImageNet Classification with Deep Convolutional Neural Networks [J]. Communications of the ACM , 2017 , 60 ( 6 ): 84 - 90 .
CARANDINI M , HEEGER D J . Normalization as a Canonical Neural Computation [J]. Nature Reviews Neuroscience , 2012 , 13 : 51 - 62 .
HEEGER D J . Normalization of Cell Responses in Cat Striate Cortex [J]. Visual Neuroscience , 1992 , 9 ( 2 ): 181 - 197 .
IOFFE S , SZEGEDY C . Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift [J]. CoRR , 2015 ( 1 ): 448 – 456 .
PENG C , XIAO T T , LI Z M , et al . MegDet: A Large Mini-Batch Object Detector [C]// Computer Vision and Pattern Recognition , Salt Lake City, USA , 2018 .
WU Y X , HE K M . Group Normalization [C]// European Conference on Computer Vision (ECCV) , Munich, Germany , 2018 .
HE K M , ZHANG X Y , REN S Q , et al . Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification [C]// IEEE International Conference on Computer Vision (ICCV) , Santiago, Chile , 2015 .
CHENG G , HAN J W , LU X Q . Remote Sensing Image Scene Classification: Benchmark and State of the Art [J]. IEEE , 2017 , 105 ( 10 ): 1865 - 1883 .
SHARMA S , KULKARNI R , AJITHAPRASAD S , et al . Fringe Pattern Normalization Algorithm Using Kalman Filter [J]. Results in Optics , 2021 , 5 ( 1 ): 100152 .
ULYANOV D , VEDALDI A , LEMPITSKY V . Instance Normalization: The Missing Ingredient for Fast Stylization [EB/OL]. [ 2016-05-17 ] https://arxiv.org/abs/1607.08022v3 https://arxiv.org/abs/1607.08022v3 .
BA J , KIROS J , HINTON G E . Layer Normalization [EB/OL]. [ 2016-06-14 ] https://arxiv.org/abs/1607.06450 https://arxiv.org/abs/1607.06450 .
SHAO W Q , LI J Y , REN J M , et al . SSN: Learning Sparse Switchable Normalization via SparsestMax [J]. International Journal of Computer Vision , 2020 , 128 ( 8 ): 2107 - 2125 .
LI B , WU F , WEINBERGER K Q , et al . Positional Normalization [C]// Neural Information Processing Systems , Vancouver, Canada , 2019 .
YAO Z , CAO Y , ZHENG S , et al . Cross-Iteration Batch Normalization [C]// Computer Vision and Pattern Recognition (CVPR) , Beijing, China , 2021 .
SINGH S , KRISHNAN S . Filter Response Normalization Layer: Eliminating Batch Dependence in the Training of Deep Neural Networks [C]// Computer Vision and Pattern Recognition (CVPR) , Seattle, USA , 2020 .
IOFFE S . Batch Renormalization: Towards Reducing Minibatch Dependence in Batch-Normalized Models [EB/OL]. [ 2022-12-21 ] https://arxiv.org/abs/1702.03275v2 https://arxiv.org/abs/1702.03275v2 .
SONG Y B , XIANG J , JIANG J W , et al . A Cross-Domain Change Detection Network Based on Instance Normalization [J]. Remote Sensing , 2023 , 15 ( 24 ): 5785 .
QIAO S Y , WANG H Y , LIU C X , et al . Weight Standardization [EB/OL]. [ 2009-01-23 ] https:// arxiv.org/abs/1903.10520 https://arxiv.org/abs/1903.10520 .
CHEN Peng , WANG Benkang , GAO Sa , et al . Building Collapse Assessment with Residual Network [J]. Geomatics and Information Science of Wuhan University , 2020 , 45 ( 8 ): 1179 - 1184 .
SZEGEDY C , LIU W , JIA Y Q , et al . Going Deeper with Convolutions [C]// Computer Vision and Pattern Recognition (CVPR) , Long Beach, USA , 2019 .
KAZIMI B , SANDFELD S . Enhancing Semantic Segmentation in High-Resolution TEM Images: A Comparative Study of Batch Normalization and Instance Normalization [J]. Microscopy and Microanalysis , 2024 , 1 : 1527 - 1546 .
HUANGI L , HUANGI L , YANG D W , et al . Decorrelated Batch Normalization [C]// IEEE/CVF Conference on Computer Vision and Pattern Recognition , Salt Lake City, USA , 2018 .
VRIES H D , STRUB F , JÉRÉMIE M , et al . Modulating Early Visual Processing by Language [EB/OL].[ 2017-11-12 ] https://arxiv.org/abs/1707.00683 https://arxiv.org/abs/1707.00683 .
SINGH S , SHRIVASTAVA A . EvalNorm: Estimating Batch Normalization Statistics for Evaluation [C]// IEEE/CVF International Conference on Computer Vision (ICCV) , Seoul, Korea , 2019 .
JIA S H , CHEN D J , CHEN H T . Instance-Level Meta Normalization [C]// Computer Vision and Pattern Recognition (CVPR) , Long Beach, USA , 2019 .
GÜLÇEHRE Ç , BENGIO Y . Knowledge Matters: Importance of Prior Information for Optimization [J]. Journal of Machine Learning Research , 2016 , 17 ( 8 ): 1 - 8 .
ARPIT D , ZHOU Y B , KOTA B U , et al . Normalization Propagation: A Parametric Technique for Removing Internal Covariate Shift in Deep Networks [EB/OL]. [ 2016-10-25 ] https://arxiv.org/abs/1603.01431v6 https://arxiv.org/abs/1603.01431v6 .
REN M Y , LIAO R J , URTASUN R , et al . Normalizing the Normalizers: Comparing and Extending Network Normalization Schemes [EB/OL]. [ 2016-08-18 ] https://arxiv.org/abs/1611.04520v2 https://arxiv.org/abs/1611.04520v2 .
GONG X Y , CHEN W Y , CHEN T L , et al . Sandwich Batch Normalization: A Drop-in Replacement for Feature Distribution Heterogeneity [C]// Conference on Applications of Computer Vision (WACV) , Waikoloa, USA , 2022 .
MIYATO T , KATAOKA T , KOYAMA M , et al . Spectral Normalization for Generative Adversarial Networks [EB/OL]. [ 2018-12-09 ] https://arxiv.org/abs/1802.05957v1 https://arxiv.org/abs/1802.05957v1 .
LIAO Q L , KAWAGUCHI K , POGGIO T . Streaming Normalization: Towards Simpler and More Biologically-Plausible Normalizations for Online and Recurrent Learning [EB/OL]. [ 2016-19-15 ] https://arxiv.org/abs/1610.06160v1 https://arxiv.org/abs/1610.06160v1 .
LUO P , PENG Z L , REN J M , et al . Do Normalization Layers in a Deep ConvNet Really Need to Be Distinct [EB/OL]. [ 2018-07-23 ] https://arxiv.org/abs/1811.07727v1 https://arxiv.org/abs/1811.07727v1 .
SALIMANS T , KINGMA D P . Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networks [EB/OL]. [ 2016-05-19 ] https//arxiv.org/abs/1602.07868 https://arxiv.org/abs/1602.07868 .
茆诗松 , 汤银才 . 贝叶斯统计(第2版) [M]. 北京 : 中国统计出版社 , 2012 .
MAO Shisong , TANG Yincai . Bayesian Statistics [M]. 2nd ed . Beijing : China Statistics Press , 2012 .
冯权泷 , 陈泊安 , 李国庆 , 等 . 遥感影像样本数据集研究综述 [J]. 遥感学报 , 2022 , 26 ( 4 ): 589 - 605 .
FENG Quanlong , CHEN Boan , LI Guoqing , et al . A Review for Sample Datasets of Remote Sensing Imagery [J]. National Remote Sensing Bulletin , 2022 , 26 ( 4 ): 589 - 605 .
胡翔云 , 张觅 , 张祖勋 , 等 . 遥感影像智能解译系统EasyFeature的关键技术及应用 [J]. 武汉大学学报 ( 信息科学版) , 2025 , 50 ( 3 ): 554 - 561 .
HU Xiangyun , ZHANG Mi , ZHANG Zuxun , et al . Key Technologies and Applications of EasyFeature—An Intelligent Interpretation System for Remote Sensing Images [J]. Geomatics and Information Science of Wuhan University , 2025 , 50 ( 3 ): 554 - 561 .
钟守熠 , 肖青 , 闻建光 , 等 . 测绘地物波谱本底数据库 [J]. 遥感学报 , 2020 , 24 ( 6 ): 701 - 716 .
ZHONG Shouyi , XIAO Qing , WEN Jianguang , et al . Design and Realization of Ground Object Background Spectral Library for Surveying and Mapping [J]. Journal of Remote Sensing , 2020 , 24 ( 6 ): 701 - 716 .
XIA G S , HU J W , HU F , et al . AID: A Benchmark Data Set for Performance Evaluation of Aerial Scene Classification [J]. IEEE Transactions on Geoscience and Remote Sensing , 2017 , 55 ( 7 ): 3965 - 3981 .
HELBER P , BISCHKE B , DENGEL A , et al . EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classification [J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing , 2019 , 12 ( 7 ): 2217 - 2226 .
BASU S , GANGULY S , MUKHOPADHYAY S , et al . DeepSat: A Learning Framework for Satellite Imagery [C]// The 23rd SIGSPATIAL International Conference on Advances in Geographic Information Systems , Seattle, USA , 2015 .
DENG J , DONG W , SOCHER R , et al . Image-Net: A Large-Scale Hierarchical Image Database [C]// Computer Vision and Pattern Recognition , Miami, USA , 2009 .
陶超 , 阴紫薇 , 朱庆 , 等 . 遥感影像智能解译: 从监督学习到自监督学习 [J]. 测绘学报 , 2021 , 50 ( 8 ): 1122 - 1134 .
TAO Chao , YIN Ziwei , ZHU Qing , et al . Remote Sensing Image Intelligent Interpretation: From Supervised Learning to Self-Supervised Learning [J]. Acta Geodaetica et Cartographica Sinica , 2021 , 50 ( 8 ): 1122 - 1134 .
0
Views
0
下载量
0
CSCD
Publicity Resources
Related Articles
Related Author
Related Institution
京公网安备11010802024621