Feb 24, 2021 · To overcome this limitation and achieve robust PolSAR image classification, this article proposes the multiscale evolving weighted graph ...

In this paper, a semi-supervised classification method for polarimetric synthetic aperture radar (PolSAR) images through multi-scale weighted graph ...

Semi-Supervised Classification for PolSAR Data With Multi-Scale Evolving Weighted Graph Convolutional Network. Ren, Shijie; ;; Zhou, Feng. Abstract. Publication ...

This article derives a new architectural design named graph evolving module that combines pairwise latent feature similarity and kernel diffusion to refine ...

Feb 13, 2023 · Abstract. Recently, convolutional neural networks (CNNs) have shown significant advantages in the tasks of image classification; however, these ...

This method provides a new idea for PolSAR classification problem based on DL. Abstract. Deep neural networks have recently been extensively utilized for ...

[29] proposed a semi-supervised classification method for PolSAR data with multi-scale evolving weighted graph convolutional network. ... Feature fusion ...

Dec 27, 2022 · Three major factors strengthen the proposed method for PolSAR image analysis. Firstly, we propose a novel sample selection criterion to select ...

Sep 27, 2020 · SEMI-SUPERVISED CLASSIFICATION OF POLSAR DATA WITH MULTI-SCALE WEIGHTED GRAPH CONVOLUTIONAL NETWORK · Presentation · Discussion · Resources ...

Aug 8, 2024 · It consists of three components: a superpixel-branch based on graph masked autoencoder, a pixel-branch based on convolutional neural networks, ...