• Home
  • Search
  • Improving remote sensing scene classification with data augmentation techniques to mitigate class imbalance
  • Cite Icon3
  • https://doi.org/10.3389/fcomp.2025.1613648Copy DOI Icon

Improving remote sensing scene classification with data augmentation techniques to mitigate class imbalance

Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

High-resolution remote sensing imagery is a powerful tool that provides massive information about ground objects. However, conventional methods often fail to achieve satisfactory results for complex urban scene classification. This is attributed to the fact that conventional methods are unable to meet the requirements of high-accuracy remote sensing image scene classification (RSSC) and are hindered by challenges such as limited labeled samples and class imbalance, which may lead to classification bias in classifiers. On the contrary, deep learning-based RSSC represents an important approach for understanding semantic information. This paper explores the feasibility of mitigating classification bias by reducing the imbalance ratio (IR) of the dataset. First, a class-imbalanced dataset was constructed using very high-resolution (VHR) images, labeled into nine land use/land cover (LULC) categories. Second, comprehensive data augmentation techniques (mirroring, rotation, cropping, Hue, Saturation, Value (HSV) perturbation, and gamma transformation) were applied, successfully reducing the dataset's IR from 9.38 to 1.28. Subsequently, four architectures, MobileNet-v2, ResNet101, ResNeXt101_32 × 32d, and Transformer, were trained and evaluated on both class-balanced and class-imbalanced datasets. The results indicate that the classification bias caused by class imbalance was alleviated, significantly improving the classifier's performance. Specifically for the most severely underrepresented category (intersections), precision and recall improvements reached up to 128% and 102%, respectively, narrowing the gap with other categories and reducing classification bias. Furthermore, the average Kappa and overall accuracy (OA) increased by 11.84% and 12.97%, respectively, with reduced standard deviations in recall and precision, demonstrating enhanced model stability.

Similar Papers
  • Research Article
  • Citations970

Remote Sensing Image Scene Classification Meets Deep Learning: Challenges, Methods, Benchmarks, and Opportunities

  • Jan 01, 2020
  • IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
  • Gong Cheng +4
  • PDF
  • Research Article
  • Citations47

Prototype Calibration with Feature Generation for Few-Shot Remote Sensing Image Scene Classification

  • Jul 12, 2021
  • Remote Sensing
  • Qingjie Zeng +4
  • PDF
  • Research Article
  • Citations64

CLRS: Continual Learning Benchmark for Remote Sensing Image Scene Classification.

  • Feb 24, 2020
  • Sensors
  • Haifeng Li +6
  • Research Article
  • Citations46

A Supervised Progressive Growing Generative Adversarial Network for Remote Sensing Image Scene Classification

  • Jan 01, 2022
  • IEEE Transactions on Geoscience and Remote Sensing
  • Ailong Ma +4
  • Research Article
  • Citations1

WHEN DATA AUGMENTATION HURTS: A SYSTEMATIC EVALUATION OF SMOTE-BASED TECHNIQUES ON MEDICAL DATASETS

  • Aug 20, 2025
  • international journal of advanced research in computer science
  • May Stow
  • PDF
  • Research Article
  • Citations17

Multi-Scale Graph-Based Feature Fusion for Few-Shot Remote Sensing Image Scene Classification

  • Nov 03, 2022
  • Remote Sensing
  • Nan Jiang +2
  • PDF
  • Research Article
  • Citations7

Evaluation of Ten Deep-Learning-Based Out-of-Distribution Detection Methods for Remote Sensing Image Scene Classification

  • Apr 24, 2024
  • Remote Sensing
  • Sicong Li +4
  • PDF
  • Research Article
  • Citations11

Self-Attention Network With Joint Loss for Remote Sensing Image Scene Classification

  • Jan 01, 2020
  • IEEE Access
  • Honglin Wu +4
  • Research Article

Semi-Supervised EdgeKRAE: Lightweight Remote Sensing Scene Classification via Key Region Adaptive Enhancement

  • Jan 01, 2025
  • IEEE Geoscience and Remote Sensing Letters
  • Chengxiang Yu +2
  • Research Article
  • Citations2783

Remote Sensing Image Scene Classification: Benchmark and State of the Art

  • Oct 01, 2017
  • Proceedings of the IEEE
  • Gong Cheng +2
  • Conference Article
  • Citations2

Learning Region Response Ranking Features for Remote Sensing Image Scene Classification

  • Jul 01, 2019
  • Junyu Yang +4
  • Research Article
  • Citations181

Looking Closer at the Scene: Multiscale Representation Learning for Remote Sensing Image Scene Classification.

  • Apr 01, 2022
  • IEEE Transactions on Neural Networks and Learning Systems
  • Qi Wang +3
  • PDF
  • Research Article
  • Citations14

Remote Sensing Image Scene Classification with Self-Supervised Learning Based on Partially Unlabeled Datasets

  • Nov 18, 2022
  • Remote Sensing
  • Xiliang Chen +2
  • Conference Article
  • Citations15

Representation Learning of Remote Sensing Knowledge Graph for Zero-Shot Remote Sensing Image Scene Classification

  • Jul 11, 2021
  • Yansheng Li +4
  • PDF
  • Research Article
  • Citations35

AMN: Attention Metric Network for One-Shot Remote Sensing Image Scene Classification

  • Dec 10, 2020
  • Remote Sensing
  • Xirong Li +4
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.