{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T22:12:42Z","timestamp":1776118362742,"version":"3.50.1"},"reference-count":53,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,12,17]],"date-time":"2024-12-17T00:00:00Z","timestamp":1734393600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,17]],"date-time":"2024-12-17T00:00:00Z","timestamp":1734393600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Supercomput"],"published-print":{"date-parts":[[2025,1]]},"DOI":"10.1007\/s11227-024-06765-8","type":"journal-article","created":{"date-parts":[[2024,12,17]],"date-time":"2024-12-17T12:24:08Z","timestamp":1734438248000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":28,"title":["YOLO-SS: optimizing YOLO for enhanced small object detection in remote sensing imagery"],"prefix":"10.1007","volume":"81","author":[{"given":"Qiang","family":"Tang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chang","family":"Su","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuan","family":"Tian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shibin","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kai","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Hao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xubin","family":"Feng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Meilin","family":"Xie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,12,17]]},"reference":[{"key":"6765_CR1","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1016\/j.isprsjprs.2018.04.003","volume":"145","author":"Z Deng","year":"2018","unstructured":"Deng Z, Sun H, Zhou S, Zhao J, Lei L, Zou H (2018) Multi-scale object detection in remote sensing imagery with convolutional neural networks. ISPRS J Photogramm Remote Sens 145:3\u201322","journal-title":"ISPRS J Photogramm Remote Sens"},{"key":"6765_CR2","doi-asserted-by":"crossref","unstructured":"Zhang W, Wang S, Thachan S, Chen J, Qian Y (2018) Deconv r-cnn for small object detection on remote sensing images. In: IGARSS 2018-2018 IEEE International Geoscience and Remote Sensing Symposium, pp. 2483\u20132486 . IEEE","DOI":"10.1109\/IGARSS.2018.8517436"},{"key":"6765_CR3","doi-asserted-by":"crossref","unstructured":"Yu J, Jiang Y, Wang Z, Cao Z, Huang T (2016) Unitbox: an advanced object detection network. In: proceedings of the 24th ACM International Conference on Multimedia, pp. 516\u2013520","DOI":"10.1145\/2964284.2967274"},{"key":"6765_CR4","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.107149","volume":"100","author":"W Ma","year":"2020","unstructured":"Ma W, Wu Y, Cen F, Wang G (2020) Mdfn: multi-scale deep feature learning network for object detection. Pattern Recognit 100:107149","journal-title":"Pattern Recognit"},{"key":"6765_CR5","doi-asserted-by":"crossref","unstructured":"Redmon J, Divvala S, Girshick R, Farhadi A (2016) You only look once: Unified, real-time object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 779\u2013788","DOI":"10.1109\/CVPR.2016.91"},{"key":"6765_CR6","doi-asserted-by":"crossref","unstructured":"Redmon J, Farhadi A (2017) Yolo9000: better, faster, stronger. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7263\u20137271","DOI":"10.1109\/CVPR.2017.690"},{"key":"6765_CR7","unstructured":"Redmon J, Farhadi A (2018) Yolov3: An incremental improvement. arXiv preprint arXiv:1804.02767"},{"key":"6765_CR8","unstructured":"Bochkovskiy, A, Wang, C-Y, Liao, H-YM.: Yolov4: optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934 (2020)"},{"key":"6765_CR9","unstructured":"Mahendrakar T, White RT, Wilde M, Kish B, Silver I (2021) Real-time satellite component recognition with yolo-v5. In: Small Satellite Conference"},{"key":"6765_CR10","unstructured":"Li C, Li L, Jiang H, Weng K, Geng Y, Li L, Ke Z, Li Q, Cheng M, Nie W, et al. (2022) Yolov6: a single-stage object detection framework for industrial applications. arXiv preprint arXiv:2209.02976"},{"key":"6765_CR11","doi-asserted-by":"crossref","unstructured":"Wang C-Y, Bochkovskiy A, Liao H-YM (2023) 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, pp. 7464\u20137475","DOI":"10.1109\/CVPR52729.2023.00721"},{"key":"6765_CR12","unstructured":"Liu B, Wang M, Foroosh H, Tappen M, Pensky M (2015) Sparse convolutional neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 806\u2013814"},{"key":"6765_CR13","doi-asserted-by":"crossref","unstructured":"Lin T-Y, Maire M, Belongie S, Hays J, Perona P, Ramanan D, Doll\u00e1r P, Zitnick CL. (2014) Microsoft coco: Common objects in context. In: Computer Vision\u2013ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part V 13, pp. 740\u2013755. Springer","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"6765_CR14","doi-asserted-by":"crossref","unstructured":"Chen C, Liu M-Y, Tuzel O, Xiao J (2017) R-cnn for small object detection. In: Computer Vision\u2013ACCV 2016: 13th Asian Conference on Computer Vision, Taipei, Taiwan, November 20-24, 2016, Revised Selected Papers, Part V 13, pp. 214\u2013230. Springer","DOI":"10.1007\/978-3-319-54193-8_14"},{"key":"6765_CR15","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109801","volume":"143","author":"H Zhang","year":"2023","unstructured":"Zhang H, Li M, Miao D, Pedrycz W, Wang Z, Jiang M (2023) Construction of a feature enhancement network for small object detection. Pattern Recognit 143:109801","journal-title":"Pattern Recognit"},{"key":"6765_CR16","doi-asserted-by":"crossref","unstructured":"Graham S, Epstein D, Rajpoot N (2019) Rota-net: rotation equivariant network for simultaneous gland and lumen segmentation in colon histology images. In: Digital Pathology: 15th European Congress, ECDP 2019, Warwick, UK, April 10\u201313, 2019, Proceedings 15, pp. 109\u2013116. Springer","DOI":"10.1007\/978-3-030-23937-4_13"},{"key":"6765_CR17","doi-asserted-by":"crossref","unstructured":"Kisantal M, Wojna Z, Murawski J, Naruniec J, Cho K (2019) Augmentation for small object detection. arXiv preprint arXiv:1902.07296","DOI":"10.5121\/csit.2019.91713"},{"key":"6765_CR18","first-page":"1","volume":"60","author":"J-H Kim","year":"2022","unstructured":"Kim J-H, Hwang Y (2022) Gan-based synthetic data augmentation for infrared small target detection. IEEE Trans Geosci Remote Sens 60:1\u201312","journal-title":"IEEE Trans Geosci Remote Sens"},{"key":"6765_CR19","doi-asserted-by":"crossref","unstructured":"Wang K, Liew JH, Zou Y, Zhou D, Feng J (2019) Panet: Few-shot image semantic segmentation with prototype alignment. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9197\u20139206","DOI":"10.1109\/ICCV.2019.00929"},{"key":"6765_CR20","doi-asserted-by":"crossref","unstructured":"Chen J, Mai H, Luo L, Chen X, Wu K (2021) Effective feature fusion network in bifpn for small object detection. In: 2021 IEEE International Conference on Image Processing (ICIP), pp. 699\u2013703. IEEE","DOI":"10.1109\/ICIP42928.2021.9506347"},{"key":"6765_CR21","doi-asserted-by":"crossref","unstructured":"Qiao S, Chen L-C, Yuille A (2021) Detectors: detecting objects with recursive feature pyramid and switchable atrous convolution. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10213\u201310224","DOI":"10.1109\/CVPR46437.2021.01008"},{"key":"6765_CR22","doi-asserted-by":"crossref","unstructured":"Li Y, Chen Y, Wang N, Zhang Z (2019) Scale-aware trident networks for object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6054\u20136063","DOI":"10.1109\/ICCV.2019.00615"},{"key":"6765_CR23","doi-asserted-by":"crossref","unstructured":"Fan D, Liu D, Chi W, Liu X, Li Y (2020) Improved ssd-based multi-scale pedestrian detection algorithm. In: advances in 3D Image and Graphics Representation, Analysis, Computing and Information Technology: algorithms and Applications, Proceedings of IC3DIT 2019, Volume 2, pp. 109\u2013118. Springer","DOI":"10.1007\/978-981-15-3867-4_14"},{"key":"6765_CR24","doi-asserted-by":"crossref","unstructured":"Singh B. Davis LS (2018) An analysis of scale invariance in object detection snip. In: proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3578\u20133587","DOI":"10.1109\/CVPR.2018.00377"},{"key":"6765_CR25","unstructured":"Singh B. Najibi M. Davis LS (2018) Sniper: efficient multi-scale training. Advances in neural information processing systems 31"},{"key":"6765_CR26","doi-asserted-by":"crossref","unstructured":"Li Y, Chen Y, Wang N, Zhang Z (2019) Scale-aware trident networks for object detection. In: proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6054\u20136063","DOI":"10.1109\/ICCV.2019.00615"},{"issue":"4","key":"6765_CR27","doi-asserted-by":"publisher","first-page":"2452","DOI":"10.1109\/TGRS.2017.2781143","volume":"56","author":"X Bai","year":"2018","unstructured":"Bai X, Bi Y (2018) Derivative entropy-based contrast measure for infrared small-target detection. IEEE Trans Geosci Remote Sens 56(4):2452\u20132466","journal-title":"IEEE Trans Geosci Remote Sens"},{"issue":"1","key":"6765_CR28","doi-asserted-by":"publisher","first-page":"47","DOI":"10.3390\/rs12010047","volume":"12","author":"S Huang","year":"2019","unstructured":"Huang S, Liu Y, He Y, Zhang T, Peng Z (2019) Structure-adaptive clutter suppression for infrared small target detection: chain-growth filtering. Remote Sens 12(1):47","journal-title":"Remote Sens"},{"issue":"6","key":"6765_CR29","doi-asserted-by":"publisher","first-page":"1758","DOI":"10.1109\/TCSVT.2019.2905881","volume":"30","author":"X Liang","year":"2019","unstructured":"Liang X, Zhang J, Zhuo L, Li Y, Tian Q (2019) Small object detection in unmanned aerial vehicle images using feature fusion and scaling-based single shot detector with spatial context analysis. IEEE Trans Circuits Syst Video Technol 30(6):1758\u20131770","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"6765_CR30","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TIM.2021.3118092","volume":"70","author":"X Lu","year":"2021","unstructured":"Lu X, Ji J, Xing Z, Miao Q (2021) Attention and feature fusion ssd for remote sensing object detection. IEEE Trans Instrument Measure 70:1\u20139","journal-title":"IEEE Trans Instrument Measure"},{"issue":"5","key":"6765_CR31","doi-asserted-by":"publisher","first-page":"3979","DOI":"10.1109\/TAES.2022.3159308","volume":"58","author":"F Chen","year":"2022","unstructured":"Chen F, Gao C, Liu F, Zhao Y, Zhou Y, Meng D, Zuo W (2022) Local patch network with global attention for infrared small target detection. IEEE Trans Aerospace Electron Syst 58(5):3979\u20133991","journal-title":"IEEE Trans Aerospace Electron Syst"},{"key":"6765_CR32","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/LGRS.2020.3011973","volume":"19","author":"M Hong","year":"2021","unstructured":"Hong M, Li S, Yang Y, Zhu F, Zhao Q, Lu L (2021) Sspnet: scale selection pyramid network for tiny person detection from uav images. IEEE Geosci Remote Sens Lett 19:1\u20135","journal-title":"IEEE Geosci Remote Sens Lett"},{"key":"6765_CR33","doi-asserted-by":"crossref","unstructured":"Yang T-Y, Chen Y-T, Lin Y-Y, Chuang Y-Y (2019) Fsa-net: Learning fine-grained structure aggregation for head pose estimation from a single image. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1087\u20131096","DOI":"10.1109\/CVPR.2019.00118"},{"key":"6765_CR34","doi-asserted-by":"crossref","unstructured":"Du L, Wu W, Li C (2024) Super-resolution-assisted feature refined extraction for small objects in remote sensing images. In: International Conference on Multimedia Modeling, pp. 296\u2013309. Springer","DOI":"10.1007\/978-3-031-53308-2_22"},{"issue":"13","key":"6765_CR35","doi-asserted-by":"publisher","first-page":"2620","DOI":"10.3390\/rs13132620","volume":"13","author":"J Wu","year":"2021","unstructured":"Wu J, Xu S (2021) From point to region: accurate and efficient hierarchical small object detection in low-resolution remote sensing images. Remote Sens 13(13):2620","journal-title":"Remote Sens"},{"key":"6765_CR36","doi-asserted-by":"crossref","unstructured":"Xu C, Wang J, Yang W, Yu H, Yu L, Xia G-S (2022) Rfla: Gaussian receptive field based label assignment for tiny object detection. In: European Conference on Computer Vision, pp. 526\u2013543. Springer","DOI":"10.1007\/978-3-031-20077-9_31"},{"key":"6765_CR37","doi-asserted-by":"crossref","unstructured":"Zheng Z, Wang P, Liu W, Li J, Ye R, Ren D (2020) Distance-iou loss: faster and better learning for bounding box regression. In: proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 12993\u201313000","DOI":"10.1609\/aaai.v34i07.6999"},{"key":"6765_CR38","doi-asserted-by":"crossref","unstructured":"Zhang H, Wang Y, Dayoub F, Sunderhauf N (2021) Varifocalnet: an iou-aware dense object detector. In: proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8514\u20138523","DOI":"10.1109\/CVPR46437.2021.00841"},{"key":"6765_CR39","unstructured":"Wang J. Xu C. Yang W. Yu L (2021) A normalized gaussian wasserstein distance for tiny object detection. arXiv preprint arXiv:2110.13389"},{"key":"6765_CR40","doi-asserted-by":"crossref","unstructured":"Wang J. Yang W. Guo H. Zhang R. Xia G-S (2021) Tiny object detection in aerial images. In: 2020 25th International Conference on Pattern Recognition (ICPR), pp. 3791\u20133798. IEEE","DOI":"10.1109\/ICPR48806.2021.9413340"},{"key":"6765_CR41","unstructured":"Chen X, Liang C, Huang D, Real E, Wang K, Pham H, Dong X, Luong T, Hsieh C-J, Lu Y, et al. (2024) Symbolic discovery of optimization algorithms. Advances in Neural Information Processing Systems 36"},{"key":"6765_CR42","doi-asserted-by":"crossref","unstructured":"Liu H-I, Tseng Y-W, Chang K-C, Wang P-J, Shuai H-H, Cheng W-H (2024) A denoising fpn with transformer r-cnn for tiny object detection. IEEE Transactions on Geoscience and Remote Sensing","DOI":"10.1109\/TGRS.2024.3396489"},{"key":"6765_CR43","doi-asserted-by":"crossref","unstructured":"Sunkara R, Luo T (2022) No more strided convolutions or pooling: A new cnn building block for low-resolution images and small objects. In: Joint European Conference on Machine Learning and Knowledge Discovery in Databases, pp. 443\u2013459. Springer","DOI":"10.1007\/978-3-031-26409-2_27"},{"key":"6765_CR44","doi-asserted-by":"crossref","unstructured":"Jeong J, Park H, Kwak N (2017) Enhancement of ssd by concatenating feature maps for object detection. arXiv preprint arXiv:1705.09587","DOI":"10.5244\/C.31.76"},{"key":"6765_CR45","doi-asserted-by":"crossref","unstructured":"Yang Z, Liu S, Hu H, Wang L, Lin S (2019) Reppoints: Point set representation for object detection. In: proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9657\u20139666","DOI":"10.1109\/ICCV.2019.00975"},{"key":"6765_CR46","doi-asserted-by":"crossref","unstructured":"Tian Z, Shen C, Chen H, He, T (2019) Fcos: Fully convolutional one-stage object detection. In: 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 9626\u20139635. 10.1109\/ICCV.2019.00972","DOI":"10.1109\/ICCV.2019.00972"},{"key":"6765_CR47","unstructured":"Zhou X, Wang D, Kr\u00e4henb\u00fchl P (2019) Objects as points. arXiv preprint arXiv:1904.07850"},{"key":"6765_CR48","doi-asserted-by":"crossref","unstructured":"Lin T-Y, Goyal P, Girshick R, He K, Doll\u00e1r P (2017) Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2980\u20132988","DOI":"10.1109\/ICCV.2017.324"},{"key":"6765_CR49","doi-asserted-by":"crossref","unstructured":"Zhang S, Chi C, Yao Y, Lei Z, Li SZ (2020) dging the gap between anchor-based and anchor-free detection via adaptive training sample selection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9759\u20139768","DOI":"10.1109\/CVPR42600.2020.00978"},{"key":"6765_CR50","doi-asserted-by":"crossref","unstructured":"Rezatofighi H, Tsoi N, Gwak J, Sadeghian A, Reid I, Savarese S (2019) 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, pp. 658\u2013666","DOI":"10.1109\/CVPR.2019.00075"},{"key":"6765_CR51","doi-asserted-by":"crossref","unstructured":"Cai Z, Vasconcelos N (018) Cascade r-cnn: Delving into high quality object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6154\u20136162","DOI":"10.1109\/CVPR.2018.00644"},{"key":"6765_CR52","doi-asserted-by":"crossref","unstructured":"Qiao S, Chen L, Yuille A (2020) b16: Detecting objects with recursive feature pyramid and switchable atrous convolution. CoRR","DOI":"10.1109\/CVPR46437.2021.01008"},{"key":"6765_CR53","unstructured":"Wang C, Yeh I, Liao H (2018) You only learn one representation: Unified network for multiple tasks. arXiv preprint arXiv:2105.04206"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-024-06765-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11227-024-06765-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-024-06765-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,17]],"date-time":"2024-12-17T13:03:35Z","timestamp":1734440615000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11227-024-06765-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,17]]},"references-count":53,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,1]]}},"alternative-id":["6765"],"URL":"https:\/\/doi.org\/10.1007\/s11227-024-06765-8","relation":{},"ISSN":["0920-8542","1573-0484"],"issn-type":[{"value":"0920-8542","type":"print"},{"value":"1573-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,17]]},"assertion":[{"value":"22 November 2024","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 December 2024","order":2,"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 that they have no known competing financial interests or personal relationships that could have appeared to influence the work reported in this paper.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"303"}}