CVLGAug 8, 2024

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

arXiv:2408.04294v16 citationsh-index: 15
Originality Incremental advance
AI Analysis

This addresses the labor-intensive annotation problem in remote sensing, but it is incremental as it builds on existing self-supervised methods.

The paper tackles PolSAR image classification with limited labels by proposing a dual-branch model using generative self-supervised learning, achieving promising results on the Flevoland dataset.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes