Unsupervised PolSAR Image Factorization with Deep Convolutional Networks

Bi, Haixia; Xu, Feng; Wei, Zhiqiang; Han, Yibo; Cui, Yuanlong; Xue, Yong; Zhao, Xu

doi:10.1109/igarss.2019.8900489

Cited by 8 publications

(3 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In 2017, Liu et al [45] proposed a neighborhood-preserving network combined with superpixels for joint spatial constraints to implement unsupervised classification. In 2019, Bi et al [46] utilized PolSAR image factorization [47] to generate different scatterers and corresponding probability distribution maps, and used the entropy function between the distribution maps and classification results as the unsupervised loss for network training. In 2020, Huang [22] input the features of a single PolSAR image after Time-Frequency Analysis (TFA) into the DEC network to achieve classification based on different scattering mechanisms, but the classification performance still needs improvement.…”

Section: B Deep Learning-based Classification Methodsmentioning

confidence: 99%

A Deep Similarity Clustering Network With Compound Regularization for Unsupervised PolSAR Image Classification

Zuo,

Li,

Ren

et al. 2024

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Section: B Deep Learning-based Classification Methodsmentioning

confidence: 99%

A Deep Similarity Clustering Network With Compound Regularization for Unsupervised PolSAR Image Classification

Zuo,

Li,

Ren

et al. 2024

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

“…Parallelly, the PolSAR image classification domain grapples with the issue of label scarcity. With the progress of deep learning, many PolSAR image classification methods [24][25][26][27][28] have been proposed to alleviate this problem. Semisupervised learning [29][30][31] ambitiously seeks to optimize classifier generalization, leveraging both labeled and unlabeled data.…”

Section: Introductionmentioning

confidence: 99%

Self-Distillation-Based Polarimetric Image Classification with Noisy and Sparse Labels

Wang,

Bi,

et al. 2023

Remote Sensing

Self Cite

View full text Add to dashboard Cite

Polarimetric synthetic aperture radar (PolSAR) image classification, a field crucial in remote sensing, faces significant challenges due to the intricate expertise required for accurate annotation, leading to susceptibility to labeling inaccuracies. Compounding this challenge are the constraints posed by limited labeled samples and the perennial issue of class imbalance inherent in PolSAR image classification. Our research objectives are to address these challenges by developing a novel label correction mechanism, implementing self-distillation-based contrastive learning, and introducing a sample rebalancing loss function. To address the quandary of noisy labels, we proffer a novel label correction mechanism that capitalizes on inherent sample similarities to rectify erroneously labeled instances. In parallel, to mitigate the limitation of sparsely labeled data, this study delves into self-distillation-based contrastive learning, harnessing sample affinities for nuanced feature extraction. Moreover, we introduce a sample rebalancing loss function that adjusts class weights and augments data for small classes. Through extensive experiments on four benchmark PolSAR images, our approach demonstrates its effectiveness in addressing label inaccuracies, limited samples, and class imbalance. Through extensive experiments on four benchmark PolSAR images, our research substantiates the robustness of our proposed methodology, particularly in rectifying label discrepancies in contexts marked by sample paucity and imbalance. The empirical findings illuminate the superior efficacy of our approach, positioning it at the forefront of state-of-the-art PolSAR classification techniques.

show abstract

“…Deep learning provides a new way for unsupervised PolSAR image classification. Bi et al [39] proposed an unsupervised PolSAR image classification method that incorporated polarimetric image factorization and deep convolutional networks into a principled framework. At present, deep learning has great potential to further improve the performance of unsupervised PolSAR image classification.…”

Section: Introductionmentioning

confidence: 99%

Learning Rotation Domain Deep Mutual Information Using Convolutional LSTM for Unsupervised PolSAR Image Classification

Wang

Gui

et al. 2020

Remote Sensing

View full text Add to dashboard Cite

Deep learning can archive state-of-the-art performance in polarimetric synthetic aperture radar (PolSAR) image classification with plenty of labeled data. However, obtaining large number of accurately labeled samples of PolSAR data is very hard, which limits the practical use of deep learning. Therefore, unsupervised PolSAR image classification is worthy of further investigation that is based on deep learning. Inspired by the superior performance of deep mutual information in natural image feature learning and clustering, an end-to-end Convolutional Long Short Term Memory (ConvLSTM) network is used in order to learn the deep mutual information of polarimetric coherent matrices in the rotation domain with different polarimetric orientation angles (POAs) for unsupervised PolSAR image classification. First, for each pixel, paired “POA-spatio” samples are generated from the polarimetric coherent matrices with different POAs. Second, a special designed ConvLSTM network, along with deep mutual information losses, is used in order to learn the discriminative deep mutual information feature representation of the paired data. Finally, the classification results can be output directly from the trained network model. The proposed method is trained in an end-to-end manner and does not have cumbersome pipelines. Experiments on four real PolSAR datasets show that the performance of proposed method surpasses some state-of-the-art deep learning unsupervised classification methods.

show abstract

Unsupervised PolSAR Image Factorization with Deep Convolutional Networks

Cited by 8 publications

References 11 publications

A Deep Similarity Clustering Network With Compound Regularization for Unsupervised PolSAR Image Classification

A Deep Similarity Clustering Network With Compound Regularization for Unsupervised PolSAR Image Classification

Self-Distillation-Based Polarimetric Image Classification with Noisy and Sparse Labels

Learning Rotation Domain Deep Mutual Information Using Convolutional LSTM for Unsupervised PolSAR Image Classification

Contact Info

Product

Resources

About