Self-Paced Convolutional Neural Network for PolSAR Images Classification

Fully polarimetric synthetic aperture radar (PolSAR) can transmit and receive electromagnetic energy on four polarization channels (HH, HV, VH, VV). The data acquired from four channels have both similarities and complementarities. Utilizing the information between the four channels can considerably improve the performance of PolSAR image classification. Convolutional neural network can be used to extract the channel-spatial features of PolSAR images. Self-paced learning has been demonstrated to be instrumental in enhancing the learning robustness of convolutional neural network. In this paper, a novel classification method for PolSAR images using self-paced convolutional neural network (SPCNN) is proposed. In our method, each pixel is denoted by a 3-dimensional tensor block formed by its scattering intensity values on four channels, Pauli’s RGB values and its neighborhood information. Then, we train SPCNN to extract the channel-spatial features and obtain the classification results. Inspired by self-paced learning, SPCNN learns the easier samples first and gradually involves more difficult samples into the training process. This learning mechanism can make network converge to better values. The proposed method achieved state-of-the-art performances on four real PolSAR dataset.

• Publication year

  2019

• Venue

  Remote Sensing

• Publication date

  2019-02-19

• Fields of study

  Geology, Computer Science, Engineering, Environmental Science

• Identifiers
  DOI 10.3390/rs11040424
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Polarimetric Convolutional Network for PolSAR Image Classification

  2018cited by this paper
• A self-paced learning algorithm for change detection in synthetic aperture radar images

  2018cited by this paper
• PolSAR Image Classification Using Polarimetric-Feature-Driven Deep Convolutional Neural Network

  2018cited by this paper
• Multi-Pixel Simultaneous Classification of PolSAR Image Using Convolutional Neural Networks

  2018cited by this paper
• Self-paced Convolutional Neural Networks

  2017cited by this paper
• Nearest-Regularized Subspace Classification for PolSAR Imagery Using Polarimetric Feature Vector and Spatial Information

  2017cited by this paper
• POLSAR Image Classification via Wishart-AE Model or Wishart-CAE Model

  2017influential reference
• Classification of the Yellow River delta area using fully polarimetric SAR measurements

  2017cited by this paper
• PolSAR image classification based on Laplacian Eigenmaps and superpixels

  2017cited by this paper
• SAR Image segmentation based on convolutional-wavelet neural network and markov random field

  2017cited by this paper
• Complex-Valued Convolutional Neural Network and Its Application in Polarimetric SAR Image Classification

  2017influential reference
• Deep Learning Advances in Computer Vision with 3D Data

  2017cited by this paper
• Polarimetric SAR Image Classification Using Deep Convolutional Neural Networks

  2016influential reference
• Polarimetric SAR image classification based on selective ensemble learning of sparse representation

  2016cited by this paper
• DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs

  2016cited by this paper
• Superpixel-Based Classification Using K Distribution and Spatial Context for Polarimetric SAR Images

  2016cited by this paper
• Random Forest and Rotation Forest for fully polarized SAR image classification using polarimetric and spatial features

  2015cited by this paper
• What Objective Does Self-paced Learning Indeed Optimize?

  2015cited by this paper
• Multi-Scale Context Aggregation by Dilated Convolutions

  2015cited by this paper
• A novel polarimetric-texture-structure descriptor for high-resolution PolSAR image classification

  2015cited by this paper
• Easy Samples First: Self-paced Reranking for Zero-Example Multimedia Search

  2014cited by this paper
• Deep Learning for Natural Language Processing: Theory and Practice (Tutorial)

  2014cited by this paper
• Polarimetric Contextual Classification of PolSAR Images Using Sparse Representation and Superpixels

  2014cited by this paper
• Speech recognition with deep recurrent neural networks

  2013cited by this paper
• SUPERVISED CLASSIFICATION OF POLARIMETRIC SAR IMAGERY USING TEMPORAL AND CONTEXTUAL INFORMATION

  2013cited by this paper
• Self-Paced Learning for Long-Term Tracking

  2013cited by this paper
• Teaching Classification Boundaries to Humans

  2013cited by this paper
• Conversational Speech Transcription Using Context-Dependent Deep Neural Networks

  2012cited by this paper
• Self-paced dictionary learning for image classification

  2012cited by this paper
• Improving Wishart Classification of Polarimetric SAR Data Using the Hopfield Neural Network Optimization Approach

  2012cited by this paper
• ImageNet classification with deep convolutional neural networks

  2012cited by this paper
• Learning the easy things first: Self-paced visual category discovery

  2011cited by this paper
• LIBSVM: A library for support vector machines

  2011influential reference
• Deep Sparse Rectifier Neural Networks

  2011cited by this paper
• Understanding the difficulty of training deep feedforward neural networks

  2010cited by this paper
• Self-Paced Learning for Latent Variable Models

  2010cited by this paper
• Classification of Polarimetric SAR Image Based on Support Vector Machine Using Multiple-Component Scattering Model and Texture Features

  2010cited by this paper
• Support Vector Machine for Multifrequency SAR Polarimetric Data Classification

  2009cited by this paper
• A Neural Probabilistic Language Model

  2003cited by this paper
• Unsupervised classification of multifrequency and fully polarimetric SAR images based on the H/A/Alpha-Wishart classifier

  2001cited by this paper
• Unsupervised classification using polarimetric decomposition and the complex Wishart classifier

  1999influential reference
• Gradient-based learning applied to document recognition

  1998cited by this paper
• An entropy based classification scheme for land applications of polarimetric SAR

  1997cited by this paper
• This article has been accepted for inclusion in a future issue of this journal. Content is final as presented, with the exception of pagination. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 1 Integrating Color Features in Polarimetric SAR Image Clas

  year unknowninfluential reference

• SSTD-Net: a self-supervised learning-based three-branch network for runway area detection in PolSAR images

  2025cites this paper
• Edge-Preserving classification of polarimetric SAR images using Wishart distribution and conditional random field

  2022influential citation
• SAR4LCZ-Net: A Complex-valued Convolutional Neural Network for Local Climate Zones Classification Using Gaofen-3 Quad-pol SAR Data

  2021cites this paper
• Self-paced hybrid dilated convolutional neural networks

  2020cites this paper
• Multiscale CNN With Autoencoder Regularization Joint Contextual Attention Network for SAR Image Classification

  2020cites this paper
• SRUN: Spectral Regularized Unsupervised Networks for Hyperspectral Target Detection

  2020cites this paper
• PolSAR image classification via a novel semi-supervised recurrent complex-valued convolution neural network

  2020cites this paper
• Self-Paced AutoEncoder

  2018cites this paper