Reconstruction Guided Few-shot Network For Remote Sensing Image Classification

TL;DR

This paper introduces RGFS-Net, a novel few-shot remote sensing image classification method that uses a reconstruction task to improve generalization and class discrimination with limited labeled data.

Contribution

The paper presents a reconstruction-guided network that enhances few-shot learning in remote sensing by integrating a masked image reconstruction task for better feature learning.

Findings

Outperforms existing baselines on EuroSAT and PatternNet datasets.

Effective under 1-shot and 5-shot classification protocols.

Compatible with standard backbone architectures.

Abstract

Few-shot remote sensing image classification is challenging due to limited labeled samples and high variability in land-cover types. We propose a reconstruction-guided few-shot network (RGFS-Net) that enhances generalization to unseen classes while preserving consistency for seen categories. Our method incorporates a masked image reconstruction task, where parts of the input are occluded and reconstructed to encourage semantically rich feature learning. This auxiliary task strengthens spatial understanding and improves class discrimination under low-data settings. We evaluated the efficacy of EuroSAT and PatternNet datasets under 1-shot and 5-shot protocols, our approach consistently outperforms existing baselines. The proposed method is simple, effective, and compatible with standard backbones, offering a robust solution for few-shot remote sensing classification. Codes are available at https://github.com/stark0908/RGFS.