{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,19]],"date-time":"2026-07-19T09:47:18Z","timestamp":1784454438053,"version":"3.55.0"},"reference-count":30,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T00:00:00Z","timestamp":1770768000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T00:00:00Z","timestamp":1770768000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100009367","name":"Mansoura University","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100009367","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Aerial image classification is considered an open challenge due to its properties and the presence of various complex images. Given the complexity and variation in aerial images, this paper proposes two hybrid models for classification. The first hybrid model combines features extracted from ResNet-50 and the Vision Transformer (ViT), followed by the application of multi-head attention (MHA) to detect the most informative features. The second hybrid model also extracts features from ResNet-50 and ViT, then applies cross-attention. Both hybrid models are assessed using the benchmark Sikkim Aerial Images Dataset for Object Detection (SAIOD). The efficacy of the two hybrid models is assessed using the well-established performance metrics, including precision, recall, F1-score, and the ROC curve. The results indicate that the first model, which employs MHA, achieves superior performance with an accuracy of 95.80%. Both models outperform the best existing methods, achieving accuracies of 95.80% and 95.52%, respectively.<\/jats:p>","DOI":"10.1038\/s41598-026-36492-4","type":"journal-article","created":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T02:07:16Z","timestamp":1770775636000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["A hybrid ResNet50-vision transformer model with an attention mechanism for aerial image classification"],"prefix":"10.1038","volume":"16","author":[{"given":"Amr","family":"Aboghanem","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mohamed","family":"Abd Elfattah","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hanan","family":"M. Amer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Abeer","family":"Tawkol Khalil","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,2,11]]},"reference":[{"key":"36492_CR1","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2024.109859","volume":"142","author":"S Dutta","year":"2025","unstructured":"Dutta, S., Das, M. & Maulik, U. Lightweight deep learning models for aerial scene classification: A comprehensive survey. Eng. Appl. Artif. Intell. 142, 109859 (2025).","journal-title":"Eng. Appl. Artif. Intell."},{"key":"36492_CR2","unstructured":"Mordor Intelligence. Aerial imaging market analysis | industry report, size & share. https:\/\/www.mordorintelligence.com\/industry-reports\/aerial-imaging-market (2025). Accessed: 2025-11-13 11:15 AM (GMT+2)."},{"key":"36492_CR3","unstructured":"Union of Concerned Scientists (UCS). Ucs satellite database. https:\/\/www.ucs.org\/resources\/satellite-database (2025). Last accessed: 2025-11-13 at 10:42 AM (GMT+2)."},{"key":"36492_CR4","doi-asserted-by":"crossref","unstructured":"Kumar, S., Singh, S. & Dewangan, N.\u00a0K. Leveraging cloud resources for distributed training of residual CNNS in aerial image classification. IEEE Access (2025).","DOI":"10.1109\/ACCESS.2025.3542093"},{"key":"36492_CR5","volume":"128","author":"Z Xu","year":"2024","unstructured":"Xu, Z., Wang, T., Skidmore, A. K. & Lamprey, R. A review of deep learning techniques for detecting animals in aerial and satellite images. Int. J. Appl. Earth Obs. Geoinf. 128, 103732 (2024).","journal-title":"Int. J. Appl. Earth Obs. Geoinf."},{"key":"36492_CR6","doi-asserted-by":"crossref","unstructured":"Shoaib, H.\u00a0A. et al. Advancements and challenges of deep learning architectures for aerial image analysis: A systematic review. Intelligent Systems with Applications 200537 (2025).","DOI":"10.1016\/j.iswa.2025.200537"},{"key":"36492_CR7","doi-asserted-by":"publisher","first-page":"255","DOI":"10.1007\/s11831-024-10134-2","volume":"32","author":"M Shah","year":"2025","unstructured":"Shah, M. & Sureja, N. A comprehensive review of bias in deep learning models: Methods, impacts, and future directions. Archiv. Computat. Methods Eng. 32, 255\u2013267 (2025).","journal-title":"Archiv. Computat. Methods Eng."},{"key":"36492_CR8","doi-asserted-by":"publisher","first-page":"160","DOI":"10.3390\/drones8040160","volume":"8","author":"Y Zhou","year":"2024","unstructured":"Zhou, Y. et al. Generalized category discovery in aerial image classification via slot attention. Drones 8, 160 (2024).","journal-title":"Drones"},{"key":"36492_CR9","volume":"29","author":"N Saini","year":"2023","unstructured":"Saini, N., Chattopadhyay, C. & Das, D. E2alertnet: An explainable, efficient, and lightweight model for emergency alert from aerial imagery. Remote Sens. Appl. Soc. nviron. 29, 100896 (2023).","journal-title":"Remote Sens. Appl. Soc. nviron."},{"key":"36492_CR10","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1007\/s11554-024-01430-y","volume":"21","author":"OM Mogaka","year":"2024","unstructured":"Mogaka, O. M., Zewail, R., Inoue, K. & Sayed, M. S. Tinyemergencynet: A hardware-friendly ultra-lightweight deep learning model for aerial scene image classification. J. Real-Time Image Proc. 21, 51 (2024).","journal-title":"J. Real-Time Image Proc."},{"key":"36492_CR11","doi-asserted-by":"publisher","DOI":"10.7717\/peerj-cs.2571","volume":"10","author":"O Pesek","year":"2024","unstructured":"Pesek, O., Krisztian, L., Landa, M., Metz, M. & Neteler, M. Convolutional neural networks for road surface classification on aerial imagery. PeerJ Comput. Sci. 10, e2571 (2024).","journal-title":"PeerJ Comput. Sci."},{"key":"36492_CR12","doi-asserted-by":"crossref","unstructured":"Pradhan, P.\u00a0K. et al. Swinsight: A hierarchical vision transformer using shifted windows to leverage aerial image classification. Multimedia Tools and Applications 1\u201322 (2024).","DOI":"10.1007\/s11042-024-19615-9"},{"key":"36492_CR13","doi-asserted-by":"crossref","unstructured":"Pradhan, P.\u00a0K. et al. Enhancing yolov11 with multi-head channel-attentive feature enhancement module for aerial image classification. In 2025 International Conference on Computing, Intelligence, and Application (CIACON), 1\u20136 (IEEE, 2025).","DOI":"10.1109\/CIACON65473.2025.11189768"},{"key":"36492_CR14","first-page":"12116","volume":"34","author":"M Raghu","year":"2021","unstructured":"Raghu, M., Unterthiner, T., Kornblith, S., Zhang, C. & Dosovitskiy, A. Do vision transformers see like convolutional neural networks?. Adv. Neural. Inf. Process. Syst. 34, 12116\u201312128 (2021).","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"36492_CR15","doi-asserted-by":"crossref","unstructured":"Chen, C.-F.\u00a0R., Fan, Q. & Panda, R. Crossvit: Cross-attention multi-scale vision transformer for image classification. In Proceedings of the IEEE\/CVF International Conference on Computer Vision, 357\u2013366 (2021).","DOI":"10.1109\/ICCV48922.2021.00041"},{"key":"36492_CR16","doi-asserted-by":"publisher","first-page":"2917","DOI":"10.1007\/s10462-023-10595-0","volume":"56","author":"A Khan","year":"2023","unstructured":"Khan, A. et al. A survey of the vision transformers and their CNN-transformer based variants. Artif. Intell. Rev. 56, 2917\u20132970 (2023).","journal-title":"Artif. Intell. Rev."},{"key":"36492_CR17","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2024.109583","volume":"139","author":"J Wang","year":"2025","unstructured":"Wang, J., Yu, L. & Tian, S. Cross-attention interaction learning network for multi-model image fusion via transformer. Eng. Appl. Artif. Intell. 139, 109583 (2025).","journal-title":"Eng. Appl. Artif. Intell."},{"key":"36492_CR18","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2025.111470","volume":"163","author":"W-T Zhang","year":"2025","unstructured":"Zhang, W.-T., Bai, Y., Zheng, S.-D., Cui, J. & Huang, Z.-Z. Tensor transformer for hyperspectral image classification. Pattern Recogn. 163, 111470 (2025).","journal-title":"Pattern Recogn."},{"key":"36492_CR19","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10462-025-11150-9","volume":"58","author":"W Hua","year":"2025","unstructured":"Hua, W. & Chen, Q. A survey of small object detection based on deep learning in aerial images. Artif. Intell. Rev. 58, 1\u201367 (2025).","journal-title":"Artif. Intell. Rev."},{"key":"36492_CR20","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S. & Sun, J. Deep residual learning for image recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 770\u2013778 (2016).","DOI":"10.1109\/CVPR.2016.90"},{"key":"36492_CR21","doi-asserted-by":"publisher","first-page":"6111","DOI":"10.1007\/s00521-019-04097-w","volume":"32","author":"L Wen","year":"2020","unstructured":"Wen, L., Li, X. & Gao, L. A transfer convolutional neural network for fault diagnosis based on resnet-50. Neural Comput. Appl. 32, 6111\u20136124 (2020).","journal-title":"Neural Comput. Appl."},{"key":"36492_CR22","unstructured":"Dosovitskiy, A. et al. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)."},{"key":"36492_CR23","unstructured":"Vaswani, A. et al. Attention is all you need. Advances in Neural Information Processing Systems30 (2017)."},{"key":"36492_CR24","doi-asserted-by":"publisher","unstructured":"Pradhan, P.\u00a0K., Das, A., Kumar, A. & Ghosal, P. Saiod sikkim aerial images dataset for object detection. Mendeley Data, V1, last access 18 Feb (2025). https:\/\/doi.org\/10.17632\/vwznrr98b9.1 (2023).","DOI":"10.17632\/vwznrr98b9.1"},{"key":"36492_CR25","unstructured":"Kingma, D.\u00a0P. & Ba, J. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"36492_CR26","first-page":"168","volume":"17","author":"A Tharwat","year":"2021","unstructured":"Tharwat, A. Classification assessment methods. Appl. Comput. Inf. 17, 168\u2013192 (2021).","journal-title":"Appl. Comput. Inf."},{"key":"36492_CR27","unstructured":"Krizhevsky, A., Sutskever, I. & Hinton, G.\u00a0E. Imagenet classification with deep convolutional neural networks. Advances in Neural Information Processing Systems25 (2012)."},{"key":"36492_CR28","unstructured":"Iandola, F.\u00a0N. et al. Squeezenet: Alexnet-level accuracy with 50x fewer parameters and$$<$$ 0.5 mb model size. arXiv preprint arXiv:1602.07360 (2016)."},{"key":"36492_CR29","doi-asserted-by":"crossref","unstructured":"Szegedy, C. et al. Going deeper with convolutions. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 1\u20139 (2015).","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"36492_CR30","doi-asserted-by":"crossref","unstructured":"Liu, Z. et al. Swin transformer: Hierarchical vision transformer using shifted windows. In Proceedings of the IEEE\/CVF International Conference on Computer Vision, 10012\u201310022 (2021).","DOI":"10.1109\/ICCV48922.2021.00986"}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-36492-4","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-36492-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-36492-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T10:21:11Z","timestamp":1770805271000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-36492-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,11]]},"references-count":30,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["36492"],"URL":"https:\/\/doi.org\/10.1038\/s41598-026-36492-4","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,11]]},"assertion":[{"value":"2 May 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 January 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 February 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"5940"}}