DiffPR-Net: Few-Shot Remote Sensing Scene Classification Based on Generative Diffusion and Prototype Rectified Model

doi:10.1109/TGRS.2025.3528071

DiffPR-Net: Few-Shot Remote Sensing Scene Classification Based on Generative Diffusion and Prototype Rectified Model

2025-01-01

1

PRE

AI

DOI：10.1109/TGRS.2025.3528071

Original

Original request for help

Save

Abstract

En 中文

Few-shot remote sensing scene classification (FSRSSC) aims to identify unseen scene classes from limited labeled samples, facing the challenge of accurately modeling data distribution and preserving image details in complex backgrounds with high intraclass variance and interclass similarity. To address this challenge, we propose a novel diffusion prototype rectified network (DiffPR-Net), which is comprised of three core modules: diffusion augmentation (DA), dual attention fusion module (DAFM), and prototype rectified module (PRM). The DA is constructed to generate high-quality remote sensing images with the objective of augmenting the training dataset. Besides, the DAFM facilitates the model to focus discriminative regions by transmitting highly fused image detail features from higher to lower layers. What is more, the PRM addresses prototype deviation by adaptively assigning temporary labels to unlabeled data based on prediction confidence, thereby correcting the initial prototypes. Experiments indicate that our proposed method is highly promising, achieving competitive or state-of-the-art (SOTA) classification performance while addressing the scarcity of remotely sensed data and enhancing focus on discriminative regions.

Keywords:

Remote sensing

Prototypes

Scene classification

Diffusion models

Feature extraction

Training

Data models

Data augmentation

Sensors

Semantics

diffusion model

few-shot remote sensing scene classification (FSRSSC)

prototype network

DiffPR-Net: Few-Shot Remote Sensing Scene Classification Based on Generative Diffusion and Prototype Rectified Model

Abstract

Journal

Organization