Skip to main navigation Skip to search Skip to main content

基于类关系挖掘的遥感图像广义小样本分割方法

Translated title of the contribution: Generalized few-shot segmentation for remote sensing image based on class relation mining
  • 丛润民
  • , 孙豪言
  • , 罗宇轩*
  • , 方豪
  • *Corresponding author for this work

Research output: Journal Publications and Reviews › RGC 21 - Publication in refereed journal › peer-review

Abstract

With the rapid development of remote sensing satellites and unmanned aerial vehicle technologies, the acquisition of remote sensing images has become more convenient, making precise interpretation of image content a research hotspot. However, existing remote sensing image semantic segmentation methods struggle to handle new object categories that emerge due to scene changes when only a small number of samples are available, thereby affecting the overall performance of the model. To address the potential issues of new classes and new scenes in remote sensing scenarios, this paper introduces the generalized few-shot segmentation technique, aiming to rapidly adapt to new classes using a few samples and efficiently complete the semantic segmentation task for remote sensing images. Firstly, to tackle the challenge of distinguishing objects of different categories and different sizes in remote sensing images, a multi-scale feature fusion decoder is introduced to enhance the model’s segmentation ability for targets of different scales. Then, to address the background semantic shift problem in the generalized few-shot segmentation task, a background consistency modeling training strategy is designed to ensure the accurate expression of background features by the model. Furthermore, this paper proposes an inter-class relationship mining technique, which utilizes prototypes generated from a large amount of base class data to enhance the prototypes generated from a small amount of new class data, enabling them to acquire beneficial information from the base classes and achieve more precise segmentation. Finally, comparative experiments with mainstream methods are conducted on public datasets, and the mIoU segmentation metric is improved by up to 11. 48%, demonstrating the effectiveness of the proposed algorithm.
Translated title of the contributionGeneralized few-shot segmentation for remote sensing image based on class relation mining
Original languageChinese (Simplified)
Article number631694
Number of pages14
Journal航空学报
Volume46
Issue number23
Online published13 May 2025
DOIs
Publication statusPublished - 15 Dec 2025

Funding

Received\uFF1A2024-12-19\uFF1BRevised\uFF1A2025-03-04\uFF1BAccepted\uFF1A2025-04-23\uFF1BPublished online\uFF1A2025-05-13 16\uFF1A 21 URL\uFF1Ahttps\uFF1A // hkxb. buaa. edu. cn/CN/Y2025/V46/I23/631694 Foundation items\uFF1ATaishan Scholar Project of Shandong Province\uFF08 ts qn202306079\uFF09 \uFF1BNational Natural Science Foundation of China \uFF08 62471278\uFF09

Research Keywords

  • 遥感图像
  • 语义分割
  • 广义小样本
  • 知识蒸馏
  • 关系挖掘
  • remote sensing
  • semantic segmentation
  • generalized few-shot
  • knowledge distillation
  • relationship mining

Fingerprint

Dive into the research topics of 'Generalized few-shot segmentation for remote sensing image based on class relation mining'. Together they form a unique fingerprint.

Cite this