基于域自适应的多源SAR图像分类方法
收稿日期: 2025-10-31
修回日期: 2025-12-02
录用日期: 2026-01-28
网络出版日期: 2026-02-27
基金资助
国家重点研发计划(2023YFB3905504)
Multi-source SAR image classification method based on domain adaptation
Received date: 2025-10-31
Revised date: 2025-12-02
Accepted date: 2026-01-28
Online published: 2026-02-27
Supported by
National Key Research and Development Program of China(2023YFB3905504)
卷积神经网络（CNNs）是当前光学图像目标识别的主流算法。由于合成孔径雷达（SAR） 成像机制的复杂性，导致标注数据稀缺、标注成本高，难以满足CNNs对大规模高质量训练数据的需求。因此，利用仿真/光学图像训练模型，再通过无监督域自适应（UDA）技术弥合仿真/光学图像与真实SAR图像之间的域差异，成为一种可行的解决方案。然而，现有UDA方法通常假设源域的全部特征均可迁移，忽略了其中的领域特有特征可能引发负迁移问题；同时，伪标签噪声也会影响域对齐效果。针对上述问题，提出一种结合特征解耦与标签噪声抑制的域自适应框架，通过特征解耦模块，将样本表示分离为可迁移的域不变特征和域特有特征，并仅对域不变特征进行对齐，以降低负迁移的风险。此外，设计了加权广义交叉熵（WGCE）损失函数，来抑制伪标签迭代过程中产生的噪声干扰。跨域SAR目标识别任务的实验结果表明，所提方法有效提升了识别精度与域适应的鲁棒性。
王洪强 , 兰雨晴 , 岳富占 , 夏正欢 , 张涛 . 基于域自适应的多源SAR图像分类方法[J]. 航空学报, 2026 , 47(10) : 533015 -533015 . DOI: 10.7527/S1000-6893.2026.33015
Convolutional Neural Networks （CNNs） have emerged as the dominant algorithms for object recognition in optical images. However， due to the complex imaging mechanism of Synthetic Aperture Radar （SAR）， labeled data is scarce and annotation costs are high， making it difficult to meet the demand of CNNs for large-scale， high-quality training data. Therefore， leveraging simulated or optical images for model training， and employing Unsupervised Domain Adaptation （UDA） techniques to bridge the domain gap between simulated or optical images and real SAR images， has become a viable solution. Nevertheless， existing UDA methods typically assume that all features from the source domain are transferable， overlooking the fact that domain-specific features may induce negative transfer. Meanwhile， noise inherent in pseudo-labels can also degrade the efficacy of domain alignment. To address these challenges， this paper proposes a domain adaptation framework that integrates feature disentanglement with label noise suppression. The framework employs a feature disentanglement module to decompose sample representations into transferable domain-invariant features and domain-specific features. By aligning only the domain-invariant features， the risk of negative transfer is effectively mitigated. Furthermore， a Weighted Generalized Cross Entropy （WGCE） loss function is designed to suppress noise interference arising during the iterative pseudo-labeling process. Experimental results on cross-domain SAR target recognition tasks demonstrate that the proposed method significantly enhances both recognition accuracy and the robustness of domain adaptation.
| [1] | ZHANG J， LIU J， PAN B， et al. Domain adaptation based on correlation subspace dynamic distribution alignment for remote sensing image scene classification［J］. IEEE Transactions on Geoscience and Remote Sensing， 2020， 58（11）： 7920-7930. |
| [2] | 吕小玲， 仇晓兰， 俞文明， 等. 基于无监督域适应的仿真辅助SAR目标分类方法及模型可解释性分析［J］. 雷达学报， 2022， 11（1）： 168-182. |
| LYU X L， QIU X L， YU W M， et al. Simulation-assisted SAR target classification based on unsupervised domain adaptation and model interpretability analysis［J］. Journal of Radars， 2022， 11（1）： 168-182 （in Chinese）. | |
| [3] | TIRANDAZ Z， AKBARIZADEH G. A two-phase algorithm based on kurtosis curvelet energy and unsupervised spectral regression for segmentation of SAR images［J］. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing， 2016， 9（3）： 1244-1264. |
| [4] | LIN H P， SONG S L， YANG J. Ship classification based on MSHOG feature and task-driven dictionary learning with structured incoherent constraints in SAR images［J］. Remote Sensing， 2018， 10（2）： 190. |
| [5] | 胡思茹， 马福民， 秦天奇， 等. 基于多特征组合的红外舰船目标识别技术［J］. 舰船电子工程， 2022， 42（2）： 185-189. |
| HU S R， MA F M， QIN T Q， et al. Infrared ship target recognition technology based on multi feature combination［J］. Ship Electronic Engineering， 2022， 42（2）： 185-189 （in Chinese）. | |
| [6] | OUCHI K. Current status on vessel detection andclassification by synthetic aperture radar for maritimesecurity and safety［C］∥38th Symposium on Remote Sensingfor Environmental Sciences. 2016： 3-5. |
| [7] | ZHANG X， HUO C L， XU N， et al. Multitask learning for ship detection from synthetic aperture radar images［J］. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing， 2021， 14： 8048-8062. |
| [8] | 张翼鹏， 卢东东， 仇晓兰， 等. 基于散射点拓扑和双分支卷积神经网络的SAR图像小样本舰船分类［J］. 雷达学报， 2024， 13（2）： 411-427. |
| ZHANG Y P， LU D D， QIU X L， et al. Few-shot ship classification of SAR images via scattering point topology and dual-branch convolutional neural network［J］. Journal of Radars， 2024， 13（2）： 411-427 （in Chinese）. | |
| [9] | WANG H P， CHEN S Z， XU F， et al. Application of deep-learning algorithms to MSTAR data［C］∥2015 IEEE International Geoscience and Remote Sensing Symposium （IGARSS）. Piscataway： IEEE Press， 2015： 3743-3745. |
| [10] | HUANG Z L， DATCU M， PAN Z X， et al. Deep SAR-net： learning objects from signals［J］. ISPRS Journal of Photogrammetry and Remote Sensing， 2020， 161： 179-193. |
| [11] | CHEN J K， QIU X L， DING C B， et al. SAR image classification based on spiking neural network through spike-time dependent plasticity and gradient descent［J］. ISPRS Journal of Photogrammetry and Remote Sensing， 2022， 188： 109-124. |
| [12] | LI Y， DU L， WEI D. Multiscale CNN based on component analysis for SAR ATR［J］. IEEE Transactions on Geoscience and Remote Sensing， 2022， 60： 5211212. |
| [13] | SHI Y， DU L， LI C， et al. Unsupervised domain adaptation for SAR target classification based on domain-and class-level alignment： From simulated to real data［J］. ISPRS Journal of Photogrammetry and Remote Sensing， 2024， 207： 1-13. |
| [14] | LONG M S， ZHU H， WANG J M， et al. Deep transfer learning with joint adaptation networks［C］∥Proceedings of the 34th International Conference on Machine Learning. 2017： 2208-2217. |
| [15] | ZHU Y C， ZHUANG F Z， WANG J D， et al. Deep subdomain adaptation network for image classification［J］. IEEE Transactions on Neural Networks and Learning Systems， 2021， 32（4）： 1713-1722. |
| [16] | LONG M S， CAO Z J， WANG J M， et al. Conditional adversarial domain adaptation［C］∥Proceedings of the 32nd International Conference on Neural Information Processing Systems. 2018. |
| [17] | DU Z K， LI J J， SU H Z， et al. Cross-domain gradient discrepancy minimization for unsupervised domain adaptation［C］∥2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR）. Piscataway： IEEE Press， 2021： 3936-3945. |
| [18] | GHIFARY M， KLEIJN W B， ZHANG M J， et al. Deep reconstruction-classification networks for unsupervised domain adaptation［C］∥Computer Vision-ECCV 2016. Cham： Springer， 2016： 597-613. |
| [19] | BOUSMALIS K， TRIGEORGIS G， SILBERMAN N， et al. Domain separation networks［C］∥30th Conference on Neural Information Processing Systems （NIPS 2016）. 2016. |
| [20] | SANKARANARAYANAN S， BALAJI Y， CASTILLO C D， et al. Generate to adapt： aligning domains using generative adversarial networks［C］∥2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE Press， 2018： 8503-8512. |
| [21] | WANG S S， XIAO Q， WANG K Y， et al. Mutual-weighted feature disentanglement for unsupervised domain adaptation［J］. Multimedia Systems， 2024， 30（6）： 308. |
| [22] | ZHOU L H， YE M， LI X P， et al. Disentanglement then reconstruction： Unsupervised domain adaptation by twice distribution alignments［J］. Expert Systems with Applications， 2024， 237： 121498. |
| [23] | CAI R Y， JIN M， WEN Q S， et al. From entanglement to alignment： representation space decomposition for unsupervised time series domain adaptation［EB/OL］. （2025-08-06）［2025-10-01］： . |
| [24] | YU X， TSENG H H， YOO S， et al. INSURE： An information theory inspired disentanglement and purification model for domain generalization［J］. IEEE Transactions on Image Processing， 2024， 33： 3508-3519. |
| [25] | GAO F， PI D C， CHEN J F. Balanced and robust unsupervised open set domain adaptation via joint adversarial alignment and unknown class isolation［J］. Expert Systems with Applications， 2024， 238： 122127. |
| [26] | LI Y， ZHANG S S， LIU Y N， et al. Loose to compact feature alignment for domain adaptive object detection［J］. Pattern Recognition Letters， 2024， 181： 92-98. |
| [27] | LEWIS B， SCARNATI T， SUDKAMP E， et al. A SAR dataset for ATR development： The synthetic and measured paired labeled experiment （SAMPLE）［C］∥Algorithms for Synthetic Aperture Radar Imagery XXVI. 2019. |
| [28] | SHI Y， DU L， GUO Y C， et al. Unsupervised domain adaptation for ship classification via progressive feature alignment： from optical to SAR images［J］. IEEE Transactions on Geoscience and Remote Sensing， 2024， 62： 5222517. |
| [29] | HOU X Y， AO W， SONG Q， et al. FUSAR-Ship： building a high-resolution SAR-AIS matchup dataset of Gaofen-3 for ship detection and recognition［J］. Science China Information Sciences， 2020， 63： 140303. |
| [30] | GANIN Y， LEMPITSKY V. Unsupervised domain adaptation by backpropagation［C］∥Proceedings of the 32nd International Conference on Machine Learning. 2015： 1180-1189. |
| [31] | SHARMA A， KALLURI T， CHANDRAKER M. Instance level affinity-based transfer for unsupervised domain adaptation［C］∥2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR）. Piscataway： IEEE Press， 2021： 5357-5367. |
| [32] | SUN B C， SAENKO K. Deep CORAL： Correlation alignment for deep domain adaptation［M］. Cham： Springer， 2016： 443-450. |
| [33] | ZHU Y C， ZHUANG F Z， WANG J D， et al. Multi-representation adaptation network for cross-domain image classification［J］. Neural Networks， 2019， 119： 214-221. |
| [34] | DAI S Y， CHENG Y， ZHANG Y Z， et al. Contrastively smoothed class alignment for unsupervised domain adaptation［C］∥Computer Vision-ACCV 2020. Cham： Springer， 2021： 268-283. |
| [35] | ZHANG Z L， SABUNCU M R. Generalized cross entropy loss for training deep neural networks with noisy labels［C］∥Proceedings of the 32nd International Conference on Neural Information Processing Systems. 2018. |
| [36] | SELVARAJU R R， COGSWELL M， DAS A， et al. Grad-CAM： Visual explanations from deep networks via gradient-based localization［J］. International Journal of Computer Vision， 2020， 128（2）： 336-359. |
/
| 〈 |
|
〉 |
CJA