{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T19:20:05Z","timestamp":1777576805438,"version":"3.51.4"},"reference-count":44,"publisher":"Emerald","issue":"1","license":[{"start":{"date-parts":[[2024,11,13]],"date-time":"2024-11-13T00:00:00Z","timestamp":1731456000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.emerald.com\/insight\/site-policies"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IJICC"],"published-print":{"date-parts":[[2025,3,7]]},"abstract":"<jats:sec><jats:title content-type=\"abstract-subheading\">Purpose<\/jats:title><jats:p>Vision transformers (ViT) detectors excel in processing natural images. However, when processing remote sensing images (RSIs), ViT methods generally exhibit inferior accuracy compared to approaches based on convolutional neural networks (CNNs). Recently, researchers have proposed various structural optimization strategies to enhance the performance of ViT detectors, but the progress has been insignificant. We contend that the frequent scarcity of RSI samples is the primary cause of this problem, and model modifications alone cannot solve it.<\/jats:p><\/jats:sec><jats:sec><jats:title content-type=\"abstract-subheading\">Design\/methodology\/approach<\/jats:title><jats:p>To address this, we introduce a faster RCNN-based approach, termed QAGA-Net, which significantly enhances the performance of ViT detectors in RSI recognition. Initially, we propose a novel quantitative augmentation learning (QAL) strategy to address the sparse data distribution in RSIs. This strategy is integrated as the QAL module, a plug-and-play component active exclusively during the model\u2019s training phase. Subsequently, we enhanced the feature pyramid network (FPN) by introducing two efficient modules: a global attention (GA) module to model long-range feature dependencies and enhance multi-scale information fusion, and an efficient pooling (EP) module to optimize the model\u2019s capability to understand both high and low frequency information. Importantly, QAGA-Net has a compact model size and achieves a balance between computational efficiency and accuracy.<\/jats:p><\/jats:sec><jats:sec><jats:title content-type=\"abstract-subheading\">Findings<\/jats:title><jats:p>We verified the performance of QAGA-Net by using two different efficient ViT models as the detector\u2019s backbone. Extensive experiments on the NWPU-10 and DIOR20 datasets demonstrate that QAGA-Net achieves superior accuracy compared to 23 other ViT or CNN methods in the literature. Specifically, QAGA-Net shows an increase in mAP by 2.1% or 2.6% on the challenging DIOR20 dataset when compared to the top-ranked CNN or ViT detectors, respectively.<\/jats:p><\/jats:sec><jats:sec><jats:title content-type=\"abstract-subheading\">Originality\/value<\/jats:title><jats:p>This paper highlights the impact of sparse data distribution on ViT detection performance. To address this, we introduce a fundamentally data-driven approach: the QAL module. Additionally, we introduced two efficient modules to enhance the performance of FPN. More importantly, our strategy has the potential to collaborate with other ViT detectors, as the proposed method does not require any structural modifications to the ViT backbone.<\/jats:p><\/jats:sec>","DOI":"10.1108\/ijicc-08-2024-0383","type":"journal-article","created":{"date-parts":[[2024,11,13]],"date-time":"2024-11-13T22:36:49Z","timestamp":1731537409000},"page":"133-152","source":"Crossref","is-referenced-by-count":32,"title":["QAGA-Net: enhanced vision transformer-based object detection for remote sensing images"],"prefix":"10.1108","volume":"18","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8235-0455","authenticated-orcid":false,"given":"Huaxiang","family":"Song","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hanjun","family":"Xia","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenhui","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wanbo","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qun","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinling","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"140","published-online":{"date-parts":[[2024,11,13]]},"reference":[{"issue":"21","key":"key2025030511413506000_ref001","doi-asserted-by":"publisher","first-page":"5460","DOI":"10.3390\/rs14215460","article-title":"MSSDet: multi-scale ship-detection framework in optical remote-sensing images and new benchmark","volume":"14","year":"2022","journal-title":"Remote Sensing"},{"key":"key2025030511413506000_ref002","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.120519","article-title":"Consistency- and dependence-guided knowledge distillation for object detection in remote sensing images","volume":"229","year":"2023","journal-title":"Expert Systems with Applications"},{"key":"key2025030511413506000_ref003","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2023.119797","article-title":"NT-DPTC: a non-negative temporal dimension preserved tensor completion model for missing traffic data imputation","volume":"653","year":"2024","journal-title":"Information Sciences"},{"key":"key2025030511413506000_ref004","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1016\/j.isprsjprs.2016.03.014","article-title":"A survey on object detection in optical remote sensing images","volume":"117","year":"2016","journal-title":"ISPRS Journal of Photogrammetry and Remote Sensing"},{"key":"key2025030511413506000_ref005","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/LGRS.2021.3104112","article-title":"Guiding clean features for object detection in remote sensing images","volume":"19","year":"2022","journal-title":"IEEE Geoscience and Remote Sensing Letters"},{"key":"key2025030511413506000_ref006","doi-asserted-by":"publisher","DOI":"10.1016\/j.rser.2024.114391","article-title":"A review of distributed solar forecasting with remote sensing and deep learning","volume":"198","year":"2024","journal-title":"Renewable and Sustainable Energy Reviews"},{"issue":"15","key":"key2025030511413506000_ref007","doi-asserted-by":"publisher","first-page":"3735","DOI":"10.3390\/rs14153735","article-title":"Attention-based multi-level feature fusion for object detection in remote sensing images","volume":"14","year":"2022","journal-title":"Remote Sensing"},{"key":"key2025030511413506000_ref008","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/LGRS.2022.3223069","article-title":"Remote sensing object detection based on gated context-aware module","volume":"19","year":"2022","journal-title":"IEEE Geoscience and Remote Sensing Letters"},{"issue":"3","key":"key2025030511413506000_ref009","doi-asserted-by":"publisher","first-page":"827","DOI":"10.3390\/rs15030827","article-title":"A review of data augmentation methods of remote sensing image target recognition","volume":"15","year":"2023","journal-title":"Remote Sensing"},{"issue":"8","key":"key2025030511413506000_ref010","doi-asserted-by":"publisher","first-page":"2929","DOI":"10.1007\/s11263-024-01988-x","article-title":"Training object detectors from scratch: an empirical study in the era of vision transformer","volume":"132","year":"2024","journal-title":"International Journal of Computer Vision"},{"issue":"1","key":"key2025030511413506000_ref011","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1108\/IJICC-03-2023-0053","article-title":"BFFNet: a bidirectional feature fusion network for semantic segmentation of remote sensing objects","volume":"17","year":"2024","journal-title":"International Journal of Intelligent\u00a0Computing and Cybernetics"},{"key":"key2025030511413506000_ref012","doi-asserted-by":"publisher","first-page":"38643","DOI":"10.1109\/ACCESS.2023.3267435","article-title":"Remote sensing object detection based on convolution and Swin transformer","volume":"11","year":"2023","journal-title":"IEEE Access"},{"issue":"6","key":"key2025030511413506000_ref013","doi-asserted-by":"publisher","first-page":"4251","DOI":"10.1007\/s00704-024-04914-w","article-title":"Advancements in drought using remote sensing: assessing progress, overcoming challenges, and exploring future opportunities","volume":"155","year":"2024","journal-title":"Theoretical and Applied Climatology"},{"issue":"4","key":"key2025030511413506000_ref014","doi-asserted-by":"publisher","first-page":"984","DOI":"10.3390\/rs14040984","article-title":"Transformer with transfer CNN for remote-sensing-image object detection","volume":"14","year":"2022","journal-title":"Remote Sensing"},{"key":"key2025030511413506000_ref015","doi-asserted-by":"publisher","first-page":"8300","DOI":"10.1109\/CAC59555.2023.10452032","article-title":"Multi-scale object detection of remote sensing images based on efficient feature extraction and transformer","year":"2023"},{"key":"key2025030511413506000_ref016","article-title":"Next-ViT: next generation vision transformer for efficient deployment in realistic industrial scenarios","year":"2022","journal-title":"arXiv"},{"key":"key2025030511413506000_ref017","doi-asserted-by":"publisher","first-page":"296","DOI":"10.1016\/j.isprsjprs.2019.11.023","article-title":"Object detection in optical remote sensing images: a survey and a new benchmark","volume":"159","year":"2020","journal-title":"ISPRS Journal of Photogrammetry and Remote Sensing"},{"key":"key2025030511413506000_ref018","doi-asserted-by":"publisher","first-page":"196","DOI":"10.1109\/ISoIRS59890.2023.00049","article-title":"SWIN-fovea: a remote sensing object detection model based on Swin transformer and FoveaBox","year":"2023"},{"key":"key2025030511413506000_ref019","doi-asserted-by":"publisher","first-page":"9992","DOI":"10.1109\/ICCV48922.2021.00986","article-title":"Swin transformer: hierarchical vision transformer using shifted windows","volume-title":"2021 IEEE\/CVF International Conference on Computer Vision (ICCV)","year":"2021"},{"issue":"7","key":"key2025030511413506000_ref020","doi-asserted-by":"publisher","first-page":"1743","DOI":"10.3390\/rs14071743","article-title":"Eagle-eye-inspired attention for object detection in remote sensing","volume":"14","year":"2022","journal-title":"Remote Sensing"},{"key":"key2025030511413506000_ref021","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/LGRS.2024.3378531","article-title":"QETR: a query-enhanced transformer for remote sensing image object detection","volume":"21","year":"2024","journal-title":"IEEE Geoscience and Remote Sensing Letters"},{"key":"key2025030511413506000_ref022","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TGRS.2024.3408895","article-title":"Complete and invariant instance classifier refinement for weakly supervised object detection in remote sensing images","volume":"62","year":"2024","journal-title":"IEEE Transactions on Geoscience and Remote Sensing"},{"issue":"4","key":"key2025030511413506000_ref023","doi-asserted-by":"publisher","first-page":"943","DOI":"10.1007\/s10530-023-03240-y","article-title":"Remote sensing enabled essential biodiversity variables for invasive alien species management: towards the development of spatial decision support system","volume":"26","year":"2024","journal-title":"Biological Invasions"},{"issue":"2","key":"key2025030511413506000_ref024","doi-asserted-by":"publisher","first-page":"336","DOI":"10.1007\/s11263-019-01228-7","article-title":"Grad-CAM:\u00a0visual explanations from deep Networks via gradient-based localization","volume":"128","year":"2020","journal-title":"International Journal\u00a0of Computer Vision"},{"issue":"3","key":"key2025030511413506000_ref025","doi-asserted-by":"publisher","first-page":"1261","DOI":"10.3390\/s23031261","article-title":"Multiple attention mechanism enhanced YOLOX for remote sensing object detection","volume":"23","year":"2023","journal-title":"Sensors"},{"issue":"3","key":"key2025030511413506000_ref026","doi-asserted-by":"publisher","first-page":"1","DOI":"10.33166\/AETiC.2023.03.001","article-title":"A leading but simple classification method for remote sensing images","volume":"7","year":"2023","journal-title":"Annals of Emerging Technologies in Computing"},{"issue":"1","key":"key2025030511413506000_ref027","doi-asserted-by":"publisher","first-page":"181","DOI":"10.1108\/IJICC-07-2023-0198","article-title":"MBC-Net: long-range enhanced feature fusion for classifying remote sensing images","volume":"17","year":"2023","journal-title":"International Journal of Intelligent Computing and Cybernetics"},{"issue":"3","key":"key2025030511413506000_ref028","doi-asserted-by":"publisher","DOI":"10.4108\/eetinis.v11i3.4748","article-title":"ERKT-Net: implementing efficient and robust knowledge distillation for remote sensing image classification","volume":"11","year":"2024","journal-title":"EAI Endorsed Transactions on Industrial Networks and Intelligent Systems"},{"issue":"2","key":"key2025030511413506000_ref029","doi-asserted-by":"publisher","first-page":"129","DOI":"10.1108\/IJWIS-10-2023-0192","article-title":"Efficient knowledge distillation for remote sensing image classification: a CNN-based approach","volume":"20","year":"2023","journal-title":"International Journal of Web Information Systems"},{"issue":"186","key":"key2025030511413506000_ref030","doi-asserted-by":"publisher","first-page":"340","DOI":"10.1111\/phor.12489","article-title":"Quantitative regularization in robust vision transformer for remote sensing image classification","volume":"39","year":"2024","journal-title":"Photogrammetric Record"},{"issue":"3","key":"key2025030511413506000_ref031","doi-asserted-by":"publisher","DOI":"10.1049\/csy2.12120","article-title":"Efficient knowledge distillation for hybrid models: a vision transformer\u2010convolutional neural network to convolutional neural network approach for classifying remote sensing images","volume":"6","year":"2024","journal-title":"IET Cyber-Systems and Robotics"},{"issue":"4","key":"key2025030511413506000_ref032","doi-asserted-by":"publisher","first-page":"56","DOI":"10.33166\/AETiC.2024.04.003","article-title":"Variance consistency learning: enhancing cross-modal knowledge distillation for remote sensing image classification","volume":"10","year":"2024","journal-title":"Annals of Emerging Technologies in Computing (AETiC)"},{"key":"key2025030511413506000_ref033","doi-asserted-by":"publisher","DOI":"10.1108\/IJICC-01-2024-0020","article-title":"MFLD: lightweight object detection with multi-receptive field and long-range dependency in remote sensing images","year":"2024","journal-title":"International Journal of Intelligent Computing and Cybernetics"},{"key":"key2025030511413506000_ref034","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TGRS.2024.3360447","article-title":"RingMo-lite: a remote sensing lightweight network with CNN-transformer hybrid framework","volume":"62","year":"2024","journal-title":"IEEE Transactions on Geoscience and Remote Sensing"},{"key":"key2025030511413506000_ref035","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TGRS.2021.3064599","article-title":"FSoD-Net:\u00a0full-scale object detection from optical remote sensing imagery","volume":"60","year":"2022","journal-title":"IEEE Transactions on Geoscience and Remote Sensing"},{"key":"key2025030511413506000_ref036","doi-asserted-by":"publisher","first-page":"6856","DOI":"10.1109\/JSTARS.2022.3198577","article-title":"Dual network structure with interweaved global-local feature hierarchy for transformer-based object detection in remote sensing image","volume":"15","year":"2022","journal-title":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing"},{"key":"key2025030511413506000_ref037","doi-asserted-by":"publisher","DOI":"10.1016\/j.scitotenv.2024.173273","article-title":"Advancements in remote sensing for active fire detection: a review of datasets and methods","volume":"943","year":"2024","journal-title":"Science of The Total Environment"},{"issue":"13","key":"key2025030511413506000_ref038","doi-asserted-by":"publisher","first-page":"38635","DOI":"10.1007\/s11042-023-16973-8","article-title":"Object detection in aerial remote sensing images using bidirectional enhancement FPN and attention module with data augmentation","volume":"83","year":"2024","journal-title":"Multimedia\u00a0Tools and Applications"},{"key":"key2025030511413506000_ref039","doi-asserted-by":"publisher","first-page":"1734","DOI":"10.1109\/JSTARS.2023.3339235","article-title":"Small object detection algorithm based on improved YOLOv8 for remote sensing","volume":"17","year":"2024","journal-title":"Ieee Journal of Selected Topics in Applied Earth Observations and Remote Sensing"},{"key":"key2025030511413506000_ref040","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/LGRS.2022.3223470","article-title":"Stepwise locating bidirectional Pyramid network for object detection in remote sensing imagery","volume":"20","year":"2023","journal-title":"IEEE Geoscience and Remote Sensing Letters"},{"issue":"3","key":"key2025030511413506000_ref041","doi-asserted-by":"publisher","first-page":"579","DOI":"10.3390\/rs14030579","article-title":"Multi-stage feature enhancement Pyramid network for detecting objects in optical remote sensing images","volume":"14","year":"2022","journal-title":"Remote Sensing"},{"issue":"4","key":"key2025030511413506000_ref042","doi-asserted-by":"publisher","first-page":"1134","DOI":"10.1080\/01431161.2024.2305632","article-title":"Optimizing distortion magnitude for data augmentation in few-shot remote sensing scene classification","volume":"45","year":"2024","journal-title":"International Journal of Remote Sensing"},{"key":"key2025030511413506000_ref043","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/LGRS.2023.3344937","article-title":"SCNet: a lightweight and efficient object detection network for remote sensing","volume":"21","year":"2024","journal-title":"IEEE Geoscience and Remote Sensing Letters"},{"issue":"3","key":"key2025030511413506000_ref044","doi-asserted-by":"publisher","first-page":"3193","DOI":"10.1007\/s10489-021-02335-0","article-title":"Spatial hierarchy perception\u00a0and hard samples metric learning for high-resolution remote sensing image object detection","volume":"52","year":"2022","journal-title":"Applied Intelligence"}],"container-title":["International Journal of Intelligent Computing and Cybernetics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.emerald.com\/insight\/content\/doi\/10.1108\/IJICC-08-2024-0383\/full\/xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.emerald.com\/insight\/content\/doi\/10.1108\/IJICC-08-2024-0383\/full\/html","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,24]],"date-time":"2025-07-24T22:54:49Z","timestamp":1753397689000},"score":1,"resource":{"primary":{"URL":"http:\/\/www.emerald.com\/ijicc\/article\/18\/1\/133-152\/1245329"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,13]]},"references-count":44,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2024,11,13]]},"published-print":{"date-parts":[[2025,3,7]]}},"alternative-id":["10.1108\/IJICC-08-2024-0383"],"URL":"https:\/\/doi.org\/10.1108\/ijicc-08-2024-0383","relation":{},"ISSN":["1756-378X","1756-3798"],"issn-type":[{"value":"1756-378X","type":"print"},{"value":"1756-3798","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,13]]}}}