Stacked Sparse Autoencoder in PolSAR Data Classification Using Local Spatial Information

Zhang, Lu; Ma, Wenping; Zhang, Dan

doi:10.1109/lgrs.2016.2586109

Cited by 122 publications

(72 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With the classification of seven types of land cover in level-1, we mainly focused on the top-2 predictionsȳ ∈ R 2 . We define the label space Y = {1, 2, ..., n} and the ground truth label y ∈ Y, the top-2 predictionsȳ ∈ Y (2) . The subset of Y (2) where the ground truth y is included, is written as Y (2) y .…”

Section: Top-2 Smooth Loss Functionmentioning

confidence: 99%

“…We define the label space Y = {1, 2, ..., n} and the ground truth label y ∈ Y, the top-2 predictionsȳ ∈ Y (2) . The subset of Y (2) where the ground truth y is included, is written as Y (2) y . The top-2 smooth loss function with temperature can be defined as:…”

Section: Top-2 Smooth Loss Functionmentioning

confidence: 99%

“…With the development of deep learning algorithms, hierarchical features can be extracted automatically. Unsupervised learning approaches, such as deep belief networks (DBNs) [1], and auto-encoders (AEs) [2], [3], are widely applied to SAR images for classification. With more detailed texture information, high-resolution (HR) PolSAR images are used to learn spatial and polarimetric features jointly via deep convolutional neural networks (DCNNs) for supervised classification which achieves state-of-the-art performance [4].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

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

Huang¹

2020

Preprint

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: Top-2 Smooth Loss Functionmentioning

confidence: 99%

Section: Top-2 Smooth Loss Functionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

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

Huang¹

2020

Preprint

View full text Add to dashboard Cite

show abstract

“…Deep features and shallow features were combined, and a fully convolutional classifier was proposed in Yan et al (2018) for better performance. As another form of deep learning, autoencoders have also been used for PolSAR image classification (Hou et al, 2017;Zhang et al, 2016;De et al, 2018b). Some scholars sought higher accuracy by developing more powerful network architectures or better combination of hyperparameters (Wang et al, 2018a;Zhou et al, 2017;De et al, 2018a).…”

Section: Introductionmentioning

confidence: 99%

Efficiently utilizing complex-valued PolSAR image data via a multi-task deep learning framework

Zhang

Dong

Zou

2019

ISPRS Journal of Photogrammetry and Remote Sensing

View full text Add to dashboard Cite

Convolutional neural networks (CNNs) have been widely used to improve the accuracy of polarimetric synthetic aperture radar (PolSAR) image classification. However, in most studies, the difference between PolSAR images and optical images is rarely considered. Most of the existing CNNs are not tailored for the task of PolSAR image classification, in which complex-valued PolSAR data have been simply equated to real-valued data to fit the optical image processing architectures and avoid complex-valued operations. This is one of the reasons CNNs unable to perform their full capabilities in PolSAR classification. To solve the above problem, the objective of this paper is to develop a tailored CNN framework for PolSAR image classification, which can be implemented from two aspects: Seeking a better form of PolSAR data as the input of CNNs and building matched CNN architectures based on the proposed input form. In this paper, considering the properties of complexvalued numbers, amplitude and phase of complex-valued PolSAR data are extracted as the input for the first time to maintain the integrity of original information while avoiding immature complex-valued operations. Then, a multi-task CNN (MCNN) architecture is proposed to match the improved input form and achieve better classification results. Furthermore, depthwise separable convolution is introduced to the proposed architecture in order to better extract information from the phase information. Experiments on three PolSAR benchmark datasets not only prove that using amplitude and phase as the input do contribute to the improvement of PolSAR classifica-

show abstract

“…The deep learning can be realized by deep neural networks that has multiple hidden layers and nonlinear active function. This technique has been successfully used in the field of image classification (Krizhevsky, Sutskever, & Hinton, 2012), object recognition (He, Lau, Liu, Huang, & Yang, 2015;Simonyan & Zisserman, 2015), and remote sensing (Chen, Jiang, Li, Jia, & Ghamisi, 2016;Chen, Zhao, & Jia, 2015;Hou, Kou et al, 2016;Liu, Jiao, Hou, & Yang, 2016;Liu et al, 2017;Zhang, Ma, & Zhang, 2016. There are mainly three kinds of models developed for deep learning, the stacked autoencoder (SAE) (Vincent, Larochelle, Bengio, & Manzagol, 2008), the deep belief network (DBN) (Hinton & Salakhutdinov, 2006) and the convolutional neural networks (CNNs) (Lécun, Bottou, Bengio, & Haffner, 1998).…”

Section: Introductionmentioning

confidence: 99%

SAR image classification using adaptive neighborhood-based convolutional neural network

Zhang

Yang

Jia

et al. 2019

European Journal of Remote Sensing

View full text Add to dashboard Cite

The convolutional neural network (CNN)-based pixel-wise synthetic aperture radar (SAR) data classification does not take fully use the spatial neighborhood information due to the fact that the impact of neighborhood pixels is not taken into consideration. The flaw of CNN-based classification method may lead to misclassification under some conditions. In this paper, we propose a novel adaptive neighborhood-based convolutional neural network (AN-CNN) for the single polarimetric synthetic aperture radar data classification. In the convolution layer, the neighborhood pixels are adaptively weighted based on their bilateral distance (spatial and feature distance) to the central pixel. In this way, different pixels have different impact on the classification result of the central pixel. The spatial distance-based weighting can reduce the misclassifications in the homogenous regions which are caused by speckle noise and the feature distance-based weighting is beneficial for the classification in the boundary regions. As a result, the misclassification is obviously reduced by the proposed AN-CNN which has a new cost function. Experimental results on simulated and real SAR data show that our proposed AN-CNN can notably improve the classification accuracy in both boundary regions and homogeneous regions compared with conventional CNN in different scenes especially when limited training samples are explored. ARTICLE HISTORY

show abstract

Stacked Sparse Autoencoder in PolSAR Data Classification Using Local Spatial Information

Cited by 122 publications

References 10 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

Efficiently utilizing complex-valued PolSAR image data via a multi-task deep learning framework

SAR image classification using adaptive neighborhood-based convolutional neural network

Contact Info

Product

Resources

About