Class Imbalance in the Automatic Interpretation of Remote Sensing Images: A Review

Class imbalance is a very challenging problem in data science, affecting the development of several application fields. This problem also plagues the automatic interpretation of remote sensing images. Especially in tasks such as classification mapping, object detection, change detection, and scene c...

Full description

Saved in:
Bibliographic Details
Main Authors: Pengdi Chen, Yuanrui Ren, Baoan Zhang, Yuan Zhao
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10945429/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850149899143741440
author Pengdi Chen
Yuanrui Ren
Baoan Zhang
Yuan Zhao
author_facet Pengdi Chen
Yuanrui Ren
Baoan Zhang
Yuan Zhao
author_sort Pengdi Chen
collection DOAJ
description Class imbalance is a very challenging problem in data science, affecting the development of several application fields. This problem also plagues the automatic interpretation of remote sensing images. Especially in tasks such as classification mapping, object detection, change detection, and scene classification, the classes of training samples required by machine learning exhibit uneven distribution, which seriously affects the accuracy of model training. Our meta-analysis is based on 171 journal papers retrieved and screened from the Web of Science database, covering publication years, highly productive countries, highly cited authors, remote sensing data types, data augmentation methods, and the distribution of the main application fields. The solution to the proposed problem involves three aspects: model innovation and optimization, loss function improvement, and data augmentation. Experiments on benchmark datasets have demonstrated the effectiveness of these methods. In terms of remote sensing task applications, we provide a comprehensive review and analysis of recent research cases on deep learning aimed at addressing the class imbalance problem. Finally, we discuss the synergistic relationship between models, loss functions, and data augmentation, summarize the current challenges in this field, as well as propose several ideas for addressing the class imbalance problem.
format Article
id doaj-art-fccc2da4976b4fc2b993a3bb37447730
institution OA Journals
issn 1939-1404
2151-1535
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
spelling doaj-art-fccc2da4976b4fc2b993a3bb374477302025-08-20T02:26:45ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing1939-14042151-15352025-01-01189483950810.1109/JSTARS.2025.355556710945429Class Imbalance in the Automatic Interpretation of Remote Sensing Images: A ReviewPengdi Chen0https://orcid.org/0009-0008-4777-7120Yuanrui Ren1Baoan Zhang2Yuan Zhao3Lanzhou University, Lanzhou, ChinaLanzhou University, Lanzhou, ChinaMapping Institution of Gansu Province, Lanzhou, ChinaMapping Institution of Gansu Province, Lanzhou, ChinaClass imbalance is a very challenging problem in data science, affecting the development of several application fields. This problem also plagues the automatic interpretation of remote sensing images. Especially in tasks such as classification mapping, object detection, change detection, and scene classification, the classes of training samples required by machine learning exhibit uneven distribution, which seriously affects the accuracy of model training. Our meta-analysis is based on 171 journal papers retrieved and screened from the Web of Science database, covering publication years, highly productive countries, highly cited authors, remote sensing data types, data augmentation methods, and the distribution of the main application fields. The solution to the proposed problem involves three aspects: model innovation and optimization, loss function improvement, and data augmentation. Experiments on benchmark datasets have demonstrated the effectiveness of these methods. In terms of remote sensing task applications, we provide a comprehensive review and analysis of recent research cases on deep learning aimed at addressing the class imbalance problem. Finally, we discuss the synergistic relationship between models, loss functions, and data augmentation, summarize the current challenges in this field, as well as propose several ideas for addressing the class imbalance problem.https://ieeexplore.ieee.org/document/10945429/Automatic interpretationclass imbalancedeep learningmeta-analysisremote sensing images
spellingShingle Pengdi Chen
Yuanrui Ren
Baoan Zhang
Yuan Zhao
Class Imbalance in the Automatic Interpretation of Remote Sensing Images: A Review
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Automatic interpretation
class imbalance
deep learning
meta-analysis
remote sensing images
title Class Imbalance in the Automatic Interpretation of Remote Sensing Images: A Review
title_full Class Imbalance in the Automatic Interpretation of Remote Sensing Images: A Review
title_fullStr Class Imbalance in the Automatic Interpretation of Remote Sensing Images: A Review
title_full_unstemmed Class Imbalance in the Automatic Interpretation of Remote Sensing Images: A Review
title_short Class Imbalance in the Automatic Interpretation of Remote Sensing Images: A Review
title_sort class imbalance in the automatic interpretation of remote sensing images a review
topic Automatic interpretation
class imbalance
deep learning
meta-analysis
remote sensing images
url https://ieeexplore.ieee.org/document/10945429/
work_keys_str_mv AT pengdichen classimbalanceintheautomaticinterpretationofremotesensingimagesareview
AT yuanruiren classimbalanceintheautomaticinterpretationofremotesensingimagesareview
AT baoanzhang classimbalanceintheautomaticinterpretationofremotesensingimagesareview
AT yuanzhao classimbalanceintheautomaticinterpretationofremotesensingimagesareview