{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,14]],"date-time":"2026-08-14T01:26:54Z","timestamp":1786670814806,"version":"build-2736575974"},"reference-count":52,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T00:00:00Z","timestamp":1780531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,8,14]],"date-time":"2026-08-14T00:00:00Z","timestamp":1786665600000},"content-version":"vor","delay-in-days":71,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Guizhou Province Science and Technology Plan Project","award":["XKBF [2025]014"],"award-info":[{"award-number":["XKBF [2025]014"]}]},{"name":"Guizhou University Natural Sciences Special Project","award":["Guida Tegang Hezi (2025) No.13"],"award-info":[{"award-number":["Guida Tegang Hezi (2025) No.13"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    Accurate small-object detection is crucial for automated processes in remote sensing imagery, such as environmental monitoring and aerial surveillance. Yet it remains challenging due to limited feature representation, complex backgrounds, and localization errors. To address these challenges, this work proposes a lightweight detection approach that integrates a scale-based dynamic loss and efficient multi-scale attention. A lightweight backbone, dubbed A2C2fLite, is designed based on the A2C2f module from the most recent YOLO variant to reduce redundant parameters and computational overhead. An EMA module is embedded before the final detection heads to enhance multi-scale feature representation and improve target-background discrimination. The SD loss is used to effectively address scale variation and occlusion, improving localization accuracy beyond existing Intersection-over-Union-based losses. Evaluated on a representative remote sensing dataset, the proposed approach achieves 93.6% precision, 86.6% recall, and 92.6%\n                    <jats:inline-formula>\n                      <jats:tex-math>$$\\hbox {mAP}_{50}$$<\/jats:tex-math>\n                    <\/jats:inline-formula>\n                    , with only 2.0M parameters and 5.7 GFLOPs. Compared to the baseline YOLOv13, it achieves a superior accuracy-efficiency trade-off by reducing parameter counts by 20% and computational overhead by 8.1%, while improving\n                    <jats:inline-formula>\n                      <jats:tex-math>$$\\hbox {mAP}_{50}$$<\/jats:tex-math>\n                    <\/jats:inline-formula>\n                    by 1.5%. Visualization results demonstrate that it suppresses missed alarms and refines bounding-box localization. By minimizing memory footprint and computational bottlenecks, this lightweight design provides clear practical advantages for real-time small-object detection on resource-constrained edge devices, such as onboard Unmanned Aerial Vehicle systems and embedded aerial sensors. These findings highlight that the proposed approach offers an efficient, robust, and highly deployable solution for complex remote sensing applications.\n                  <\/jats:p>","DOI":"10.1038\/s41598-026-55239-9","type":"journal-article","created":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T07:13:53Z","timestamp":1780557233000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A lightweight remote sensing small-object detection approach with scale-based dynamic loss and efficient multi-scale attention"],"prefix":"10.1038","volume":"16","author":[{"given":"Anying","family":"Xu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuanyu","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wuzhong","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,6,4]]},"reference":[{"key":"55239_CR1","doi-asserted-by":"crossref","unstructured":"Cao, Z., Li, J., Niu, J. & Zhou, M. QuerySOD: a small object detection algorithm based on sparse convolutional network and query mechanism. In 2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS) 9581\u20139587 (IEEE, 2024).","DOI":"10.1109\/IROS58592.2024.10801539"},{"key":"55239_CR2","unstructured":"Zeng, Y. HMPE: HeatMap embedding for efficient transformer-based small object detection. arXiv preprint arXiv:2504.13469 (2025)."},{"key":"55239_CR3","doi-asserted-by":"crossref","unstructured":"Peng, Y., Wang, J., Wang, W., Liu, L. et al. An efficient multi-band infrared small objects detection approach for low-altitude artificial intelligence of thing. IEEE Internet Things J. (2025).","DOI":"10.1109\/JIOT.2025.3544258"},{"key":"55239_CR4","doi-asserted-by":"publisher","DOI":"10.1016\/j.aei.2025.103224","volume":"65","author":"T Sun","year":"2025","unstructured":"Sun, T., Fan, Q. & Shao, Y. Deep learning-based rebar detection and instance segmentation in images. Adv. Eng. Inform. 65, 103224 (2025).","journal-title":"Adv. Eng. Inform."},{"key":"55239_CR5","doi-asserted-by":"crossref","unstructured":"Shen, J. Lightweight semantic feature extraction model with direction awareness for aerial traffic object detection. IEEE Trans. Intell. Transp. Syst. (2025).","DOI":"10.1109\/TITS.2025.3642410"},{"key":"55239_CR6","doi-asserted-by":"crossref","unstructured":"Li, D. KACNet: enhancing CNN feature representation with Kolmogorov-Arnold networks for medical image segmentation and classification. Inf. Sci. 122760 (2025).","DOI":"10.1016\/j.ins.2025.122760"},{"key":"55239_CR7","doi-asserted-by":"publisher","first-page":"315","DOI":"10.1109\/TCSVT.2023.3284453","volume":"34","author":"F Fang","year":"2023","unstructured":"Fang, F. et al. Enhancing representation learning with spatial transformation and early convolution for reinforcement learning-based small object detection. IEEE Trans. Circuits Syst. Video Technol. 34, 315\u2013328 (2023).","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"55239_CR8","first-page":"1","volume":"71","author":"J Shen","year":"2021","unstructured":"Shen, J. et al. Finger vein recognition algorithm based on lightweight deep convolutional neural network. IEEE Trans. Instrum. Meas. 71, 1\u201313 (2021).","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"55239_CR9","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T. & Malik, J. Rich feature hierarchies for accurate object detection and semantic segmentation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 580\u2013587 (2014).","DOI":"10.1109\/CVPR.2014.81"},{"key":"55239_CR10","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2016","unstructured":"Ren, S., He, K., Girshick, R. & Sun, J. Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 39, 1137\u20131149 (2016).","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"55239_CR11","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2024.109458","volume":"226","author":"Q Liu","year":"2024","unstructured":"Liu, Q., Lv, J. & Zhang, C. MAE-YOLOv8-based small object detection of green crisp plum in real complex orchard environments. Comput. Electron. Agric. 226, 109458 (2024).","journal-title":"Comput. Electron. Agric."},{"key":"55239_CR12","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.122788","volume":"241","author":"AS Sagar","year":"2024","unstructured":"Sagar, A. S., Chen, Y., Xie, Y. & Kim, H. S. MSA R-CNN: a comprehensive approach to remote sensing object detection and scene understanding. Expert Syst. Appl. 241, 122788 (2024).","journal-title":"Expert Syst. Appl."},{"key":"55239_CR13","doi-asserted-by":"crossref","unstructured":"Liu, W., Anguelov, D., Erhan, D., Szegedy, C. et al. SSD: single shot multibox detector. In European Conference on Computer Vision 21\u201337 (Springer, 2016).","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"55239_CR14","unstructured":"Alif, M. A.\u00a0R. & Hussain, M. YOLOv1 to YOLOv10: a comprehensive review of YOLO variants and their application in the agricultural domain. arXiv preprint arXiv:2406.10139 (2024)."},{"key":"55239_CR15","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R. & Farhadi, A. You only look once: unified, real-time object detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 779\u2013788 (2016).","DOI":"10.1109\/CVPR.2016.91"},{"key":"55239_CR16","doi-asserted-by":"crossref","unstructured":"Redmon, J. & Farhadi, A. YOLO9000: better, faster, stronger. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 7263\u20137271 (2017).","DOI":"10.1109\/CVPR.2017.690"},{"key":"55239_CR17","unstructured":"Bochkovskiy, A., Wang, C.-Y. & Liao, H.-Y.\u00a0M. YOLOv4: optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934 (2020)."},{"key":"55239_CR18","unstructured":"Li, C., Li, L., Jiang, H., Weng, K. et al. YOLOv6: a single-stage object detection framework for industrial applications. arXiv preprint arXiv:2209.02976 (2022)."},{"key":"55239_CR19","doi-asserted-by":"crossref","unstructured":"Wang, C.-Y., Bochkovskiy, A. & Liao, H.-Y.\u00a0M. YOLOv7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition 7464\u20137475 (2023).","DOI":"10.1109\/CVPR52729.2023.00721"},{"key":"55239_CR20","doi-asserted-by":"crossref","unstructured":"Wang, C.-Y., Yeh, I.-H. & Mark Liao, H.-Y. YOLOv9: learning what you want to learn using programmable gradient information. In European Conference on Computer Vision 1\u201321 (Springer, 2024).","DOI":"10.1007\/978-3-031-72751-1_1"},{"key":"55239_CR21","doi-asserted-by":"publisher","first-page":"107984","DOI":"10.52202\/079017-3429","volume":"37","author":"A Wang","year":"2024","unstructured":"Wang, A. et al. Yolov10: real-time end-to-end object detection. Adv. Neural. Inf. Process. Syst. 37, 107984\u2013108011 (2024).","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"55239_CR22","doi-asserted-by":"crossref","unstructured":"Tian, Y., Ye, Q. & Doermann, D. YOLOv12: attention-centric real-time object detectors. arXiv preprint arXiv:2502.12524 (2025).","DOI":"10.52202\/085713-2627"},{"key":"55239_CR23","doi-asserted-by":"crossref","unstructured":"Cheng, T., Song, L., Ge, Y. & Liu, W. Yolo-world: real-time open-vocabulary object detection. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition 16901\u201316911 (2024).","DOI":"10.1109\/CVPR52733.2024.01599"},{"key":"55239_CR24","unstructured":"Lei, M., Li, S., Wu, Y., Hu, H. et al. YOLOv13: real-time object detection with hypergraph-enhanced adaptive visual perception. arXiv preprint arXiv:2506.17733 (2025)."},{"key":"55239_CR25","first-page":"1","volume":"56","author":"H-I Liu","year":"2024","unstructured":"Liu, H.-I. et al. Lightweight deep learning for resource-constrained environments: a survey. ACM Comput. Surv. 56, 1\u201342 (2024).","journal-title":"ACM Comput. Surv."},{"key":"55239_CR26","unstructured":"Howard, A. G., Zhu, M., Chen, B. & Kalenichenko, D. MobileNets: efficient convolutional neural networks for mobile vision applications arXiv preprint. arXiv:1704.04861 (2017)."},{"key":"55239_CR27","doi-asserted-by":"crossref","unstructured":"Zhang, X., Zhou, X., Lin, M. & Sun, J. Shufflenet: an extremely efficient convolutional neural network for mobile devices. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 6848\u20136856 (2018).","DOI":"10.1109\/CVPR.2018.00716"},{"key":"55239_CR28","doi-asserted-by":"crossref","unstructured":"Han, K., Wang, Y., Tian, Q. & Guo, J. Ghostnet: more features from cheap operations. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition 1580\u20131589 (2020).","DOI":"10.1109\/CVPR42600.2020.00165"},{"key":"55239_CR29","doi-asserted-by":"crossref","unstructured":"Fu, J., Li, F. & Zhao, J. Regional saliency combined with morphological filtering for infrared maritime target detection in unmanned aerial vehicles images. IEEE Trans. Instrum. Meas. (2025).","DOI":"10.1109\/TIM.2025.3545723"},{"key":"55239_CR30","doi-asserted-by":"publisher","first-page":"21239","DOI":"10.1109\/JIOT.2024.3367415","volume":"11","author":"X Xiong","year":"2024","unstructured":"Xiong, X. et al. Adaptive feature fusion and improved attention mechanism-based small object detection for UAV target tracking. IEEE Internet Things J. 11, 21239\u201321249 (2024).","journal-title":"IEEE Internet Things J."},{"key":"55239_CR31","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L. & Sun, G. Squeeze-and-excitation networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 7132\u20137141 (2018).","DOI":"10.1109\/CVPR.2018.00745"},{"key":"55239_CR32","doi-asserted-by":"crossref","unstructured":"Woo, S., Park, J., Lee, J.-Y. & Kweon, I.\u00a0S. CBAM: convolutional block attention module. In Proceedings of the European Conference on Computer Vision (ECCV), 3\u201319 (2018).","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"55239_CR33","doi-asserted-by":"crossref","unstructured":"Hou, Q., Zhou, D. & Feng, J. Coordinate attention for efficient mobile network design. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 13713\u201313722 (2021).","DOI":"10.1109\/CVPR46437.2021.01350"},{"key":"55239_CR34","doi-asserted-by":"crossref","unstructured":"Rezatofighi, H., Tsoi, N., Gwak, J. & Sadeghian, A. Generalized intersection over union: a metric and a loss for bounding box regression. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition 658\u2013666 (2019).","DOI":"10.1109\/CVPR.2019.00075"},{"key":"55239_CR35","doi-asserted-by":"crossref","unstructured":"Zheng, Z. et al. Distance-IoU loss: faster and better learning for bounding box regression. In Proceedings of the AAAI Conference on Artificial Intelligence 34, 12993\u201313000 (2020).","DOI":"10.1609\/aaai.v34i07.6999"},{"key":"55239_CR36","doi-asserted-by":"publisher","first-page":"8574","DOI":"10.1109\/TCYB.2021.3095305","volume":"52","author":"Z Zheng","year":"2021","unstructured":"Zheng, Z. et al. Enhancing geometric factors in model learning and inference for object detection and instance segmentation. IEEE Trans. Cybern. 52, 8574\u20138586 (2021).","journal-title":"IEEE Trans. Cybern."},{"key":"55239_CR37","doi-asserted-by":"crossref","unstructured":"Yang, J. et al. Pinwheel-shaped convolution and scale-based dynamic loss for infrared small target detection. In Proceedings of the AAAI Conference on Artificial Intelligence 39, 9202\u20139210 (2025).","DOI":"10.1609\/aaai.v39i9.32996"},{"key":"55239_CR38","doi-asserted-by":"crossref","unstructured":"Ouyang, D., He, S., Zhang, G., Luo, M. et al. Efficient multi-scale attention module with cross-spatial learning. In ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 1\u20135 (IEEE, 2023).","DOI":"10.1109\/ICASSP49357.2023.10096516"},{"key":"55239_CR39","doi-asserted-by":"publisher","first-page":"24330","DOI":"10.1109\/TITS.2022.3203715","volume":"23","author":"J Shen","year":"2022","unstructured":"Shen, J. et al. An anchor-free lightweight deep convolutional network for vehicle detection in aerial images. IEEE Trans. Intell. Transp. Syst. 23, 24330\u201324342 (2022).","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"55239_CR40","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2025.126440","volume":"269","author":"H Wang","year":"2025","unstructured":"Wang, H. et al. Precision and speed: LSOD-YOLO for lightweight small object detection. Expert Syst. Appl. 269, 126440 (2025).","journal-title":"Expert Syst. Appl."},{"key":"55239_CR41","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.121036","volume":"234","author":"B Mahaur","year":"2023","unstructured":"Mahaur, B., Mishra, K. & Kumar, A. An improved lightweight small object detection framework applied to real-time autonomous driving. Expert Syst. Appl. 234, 121036 (2023).","journal-title":"Expert Syst. Appl."},{"key":"55239_CR42","doi-asserted-by":"publisher","first-page":"1624","DOI":"10.1109\/TSC.2019.2916416","volume":"14","author":"SY Nikouei","year":"2019","unstructured":"Nikouei, S. Y. et al. Toward intelligent surveillance as an edge network service (iSENSE) using lightweight detection and tracking algorithms. IEEE Trans. Serv. Comput. 14, 1624\u20131637 (2019).","journal-title":"IEEE Trans. Serv. Comput."},{"key":"55239_CR43","doi-asserted-by":"publisher","first-page":"48165","DOI":"10.1007\/s11042-023-17192-x","volume":"83","author":"Z Lyu","year":"2024","unstructured":"Lyu, Z. et al. A survey of model compression strategies for object detection. Multimed. Tools Appl. 83, 48165\u201348236 (2024).","journal-title":"Multimed. Tools Appl."},{"key":"55239_CR44","doi-asserted-by":"publisher","first-page":"5459","DOI":"10.1007\/s40747-024-01448-6","volume":"10","author":"M Li","year":"2024","unstructured":"Li, M., Chen, Y., Zhang, T. & Huang, W. TA-YOLO: a lightweight small object detection model based on multi-dimensional trans-attention module for remote sensing images. Complex Intell. Syst. 10, 5459\u20135473 (2024).","journal-title":"Complex Intell. Syst."},{"key":"55239_CR45","doi-asserted-by":"crossref","unstructured":"Gong, B., Zhang, H., Ma, B. & Tao, Z. Enhancing real-time low-light object detection via multi-scale edge and illumination-guided features in YOLOv8. J. Supercomput.81, 1120 (2025).","DOI":"10.1007\/s11227-025-07594-z"},{"key":"55239_CR46","unstructured":"Veraar, P. Tiny Object Detection in Video with Transformers using Temporal Context. Master\u2019s thesis (2024)."},{"key":"55239_CR47","doi-asserted-by":"crossref","unstructured":"Cheng, X., Zhang, H., Zhang, S., Chen, L. et al. A triple dynamic optimization-based multi-scale object detection network. IEEE J. Sel. Top. Appl. Earth Observ. Remote Sens. (2025).","DOI":"10.1109\/JSTARS.2025.3610623"},{"key":"55239_CR48","doi-asserted-by":"publisher","first-page":"7405","DOI":"10.1109\/TGRS.2016.2601622","volume":"54","author":"G Cheng","year":"2016","unstructured":"Cheng, G., Zhou, P. & Han, J. Learning rotation-invariant convolutional neural networks for object detection in VHR optical remote sensing images. IEEE Trans. Geosci. Remote Sens. 54, 7405\u20137415 (2016).","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"55239_CR49","doi-asserted-by":"crossref","unstructured":"Zhao, Q., Fang, S., Li, Y. & Shang, H. Track defect detection based on improved YOLOv5s. IEEE Trans. Industr. Inf. (2025).","DOI":"10.1109\/TII.2024.3523593"},{"key":"55239_CR50","unstructured":"Zhang, H. & Zhang, S. Focaler-IoU: more focused intersection over union loss. arXiv preprint arXiv:2401.10525 (2024)."},{"key":"55239_CR51","doi-asserted-by":"publisher","first-page":"51094","DOI":"10.52202\/075280-2224","volume":"36","author":"C Wang","year":"2023","unstructured":"Wang, C. et al. Gold-YOLO: efficient object detector via gather-and-distribute mechanism. Adv. Neural. Inf. Process. Syst. 36, 51094\u201351112 (2023).","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"55239_CR52","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Lv, W., Xu, S. & Wei, J. Detrs beat yolos on real-time object detection. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition 16965\u201316974 (2024).","DOI":"10.1109\/CVPR52733.2024.01605"}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-55239-9","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-55239-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-55239-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,14]],"date-time":"2026-08-14T00:29:57Z","timestamp":1786667397000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-55239-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,4]]},"references-count":52,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["55239"],"URL":"https:\/\/doi.org\/10.1038\/s41598-026-55239-9","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,4]]},"assertion":[{"value":"9 April 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 May 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 June 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","label":"Competing interests","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"25448"}}