1.中国科学院新疆生态与地理研究所荒漠与绿洲生态国家重点实验室,新疆 乌鲁木齐,830011
2.中国科学院大学资源与环境学院,北京,100049
3.江苏师范大学地理测绘与城乡规划学院,江苏 徐州,221116
徐仁,硕士,主要研究方向为遥感图像分类和语义分割。xuren21@mails.ucas.ac.cn
阿里木·赛买提,博士,研究员。alim_smt@ms.xjb.ac.cn
收稿:2023-07-28,
纸质出版:2025-07-05
移动端阅览
徐仁,阿里木·赛买提,李二珠,等.面向任务对齐的遥感场景图像非监督域适应分类[J].武汉大学学报(信息科学版),2025,50(7):1359-1369.
XU Ren,SAMAT Alim,LI Erzhu,et al.Task-Oriented Alignment for Unsupervised Domain Adaptation of Remote Sensing Scene Image Classification[J].Geomatics and Information Science of Wuhan University,2025,50(7):1359-1369.
徐仁,阿里木·赛买提,李二珠,等.面向任务对齐的遥感场景图像非监督域适应分类[J].武汉大学学报(信息科学版),2025,50(7):1359-1369. DOI:10.13203/j.whugis20230084
XU Ren,SAMAT Alim,LI Erzhu,et al.Task-Oriented Alignment for Unsupervised Domain Adaptation of Remote Sensing Scene Image Classification[J].Geomatics and Information Science of Wuhan University,2025,50(7):1359-1369. DOI:10.13203/j.whugis20230084
近年来,深度学习在端到端处理、隐含特征表示等方面的特殊优势,已成为遥感图像分类、目标识别、变化监测等任务中的主流解决方案。遥感场景图像分类是遥感图像分类领域中的研究热点之一,常规深度学习方法的性能常因图像的场景结构、空间尺度与分辨率、数据源及模型假设等因素而受到一定限制,尤其是在异源场景数据间的特征迁移、模型复用任务中。针对此问题,将计算机视觉领域中面向任务对齐的非监督域适应方法(task-oriented alignment for unsupervised domain adaptation
ToAlign UDA)引入到跨域遥感场景图像分类任务中,在解释算法原理和优化机制的基础上通过对比实验评价了其分类性能。使用ToAlign UDA对源域数据集进行训练学习,对NWPU-RESISC45、AID、PatternNet 3个目标数据集进行测试,在源域和目标域的空间分布、光谱特征、尺度等相似度较高的情况下,3个目标数据集的总体分类精度分别达到了95.16%、96.17%、99.28%。三者的分类精度均高于大多数场景分类算法,表明ToAlign UDA在遥感场景图像分类领域具有良好的算法竞争力。
Objectives
2
We primarily aim at addressing the prevailing challenges in remote sensing scene image classification
specifically those associated with the utilization of heterogeneous data and the achievement of cross-domain classification. The conventional deep learning methods
while effective
often encounter limitations due to factors such as spatial scale and resolution
data sources
model assumptions
and the inherent diversity of scene data when dealing with tasks like feature transferring and model reuse.
Methods
2
In an attempt to overcome these obstacles
we introduce a novel approach called task-oriented alignment for unsupervised domain adaptation (ToAlign UDA). This algorithm
borrowed from the field of computer vision
is designed to enhance cross-domain remote sensing scene image classification. The principles and optimization mechanisms of the algorithm are explained
and its classification performance is evaluated through comparative experiments.
Results
2
ToAlign UDA is used in the experiment to train on the source domain dataset
while tests are conducted on three target datasets: NWPU-RESISC45
AID
and PatternNet. When the spatial distribution
spectral characteristics
scale
and other similarities between the source and target domains are high
ToAlign UDA achieves an overall classification accuracy of 95.16% on NWPU-RESISC45
96.17% on AID
and 99.28% on PatternNet.
Conclusions
2
The results clearly indicate that the ToAlign UDA approach outperforms most scene classification algorithms in terms of classification accuracy in remote sensing scene image analysis. Therefore
it holds significant potential in advancing the field of remote sensing image classification
particularly in the context of utilizing heterogeneous data and achieving cross-domain classification.
秦增忍 . 高分辨率影像在测绘生产中的应用及其发展潜力探讨 [J]. 科技创新导报 , 2015 , 12 ( 17 ): 75 - 76 .
QIN Zengren . Application of High-Resolution Image in Surveying and Mapping Production and Its Development Potential [J]. Science and Technology Innovation Herald , 2015 , 12 ( 17 ): 75 - 76 .
任武 , 葛咏 . 遥感影像亚像元制图方法研究进展综述 [J]. 遥感技术与应用 , 2011 , 26 ( 1 ): 33 - 44 .
REN Wu , GE Yong . Progress on Sub-Pixel Mapping Methods for Remotely Sensed Images [J]. Remote Sensing Technology and Application , 2011 , 26 ( 1 ): 33 - 44 .
朱述龙 . 基于混合像元的遥感图像分类技术 [J]. 测绘科学技术学报 , 1995 , 12 ( 4 ): 276 - 278 .
ZHU Shulong . Remote Sensing Image Classification Technology Based on Mixed Pixels [J]. Journal of Geomatics Science and Technology , 1995 , 12 ( 4 ): 276 - 278 .
张思宇 . 基于超像素的遥感图像分类技术研究 [D]. 哈尔滨 : 哈尔滨工程大学 , 2018 .
ZHANG Siyu . Research on Classification Technology of Remote Sensing Image Based on Superpixel [D]. Harbin : Harbin Engineering University , 2018 .
曹雪 , 柯长青 . 基于对象级的高分辨率遥感影像分类研究 [J]. 遥感信息 , 2006 , 21 ( 5 ): 27 - 30 .
CAO Xue , KE Changqing . Classification of High-Resolution Remote Sensing Images Using Object-Oriented Method [J]. Remote Sensing Information , 2006 , 21 ( 5 ): 27 - 30 .
张馨月 . 基于DCNN的高分辨率遥感图像场景分类 [D]. 长春 : 吉林大学 , 2019 .
ZHANG Xinyue . Scene Classification of High Resolution Remote Sensing Images Based on DCNN [D]. Changchun : Jilin University , 2019 .
李学龙 , 史建华 , 董永生 , 等 . 场景图像分类技术综述 [J]. 中国科学: 信息科学 , 2015 , 45 ( 7 ): 827 - 848 .
LI Xuelong , SHI Jianhua , DONG Yongsheng , et al . A Survey on Scene Image Classification [J]. Scientia Sinica (Informationis) , 2015 , 45 ( 7 ): 827 - 848 .
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 Bo'an , LI Guoqing , et al . A Review for Sample Datasets of Remote Sensing Imagery [J]. National Remote Sensing Bulletin , 2022 , 26 ( 4 ): 589 - 605 .
LECUN Y , BENGIO Y , HINTON G . Deep Learning [J]. Nature , 2015 , 521 ( 7553 ): 436 - 444 .
CHENG G , YANG C Y , YAO X W , et al . When Deep Learning Meets Metric Learning: Remote Sensing Image Scene Classification via Learning Discriminative CNNS [J]. IEEE Transactions on Geoscience and Remote Sensing , 2018 , 56 ( 5 ): 2811 - 2821 .
XU K J , HUANG H , DENG P F , et al . Two-Stream Feature Aggregation Deep Neural Network for Scene Classification of Remote Sensing Images [J]. Information Sciences , 2020 , 539 : 250 - 268 .
SHI C P , WANG T , WANG L G . Branch Feature Fusion Convolution Network for Remote Sensing Scene Classification [J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing , 2020 , 13 : 5194 - 5210 .
HE N J , FANG L Y , LI S T , et al . Skip-Connected Covariance Network for Remote Sensing Scene Classification [J]. IEEE Transactions on Neural Networks and Learning Systems , 2020 , 31 ( 5 ): 1461 - 1474 .
时永欣 , 周维勋 , 邵振峰 . 融合多尺度注意力的多视角遥感影像场景分类 [J]. 武汉大学学报(信息科学版) , 2024 , 49 ( 3 ): 366 - 375 .
SHI Yongxin , ZHOU Weixun , SHAO Zhenfeng . Multi-view remote Sensing Image Scene Classification by Fusing Multi-scale Attention [J]. Geomatics and Information Science of Wuhan University , 2024 , 49 ( 3 ): 366 - 375 .
虞欣 , 郑肇葆 , 孟令奎 , 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) , 2023 , DOI: 10.13203/j.whugis20220632 http://dx.doi.org/10.13203/j.whugis20220632 .
YU Xin , ZHENG Zhaobao , MENG Lingkui , et al . Scene Recognition of Remotely Sensed Images Based on Bayes Adjoint Batch Normalization [J]. Geomatics and Information Science of Wuhan University , 2023 , DOI: 10.13203/j.whugis20220632 http://dx.doi.org/10.13203/j.whugis20220632 .
毛丽君 , 李明诗 . GEE环境下联合Sentinel主被动遥感数据的国家公园土地覆盖分类 [J]. 武汉大学学报(信息科学版) , 2023 , 48 ( 5 ): 756 - 764 .
MAO Lijun , LI Mingshi . Integrating Sentinel Active and Passive Remote Sensing Data to Land Cover Classification in a National Park from GEE Platform [J]. Geomatics and Information Science of Wuhan University , 2023 , 48 ( 5 ): 756 - 764 .
卢晓燕 . 面向高分辨率遥感影像大范围道路提取的深度学习方法研究 [J]. 武汉大学学报(信息科学版) , 2023 , 48 ( 5 ): 821 .
LU Xiaoyan . Deep Learning Method for Large-Scale Road Extraction from High Resolution Remote Sensing Imagery [J]. Geomatics and Information Science of Wuhan University , 2023 , 48 ( 5 ): 821 .
张新长 , 黄健锋 , 宁婷 . 高分辨率遥感影像耕地提取研究进展与展望 [J]. 武汉大学学报(信息科学版) , 2023 , 48 ( 10 ): 1582 - 1590 .
ZHANG Xinchang , HUANG Jianfeng , NING Ting . Progress and Prospect of Cultivated Land Extraction from High Resolution Remote Sensing Images [J]. Geomatics and Information Science of Wuhan University , 2023 , 48 ( 10 ): 1582 - 1590 .
王严 , 刘万军 , 谭亚丽 , 等 . 卷积神经网络滑窗识别结合语义推理的城市功能区分类 [J]. 武汉大学学报(信息科学版) , 2023 , 48 ( 6 ): 950 - 959 .
WANG Yan , LIU Wanjun , TAN Yali , et al . Classification of Urban Functional Areas by Convolution Neural Network Recognition Combined with Sliding Window and Semantic Reasoning [J]. Geomatics and Information Science of Wuhan University , 2023 , 48 ( 6 ): 950 - 959 .
周亚男 , 何金珂 , 冯莉 , 等 . 深度时空卷积网络支持的地块尺度作物种植类型分类 [J]. 武汉大学学报(信息科学版) , 2023 , DOI: 10.13203/j.whugis20230136 http://dx.doi.org/10.13203/j.whugis20230136 .
ZHOU Ya'nan , HE Jinke , FENG Li , et al . Parcel-Scale Crop Type Classification Using Tile-Slice-Based Spatial-Temporal Convolutional Networks [J]. Geomatics and Information Science of Wuhan University , 2023 , DOI: 10.13203/j.whugis20230136 http://dx.doi.org/10.13203/j.whugis20230136 .
许慧琳 . 样本受限条件下的高光谱遥感影像分类方法研究 [J]. 武汉大学学报(信息科学版) , 2023 , 48 ( 5 ): 822 .
XU Huilin . Sample Constrained Conditions Methods for Hyperspectral Remote Sensing Image Classification [J]. Geomatics and Information Science of Wuhan University , 2023 , 48 ( 5 ): 822 .
WANG M , DENG W H . Deep Visual Domain Adaptation: A Survey [J]. Neurocomputing , 2018 , 312 : 135 - 153 .
FARAHANI A , VOGHOEI S , RASHEED K , et al . A Brief Review of Domain Adaptation [C]// The 16th International Conference on Data Science , Las Vegas, USA , 2021 .
范苍宁 , 刘鹏 , 肖婷 , 等 . 深度域适应综述: 一般情况与复杂情况 [J]. 自动化学报 , 2021 , 47 ( 3 ): 515 - 548 .
FAN Cangning , LIU Peng , XIAO Ting , et al . A Review of Deep Domain Adaptation: General Situation and Complex Situation [J]. Acta Automatica Sinica , 2021 , 47 ( 3 ): 515 - 548 .
PANAREDA B P , GALL J . Open Set Domain Adaptation [C]// IEEE International Conference on Computer Vision , Venice, Italy , 2017 .
WILSON G , COOK D J . A Survey of Unsupervised Deep Domain Adaptation [J]. ACM Transactions on Intelligent Systems and Technology , 2020 , 11 ( 5 ): 1 - 46 .
GANIN Y , LEMPITSKY V . Unsupervised Domain Adaptation by Backpropagation [C]// The 32nd International Conference on Machine Learning , Lille , 2015 .
许夙晖 , 慕晓冬 , 张雄美 , 等 . 结合对抗网络与辅助任务的遥感影像无监督域适应方法 [J]. 测绘学报 , 2017 , 46 ( 12 ): 1969 - 1977 .
XU Suhui , MU Xiaodong , ZHANG Xiongmei , et al . Unsupervised Remote Sensing Domain Adaptation Method with Adversarial Network and Auxiliary Task [J]. Acta Geodaetica et Cartographica Sinica , 2017 , 46 ( 12 ): 1969 - 1977 .
SUN B C , SAENKO K . Deep CORAL: Correlation Alignment for Deep Domain Adaptation [C]// ECCV 2016 Workshop , Amsterdam , 2016 .
WANG X S , LI Y R , CHENG Y H . Hyperspectral Image Classification Based on Unsupervised Heterogeneous Domain Adaptation CycleGan [J]. Chinese Journal of Electronics , 2020 , 29 ( 4 ): 608 - 614 .
周少康 . 基于无监督领域适应的高光谱图像分类 [D]. 徐州 : 中国矿业大学 , 2022 .
ZHOU Shaokang . Hyperspectral Image Classification Based on Unsupervised Domain Adaptation [D]. Xuzhou : China University of Mining and Technology , 2022 .
陈渠川 . 面向类别分布差异的无监督域适应学习研究 [D]. 南京 : 南京邮电大学 , 2022 .
CHEN Quchuan . Research on Unsupervised Domain Adaptive Learning for Category Distribution Differences [D]. Nanjing : Nanjing University of Posts and Telecommunications , 2022 .
BAKTASHMOTLAGH M , HARANDI M T , LOVELL B C , et al . Unsupervised Domain Adaptation by Domain Invariant Projection [C]// IEEE International Conference on Computer Vision , Sydney, Australia , 2013 .
WEI G , LAN C , ZENG W , et al . ToAlign: Task-Oriented Alignment for Unsupervised Domain Adaptation [J]. Advances in Neural Information Processing Systems , 2021 , 34 : 13834 - 13846 .
周彪 . 基于对抗学习的域适应方法研究 [D]. 合肥 : 安徽大学 , 2021 .
ZHOU Biao . Research on Domain Adaptation Method Based on Adversarial Learning [D]. Hefei : Anhui University , 2021
孙语泽 . 迁移图像语义分割研究 [D]. 南京 : 南京邮电大学 , 2020 .
SUN Yuze . Research on Semantic Segmentation of Migrated Images [D]. Nanjing : Nanjing University of Posts and Telecommunications , 2020 .
杨存建 , 周成虎 . 基于知识的遥感图像分类方法的探讨 [J]. 地理学与国土研究 , 2001 , 17 ( 1 ): 72 - 77 .
YANG Cunjian , ZHOU Chenghu . Investigation on Classification of Remote Sensing Image on Basis of Knowledge [J]. Geography and Territorial Research , 2001 , 17 ( 1 ): 72 - 77 .
SELVARAJU R R , COGSWELL M , DAS A , et al . Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization [C]// IEEE International Conference on Computer Vision , Venice, Italy , 2017 .
SIMONYAN K , VEDALDI A , ZISSERMAN A . Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps [C]// International Conference on Learning Representations , Banff, AB, Canada,2014 .
GANIN Y , USTINOVA E , AJAKAN H , et al . Domain-Adversarial Training of Neural Networks [J]. The Journal of Machine Learning Research , 2016 , 17 ( 1 ): 2096 - 2030 .
ZHAO Z C , LI J Q , LUO Z , et al . Remote Sensing Image Scene Classification Based on an Enhanced Attention Module [J]. IEEE Geoscience and Remote Sensing Letters , 2021 , 18 ( 11 ): 1926 - 1930 .
XIA G S , HU J , 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 .
WANG Q , LIU S T , CHANUSSOT J , et al . Scene Classification with Recurrent Attention of VHR Remote Sensing Images [J]. IEEE Transactions on Geoscience and Remote Sensing , 2019 , 57 ( 2 ): 1155 - 1167 .
ZHOU W X , NEWSAM S , LI C M , et al . PatternNet: A Benchmark Dataset for Performance Evaluation of Remote Sensing Image Retrieval [J]. ISPRS Journal of Photogrammetry and Remote Sensing , 2018 , 145 : 197 - 209 .
XU K , HUANG H , LI Y , et al . Multilayer Feature Fusion Network for Scene Classification in Remote Sensing [J]. IEEE Geoscience and Remote Sensing Letters , 2020 , 17 ( 11 ): 1894 - 1898 .
LIANG J , DENG Y , ZENG D . A Deep Neural Network Combined CNN and GCN for Remote Sensing Scene Classification [J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing , 2020 , 13 : 4325 - 4338 .
GAO Y , SHI J , LI J , et al . Remote Sensing Scene Classification Based on High-Order Graph Convolu-
0
浏览量
0
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621