Dual-branch PolSAR Image Classification Based on GraphMAE and Local Feature Extraction

TL;DR

This paper introduces a dual-branch self-supervised learning model for PolSAR image classification, combining superpixel and pixel-level features with a graph masked autoencoder to improve accuracy with limited labels.

Contribution

It presents a novel dual-branch generative self-supervised framework that fuses superpixel and pixel features for improved PolSAR image classification.

Findings

Achieves promising results on the Flevoland dataset.

Outperforms existing methods in limited-label scenarios.

Demonstrates effectiveness of graph-based self-supervised learning.

Abstract

The annotation of polarimetric synthetic aperture radar (PolSAR) images is a labor-intensive and time-consuming process. Therefore, classifying PolSAR images with limited labels is a challenging task in remote sensing domain. In recent years, self-supervised learning approaches have proven effective in PolSAR image classification with sparse labels. However, we observe a lack of research on generative selfsupervised learning in the studied task. Motivated by this, we propose a dual-branch classification model based on generative self-supervised learning in this paper. The first branch is a superpixel-branch, which learns superpixel-level polarimetric representations using a generative self-supervised graph masked autoencoder. To acquire finer classification results, a convolutional neural networks-based pixel-branch is further incorporated to learn pixel-level features. Classification with fused dual-branch features is finally performed to obtain the predictions. Experimental results on the benchmark Flevoland dataset demonstrate that our approach yields promising classification results.