A Deep Similarity Clustering Network With Compound Regularization for Unsupervised PolSAR Image Classification
Authors:
Open Access
- 15 May 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 17 (19391404) , 11451-11466
Abstract
Polarimetric SAR (PolSAR) image classification is a critical application of remote sensing image interpretation. Most of the early algorithms that use hand-crafted features to divide the image into various scattering categories have a general classification performance. The Convolutional Neural Networks (CNNs) show superior performance in image processing with powerful nonlinear representation capabilities. However, they also require a large amount of labeled training data, which limits the practical use of CNNs in PolSAR image classification scene where labeled data are rare and expensive. To address the previous issue, this paper proposes a deep similarity clustering model with compound regularization for unsupervised PolSAR image classification. The proposed model combines an unsupervised feature extraction pipeline with Wishart distance metric and a deep clustering pipeline with feature similarity metric. The regularization combines two ingredients to preserve both the sharpness of edges and the semantic continuity of the image contents. The first is the differential constraint based on pixel-level features, and the second is the graph partition constraint based on superpixel-level features. Experiments prove the effectiveness of the proposed method on both spaceborne (RadarSat2) and airborne (E-SAR/UAVSAR) PolSAR images. The visual results and quantitative scores show that our method outperforms the traditional unsupervised methods and deep learning-based unsupervised methods with a large margin.Keywords
Funding Information
- Outstanding Member of Youth Innovation Promotion Association
- Chinese Academy of Sciences (Y2022052)
- Key Projects of National Natural Science Foundation of China (62131019)
This publication has 50 references indexed in Scilit:
- Unsupervised Few-Shot Image Classification by Learning Features into Clustering Space2022
- Inductive Unsupervised Domain Adaptation for Few-Shot Classification via Clustering2021
- Deep Superpixel Cut for Unsupervised Image Segmentation2021
- Unsupervised PolSAR Image Factorization with Deep Convolutional Networks2019
- Semi-Supervised Complex-Valued GAN for Polarimetric SAR Image Classification2019
- A contextual-based segmentation of compact PolSAR images using Markov Random Field (MRF) modelInternational Journal of Remote Sensing, 2018
- POLSAR Image Classification via Wishart-AE Model or Wishart-CAE ModelIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2017
- SAR Image segmentation based on convolutional-wavelet neural network and markov random fieldPattern Recognition, 2017
- Polarimetric SAR Feature Extraction With Neighborhood Preservation-Based Deep LearningIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2016
- Use of the SVM Classification with Polarimetric SAR Data for Land Use Cartography2006