{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T20:37:10Z","timestamp":1781728630938,"version":"3.54.5"},"reference-count":41,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,10,8]],"date-time":"2025-10-08T00:00:00Z","timestamp":1759881600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Comput. Sci."],"abstract":"<jats:p>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 \u00d7 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.<\/jats:p>","DOI":"10.3389\/fcomp.2025.1613648","type":"journal-article","created":{"date-parts":[[2025,10,8]],"date-time":"2025-10-08T05:42:49Z","timestamp":1759902169000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Improving remote sensing scene classification with data augmentation techniques to mitigate class imbalance"],"prefix":"10.3389","volume":"7","author":[{"given":"Ping","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xin","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuanhui","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lili","family":"Zhan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,10,8]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"103735","DOI":"10.1016\/j.compbiomed.2020.103735","article-title":"Addressing class imbalance in deep learning for small lesion detection on medical images","volume":"120","author":"Bria","year":"2020","journal-title":"Comput. Biol. Med."},{"key":"B2","doi-asserted-by":"publisher","first-page":"249","DOI":"10.1016\/j.neunet.2018.07.011","article-title":"A systematic study of the class imbalance problem in convolutional neural networks","volume":"106","author":"Buda","year":"2018","journal-title":"Neural Netw."},{"key":"B3","doi-asserted-by":"publisher","first-page":"1865","DOI":"10.1109\/JPROC.2017.2675998","article-title":"Remote sensing image scene classification: benchmark and state of the art","volume":"105","author":"Cheng","year":"2017","journal-title":"Proc. IEEE"},{"key":"B4","doi-asserted-by":"publisher","first-page":"5605111","DOI":"10.1109\/TGRS.2021.3081421","article-title":"Perturbation-seeking generative adversarial networks: a defense framework for remote sensing image scene classification","volume":"60","author":"Cheng","year":"2022","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"B5","doi-asserted-by":"publisher","first-page":"3735","DOI":"10.1109\/JSTARS.2020.3005403","article-title":"Remote sensing image scene classification meets deep learning: challenges, methods, benchmarks, and opportunities","volume":"13","author":"Cheng","year":"2020","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"B6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/LGRS.2023.3344840","article-title":"Masked second-order pooling for few-shot remote-sensing scene classification","volume":"21","author":"Deng","year":"2024","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"B7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.ins.2018.06.056","article-title":"Improving imbalanced learning through a heuristic oversampling method based on k-means and SMOTE","volume":"465","author":"Douzas","year":"2018","journal-title":"Inf. Sci."},{"key":"B8","doi-asserted-by":"publisher","first-page":"1017","DOI":"10.1109\/TCYB.2016.2536638","article-title":"Stacked convolutional denoising auto-encoders for feature representation","volume":"47","author":"Du","year":"2017","journal-title":"IEEE Trans. Cybern."},{"key":"B9","first-page":"185","article-title":"\u201cOn the pairing of the softmax activation and cross-entropy penalty functions and the derivation of the softmax activation function,\u201d","volume-title":"Proceedings of the 8th Australasian Conference on Neural Networks, Vol. 181","author":"Dunne","year":"1997"},{"key":"B10","doi-asserted-by":"publisher","first-page":"1879","DOI":"10.1109\/LGRS.2019.2913387","article-title":"Imbalanced hyperspectral image classification with an adaptive ensemble method based on SMOTE and rotation forest with differentiated sampling rates","volume":"16","author":"Feng","year":"2019","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"B11","doi-asserted-by":"publisher","first-page":"863","DOI":"10.1613\/jair.1.11192","article-title":"SMOTE for learning from imbalanced data: progress and challenges, marking the 15-year anniversary","volume":"61","author":"Fern\u00e1ndez","year":"2018","journal-title":"J. Artif. Intell. Res."},{"key":"B12","doi-asserted-by":"publisher","first-page":"2110","DOI":"10.3390\/app9102110","article-title":"A survey on deep learning-driven remote sensing image scene understanding: scene classification, scene retrieval and scene-guided object detection","volume":"9","author":"Gu","year":"2019","journal-title":"Appl. Sci."},{"key":"B13","first-page":"4042","article-title":"\u201cMeta metric learning for highly imbalanced aerial scene classification,\u201d","volume-title":"ICASSP 2020 - 2020 IEEE Int. Conf. Acoust. Speech Signal Process","author":"Guan","year":"2020"},{"key":"B14","doi-asserted-by":"publisher","first-page":"2290","DOI":"10.18517\/ijaseit.10.6.10948","article-title":"MobileNets: efficient convolutional neural network for identification of protected birds","volume":"10","author":"Harjoseputro","year":"2020","journal-title":"Int. J. Adv. Sci. Eng. Inf. Technol."},{"key":"B15","first-page":"770","article-title":"\u201cDeep residual learning for image recognition kaiming,\u201d","volume-title":"Proceedings of the Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"He","year":"2016"},{"key":"B16","doi-asserted-by":"crossref","first-page":"1314","DOI":"10.1109\/ICCV.2019.00140","article-title":"\u201cSearching for MobileNetV3 accuracy vs MADDs vs model size,\u201d","volume-title":"2019 IEEE\/CVF International Conference on Computer Vision (ICCV)","author":"Howard","year":"2019"},{"key":"B17","first-page":"7132","article-title":"\u201cSqueeze-and-excitation networks,\u201d","author":"Hu","year":"2018","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"B18","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1186\/s40537-019-0192-5","article-title":"Survey on deep learning with class imbalance","volume":"6","author":"Johnson","year":"2019","journal-title":"J. Big Data"},{"key":"B19","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1016\/j.compag.2018.02.016","article-title":"Deep learning in agriculture: a survey","volume":"147","author":"Kamilaris","year":"2018","journal-title":"Comput. Electron. Agric."},{"key":"B20","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1023\/A:1021564703268","article-title":"A taxonomy of dirty data","volume":"7","author":"Kim","year":"2003","journal-title":"Data Min. Knowl. Discov."},{"key":"B21","doi-asserted-by":"publisher","first-page":"42","DOI":"10.1186\/s40537-018-0151-6","article-title":"A survey on addressing high-class imbalance in big data","volume":"5","author":"Leevy","year":"2018","journal-title":"J. Big Data"},{"key":"B22","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1080\/15326348908807096","article-title":"Gamma processes","volume":"5","author":"Lewis","year":"1989","journal-title":"Commun. Stat. Stoch. Model."},{"key":"B23","first-page":"413","article-title":"\u201cSoft-margin softmax for deep classification,\u201d","volume-title":"Lect. Notes Comput. Sci. (Including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics)","author":"Liang","year":"2017"},{"key":"B24","doi-asserted-by":"publisher","first-page":"105292","DOI":"10.1016\/j.knosys.2019.105292","article-title":"Dealing with class imbalance in classifier chains via random undersampling","volume":"192","author":"Liu","year":"2020","journal-title":"Knowl. -Based Syst."},{"key":"B25","doi-asserted-by":"publisher","first-page":"1200","DOI":"10.1109\/LGRS.2019.2894399","article-title":"Siamese convolutional neural networks for remote sensing scene classification","volume":"16","author":"Liu","year":"2019","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"B26","doi-asserted-by":"publisher","first-page":"216","DOI":"10.1016\/j.patcog.2019.02.023","article-title":"The impact of class imbalance in classification performance metrics based on the binary confusion matrix","volume":"91","author":"Luque","year":"2019","journal-title":"Pattern Recognit."},{"key":"B27","doi-asserted-by":"publisher","first-page":"1046","DOI":"10.1109\/LGRS.2018.2890413","article-title":"SiftingGAN: generating and sifting labeled samples to improve the remote sensing image scene classification baseline in vitro","volume":"16","author":"Ma","year":"2019","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"B28","article-title":"Impacts of dirty data: and experimental evaluation","author":"Qi","year":"2018","journal-title":"arXiv preprint"},{"key":"B29","doi-asserted-by":"publisher","first-page":"1","DOI":"10.3390\/rs12213547","article-title":"Full convolutional neural network based on multi-scale feature fusion for the class imbalance remote sensing image classification","volume":"12","author":"Ren","year":"2020","journal-title":"Remote Sens."},{"key":"B30","first-page":"4510","article-title":"\u201cMobileNetV2: inverted residuals and linear bottlenecks,\u201d","volume-title":"018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Sandler","year":"2018"},{"key":"B31","doi-asserted-by":"publisher","first-page":"747","DOI":"10.1049\/iet-ipr.2019.0992","article-title":"Normalised gamma transformation-based contrast-limited adaptive histogram equalisation with colour correction for sand-dust image enhancement","volume":"14","author":"Shi","year":"2020","journal-title":"IET Image Process."},{"key":"B32","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/CVPR.2015.7298594","author":"Szegedy","year":"2015"},{"key":"B33","doi-asserted-by":"publisher","first-page":"2030","DOI":"10.1109\/JSTARS.2021.3051569","article-title":"Attention consistent network for remote sensing scene classification","volume":"14","author":"Tang","year":"2021","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"B34","doi-asserted-by":"publisher","first-page":"429","DOI":"10.1016\/j.ins.2019.11.004","article-title":"Data imbalance in classification: experimental evaluation","volume":"513","author":"Thabtah","year":"2020","journal-title":"Inf. Sci."},{"key":"B35","doi-asserted-by":"crossref","first-page":"1492","DOI":"10.1109\/CVPR.2017.634","article-title":"\u201cAggregated residual transformations for deep,\u201d","volume-title":"2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Xie","year":"2017"},{"key":"B36","doi-asserted-by":"crossref","first-page":"1349","DOI":"10.1109\/IGARSS39084.2020.9323583","article-title":"\u201cA comparative study of deep learning loss functions for multi-label remote sensing image classification,\u201d","volume-title":"IGARSS 2020 - 2020 IEEE International Geoscience and Remote Sensing Symposium","author":"Yessou","year":"2020"},{"key":"B37","doi-asserted-by":"publisher","first-page":"3320","DOI":"10.48550\/arXiv.1411.1792","article-title":"How transferable are features in deep neural networks?","volume":"4","author":"Yosinski","year":"2014","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"B38","doi-asserted-by":"publisher","first-page":"519","DOI":"10.1109\/TGRS.2019.2937830","article-title":"Attention GANs: unsupervised deep feature learning for aerial scene classification","volume":"58","author":"Yu","year":"2020","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"B39","doi-asserted-by":"publisher","first-page":"145","DOI":"10.26599\/BDMA.2024.9020049","article-title":"An overview of deep neural networks for few-shot learning","volume":"8","author":"Zhao","year":"2025","journal-title":"Big Data Min. Anal."},{"key":"B40","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TGRS.2024.3367877","article-title":"Co-enhanced global-part integration for remote-sensing scene classification","volume":"62","author":"Zhao","year":"","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"B41","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TGRS.2024.3424489","article-title":"Gradient-guided multiscale focal attention network for remote sensing scene classification","volume":"62","author":"Zhao","year":"","journal-title":"IEEE Trans. Geosci. Remote Sens."}],"container-title":["Frontiers in Computer Science"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fcomp.2025.1613648\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,8]],"date-time":"2025-10-08T05:42:51Z","timestamp":1759902171000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fcomp.2025.1613648\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,8]]},"references-count":41,"alternative-id":["10.3389\/fcomp.2025.1613648"],"URL":"https:\/\/doi.org\/10.3389\/fcomp.2025.1613648","relation":{},"ISSN":["2624-9898"],"issn-type":[{"value":"2624-9898","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,8]]},"article-number":"1613648"}}