What, Where, and How to Transfer in SAR Target Recognition Based on Deep CNNs

Huang, Zhongling; Pan, Zongxu; Lei, Bin

doi:10.1109/tgrs.2019.2947634

Cited by 140 publications

(57 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The ImageNet pre-trained model is popular as a transferred source. However, the large difference lying between SAR land cover patches and natural object images may harm the transferability, making it necessary to find a bridge to narrow the gap [12]. Rather than using the ImageNet pre-trained model as most remote sensing applications do, we proposed a transitive transfer learning method with the help of the NWPU-RESISC45 dataset [10] to build a bridge linking the natural and SAR land cover images.…”

Section: A Transfer Learning With Deep Residual Networkmentioning

confidence: 99%

Classification of Large-Scale High-Resolution SAR Images with Deep Transfer Learning

Huang¹

2020

Preprint

Self Cite

View full text Add to dashboard Cite

The classification of large-scale high-resolution SAR land cover images acquired by satellites is a challenging task, facing several difficulties such as semantic annotation with expertise, changing data characteristics due to varying imaging parameters or regional target area differences, and complex scattering mechanisms being different from optical imaging. Given a large-scale SAR land cover dataset collected from TerraSAR-X images with a hierarchical three-level annotation of 150 categories and comprising more than 100,000 patches, three main challenges in automatically interpreting SAR images of highly imbalanced classes, geographic diversity, and label noise are addressed. In this letter, a deep transfer learning method is proposed based on a similarly annotated optical land cover dataset (NWPU-RESISC45). Besides, a top-2 smooth loss function with cost-sensitive parameters was introduced to tackle the label noise and imbalanced classes' problems. The proposed method shows high efficiency in transferring information from a similarly annotated remote sensing dataset, a robust performance on highly imbalanced classes, and is alleviating the over-fitting problem caused by label noise. What's more, the learned deep model has a good generalization for other SAR-specific tasks, such as MSTAR target recognition with a state-of-the-art classification accuracy of 99.46%.

show abstract

Section: A Transfer Learning With Deep Residual Networkmentioning

confidence: 99%

Classification of Large-Scale High-Resolution SAR Images with Deep Transfer Learning

Huang¹

2020

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…(3) 神经网络提取特征可分为一般性特征和特殊性特征, 一般性特征与任务的关联性小, 可直接用于其他任务, 特殊性特征具有较强的任务关联性, 仅适用于特定任务, 在网络中靠前层特征表现出更强的一般性而靠后层特征则具有更强的特殊性, 对于特定的源任务和目标任务, 需要对网络特征中的一般性和特殊性进行分析以确定哪些层可直接进行迁移, 哪些层需要进一步使用目标域数据进行参数调优; (4) 在迁移过程中加入域自适应学习可有效拉近源域和目标域数据的距离, 从而进一步提升迁移的性能. 结合上述结论, Huang 等 [65]…”

Section: 小样本条件下基于迁移学习的雷达图像目标识别方法unclassified

Progress of deep learning-based target recognition in radar images

Pan

Zhang

2019

Sci. Sin.-Inf.

Self Cite

View full text Add to dashboard Cite

Deep-learning-based extraction of the animal migration patterns from weather radar images SCIENCE CHINA Information Sciences 63, 140304 (2020); Deep learning approach for recognition and classification of yield affecting paddy crop stresses using field images Aritificial Intelligence in Agriculture 4, 12 (2020); Radar automatic target recognition based on feature extraction for complex HRRP Science in China Series F-Information Sciences 51, 1138 (2008); Deep reinforcement learning-based joint task offloading and bandwidth allocation for multiuser mobile edge computing 数字通信和网络 5, 10 (2019); Multitask deep learning-based multiuser hybrid beamforming for mm-wave orthogonal frequency division multiple access systems

show abstract

“…To this goal, these methods resort to simulators or generative models to produce new SAR target samples. As shown in Figure 1b, the second category of methods is transfer-learning [26][27][28][29][30][31][32]. It can transfer the pre-trained knowledge from source domain to SAR target images.…”

Section: Introductionmentioning

confidence: 99%

SAR Target Classification Based on Sample Spectral Regularization

et al. 2020

View full text Add to dashboard Cite

Synthetic Aperture Radar (SAR) target classification is an important branch of SAR image interpretation. The deep learning based SAR target classification algorithms have made remarkable achievements. But the acquisition and annotation of SAR target images are time-consuming and laborious, and it is difficult to obtain sufficient training data in many cases. The insufficient training data can make deep learning based models suffering from over-fitting, which will severely limit their wide application in SAR target classification. Motivated by the above problem, this paper employs transfer-learning to transfer the prior knowledge learned from a simulated SAR dataset to a real SAR dataset. To overcome the sample restriction problem caused by the poor feature discriminability for real SAR data. A simple and effective sample spectral regularization method is proposed, which can regularize the singular values of each SAR image feature to improve the feature discriminability. Based on the proposed regularization method, we design a transfer-learning pipeline to leverage the simulated SAR data as well as acquire better feature discriminability. The experimental results indicate that the proposed method is feasible for the sample restriction problem in SAR target classification. Furthermore, the proposed method can improve the classification accuracy when relatively sufficient training data is available, and it can be plugged into any convolutional neural network (CNN) based SAR classification models.

show abstract

What, Where, and How to Transfer in SAR Target Recognition Based on Deep CNNs

Cited by 140 publications

References 35 publications

Classification of Large-Scale High-Resolution SAR Images with Deep Transfer Learning

Classification of Large-Scale High-Resolution SAR Images with Deep Transfer Learning

Progress of deep learning-based target recognition in radar images

SAR Target Classification Based on Sample Spectral Regularization

Contact Info

Product

Resources

About