{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T20:35:59Z","timestamp":1790368559120,"version":"4.1.0"},"reference-count":32,"publisher":"Public Library of Science (PLoS)","issue":"5","license":[{"start":{"date-parts":[[2025,5,23]],"date-time":"2025-05-23T00:00:00Z","timestamp":1747958400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>In the domain of remote sensing image small target detection, challenges such as difficulties in extracting features of small targets, complex backgrounds that easily lead to confusion with targets, and high computational complexity with significant resource consumption are prevalent. We propose a lightweight small target detection algorithm for remote sensing images that combines GSConv and PConv, named LI-YOLOv8. Using YOLOv8n as the baseline algorithm, the activation function SiLU in the CBS at the backbone network\u2019s SPPF is replaced with ReLU, which reduces interdependencies among parameters. Then, RFAConv is embedded after the first CBS to expand the receptive field and extract more features of small targets. An efficient Multi-Scale Attention (EMA) mechanism is embedded at the terminal of C2f within the neck network to integrate more detailed information, enhancing the focus on small targets. The head network incorporates a lightweight detection head, GP-Detect, which combines GSConv and PConv to decrease the parameter count and computational demand. Integrating Inner-IoU and Wise-IoU v3 to design the Inner-Wise IoU loss function, replacing the original CIoU loss function. This approach provides the algorithm with a gain distribution strategy, focuses on anchor boxes of ordinary quality, and strengthens generalization capability. We conducted ablation and comparative experiments on the public datasets RSOD and NWPU VHR-10. Compared to YOLOv8, our approach achieved improvements of 7.6% and 2.8% in mAP@0.5, and increases of 2.1% and 1.1% in mAP@0.5:0.95. Furthermore, Parameters and GFLOPs were reduced by 10.0% and 23.2%, respectively, indicating a significant enhancement in detection accuracy along with a substantial decrease in both parameters and computational costs. Generalization experiments were conducted on the TinyPerson, LEVIR-ship, brain-tumor, and smoke_fire_1 datasets. The mAP@0.5 metric improved by 2.6%, 5.3%, 2.6%, and 2.3%, respectively, demonstrating the algorithm\u2019s robust performance.<\/jats:p>","DOI":"10.1371\/journal.pone.0321026","type":"journal-article","created":{"date-parts":[[2025,5,23]],"date-time":"2025-05-23T13:37:08Z","timestamp":1748007428000},"page":"e0321026","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":17,"title":["LI-YOLOv8: Lightweight small target detection algorithm for remote sensing images that combines GSConv and PConv"],"prefix":"10.1371","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-2095-5500","authenticated-orcid":true,"given":"Pingping","family":"Yan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiangming","family":"Qi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liang","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2025,5,23]]},"reference":[{"key":"pone.0321026.ref001","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1007\/978-3-319-46448-0_2","article-title":"SSD: Single shot multibox detector.","volume-title":"Computer Vision\u2013ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11\u201314, 2016, Proceedings, Part I 14","author":"W Liu","year":"2016"},{"key":"pone.0321026.ref002","first-page":"779","article-title":"You only look once: unified, real-time object detection.","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"J Redmon","year":"2016"},{"key":"pone.0321026.ref003","first-page":"7263","article-title":"YOLO9000: better, faster, stronger.","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"J Redmon","year":"2017"},{"key":"pone.0321026.ref004","article-title":"YOLOv3: an incremental improvement","author":"J Redmon","year":"2018","journal-title":"arXiv preprint"},{"key":"pone.0321026.ref005","article-title":"YOLOv4: Optimal speed and accuracy of object detection","author":"A Bochkovskiy","year":"2018","journal-title":"arXiv preprint"},{"key":"pone.0321026.ref006","first-page":"7464","article-title":"YOLOv7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors.","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"C Wang","year":"2023"},{"key":"pone.0321026.ref007","doi-asserted-by":"crossref","first-page":"4371","DOI":"10.1109\/JSTARS.2022.3175498","article-title":"Finding nonrigid tiny person with densely cropped and local attention object detector networks in low-altitude aerial images","volume":"15","author":"X Zhang","year":"2022","journal-title":"IEEE J Select Topics Appl Earth Observ Remote Sens"},{"key":"pone.0321026.ref008","article-title":"BAM: bottleneck attention module","author":"J Park","year":"2018","journal-title":"arXiv preprint"},{"issue":"14","key":"pone.0321026.ref009","doi-asserted-by":"crossref","first-page":"3240","DOI":"10.3390\/rs14143240","article-title":"YOLOD: a target detection method for UAV aerial imagery","volume":"14","author":"X Luo","year":"2022","journal-title":"Remote Sens"},{"key":"pone.0321026.ref010","first-page":"233","article-title":"YOLOv7-SEA: object detection of maritime UAV images based on improved YOLOv7.","volume-title":"Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision","author":"H Zhao","year":"2023"},{"issue":"12","key":"pone.0321026.ref011","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0289162","article-title":"A lightweight YOLOv7 insulator defect detection algorithm based on DSC-SE","volume":"18","author":"Y Zhang","year":"2023","journal-title":"PLoS One"},{"key":"pone.0321026.ref012","article-title":"CSPPartial-YOLO: a lightweight YOLO-based method for typical objects detection in remote sensing images","author":"S Xie","year":"2023","journal-title":"IEEE J Select Topics Appl Earth Observ Remote Sens"},{"key":"pone.0321026.ref013","doi-asserted-by":"crossref","first-page":"1348883","DOI":"10.3389\/fmars.2024.1348883","article-title":"Underwater small target detection based on dynamic convolution and attention mechanism","volume":"11","author":"C Cheng","year":"2024","journal-title":"Front Marine Sci"},{"key":"pone.0321026.ref014","article-title":"Omni-dimensional dynamic convolution","author":"C Li","year":"2022","journal-title":"arXiv preprint"},{"issue":"2","key":"pone.0321026.ref015","article-title":"Lightweight high-precision SAR ship detection method based on YOLOv7-LDS","volume":"19","author":"S Zhu","year":"2024","journal-title":"PLoS One"},{"issue":"9","key":"pone.0321026.ref016","doi-asserted-by":"crossref","first-page":"1904","DOI":"10.1109\/TPAMI.2015.2389824","article-title":"Spatial pyramid pooling in deep convolutional networks for visual recognition","volume":"37","author":"K He","year":"2015","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"pone.0321026.ref017","first-page":"2117","article-title":"Feature pyramid networks for object detection.","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"T Lin","year":"2017"},{"key":"pone.0321026.ref018","doi-asserted-by":"crossref","first-page":"508","DOI":"10.1109\/ICME.2019.00094","article-title":"Panet: a context based predicate association network for scene graph generation.","volume-title":"2019 IEEE International Conference on Multimedia and Expo (ICME)","author":"Y Chen","year":"2019"},{"issue":"8","key":"pone.0321026.ref019","doi-asserted-by":"crossref","first-page":"8574","DOI":"10.1109\/TCYB.2021.3095305","article-title":"Enhancing geometric factors in model learning and inference for object detection and instance segmentation","volume":"52","author":"Z Zheng","year":"2022","journal-title":"IEEE Trans Cybern"},{"key":"pone.0321026.ref020","article-title":"RFAConv: Innovating spatial attention and standard convolutional operation","author":"X Zhang","year":"2023","journal-title":"arXiv preprint"},{"key":"pone.0321026.ref021","first-page":"1","article-title":"Efficient multi-scale attention module with cross-spatial learning.","volume-title":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"D Ouyang","year":"2023"},{"key":"pone.0321026.ref022","article-title":"Slim-neck by GSConv: a better design paradigm of detector architectures for autonomous vehicles","author":"H Li","year":"2022","journal-title":"arXiv preprint"},{"key":"pone.0321026.ref023","first-page":"1251","article-title":"Xception: deep learning with depthwise separable convolutions.","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"F Chollet","year":"2017"},{"key":"pone.0321026.ref024","first-page":"12021","article-title":"Run, don\u2019t walk: chasing higher flops for faster neural networks.","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"J Chen","year":"2023"},{"key":"pone.0321026.ref025","article-title":"Inner-IoU: more effective intersection over union loss with auxiliary bounding box","author":"H Zhang","year":"2023","journal-title":"arXiv preprint"},{"key":"pone.0321026.ref026","article-title":"Wise-IoU: bounding box regression loss with dynamic focusing mechanism","author":"Z Tong","year":"2023","journal-title":"arXiv preprint"},{"issue":"5","key":"pone.0321026.ref027","doi-asserted-by":"crossref","first-page":"2486","DOI":"10.1109\/TGRS.2016.2645610","article-title":"Accurate object localization in remote sensing images based on convolutional neural networks","volume":"55","author":"Y Long","year":"2017","journal-title":"IEEE Trans Geosci Remote Sensing"},{"key":"pone.0321026.ref028","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1016\/j.isprsjprs.2014.10.002","article-title":"Multi-class geospatial object detection and geographic image classification based on collection of part detectors","volume":"98","author":"G Cheng","year":"2014","journal-title":"ISPRS J Photogram Remote Sens"},{"key":"pone.0321026.ref029","doi-asserted-by":"crossref","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","author":"G Cheng","year":"2016","journal-title":"SPRS J Photogram Remote Sens"},{"issue":"12","key":"pone.0321026.ref030","doi-asserted-by":"crossref","first-page":"7405","DOI":"10.1109\/TGRS.2016.2601622","article-title":"Learning rotation-invariant convolutional neural networks for object detection in VHR optical remote sensing images","volume":"54","author":"G Cheng","year":"2016","journal-title":"IEEE Trans Geosci Remote Sens"},{"key":"pone.0321026.ref031","article-title":"YOLOv9: Learning what you want to learn using programmable gradient information","author":"CY Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"pone.0321026.ref032","article-title":"YOLOv10: real-time end-to-end object detection","author":"A Wang","year":"2024","journal-title":"arXiv preprint"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0321026","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,23]],"date-time":"2025-05-23T13:37:25Z","timestamp":1748007445000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0321026"}},"subtitle":[],"editor":[{"given":"Yile","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2025,5,23]]},"references-count":32,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2025,5,23]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0321026","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5,23]]}}}