{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T15:12:43Z","timestamp":1778857963027,"version":"3.51.4"},"reference-count":38,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2026,3,2]],"date-time":"2026-03-02T00:00:00Z","timestamp":1772409600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,3,2]],"date-time":"2026-03-02T00:00:00Z","timestamp":1772409600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"Ministry of Education of the Republic of Korea and the National Research Foundation of Korea","award":["NRF-2020S1A5C2A02093223"],"award-info":[{"award-number":["NRF-2020S1A5C2A02093223"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Machine Vision and Applications"],"published-print":{"date-parts":[[2026,5]]},"DOI":"10.1007\/s00138-026-01803-2","type":"journal-article","created":{"date-parts":[[2026,3,2]],"date-time":"2026-03-02T17:31:37Z","timestamp":1772472697000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Enhancing object detection algorithm for size-insensitive performance"],"prefix":"10.1007","volume":"37","author":[{"given":"Hyoju","family":"Kim","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Soomin","family":"Kwon","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7831-6353","authenticated-orcid":false,"given":"Jaeoh","family":"Kim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,3,2]]},"reference":[{"key":"1803_CR1","unstructured":"Autogyro Yolo-v8: implementation of ultralytics yolov8 in pytorch. https:\/\/github.com\/autogyro\/yolo-V8, accessed: 2025\u201307-13 (2023)"},{"key":"1803_CR2","unstructured":"Bochkovskiy, A., Wang, C., Liao, H.: Yolov4: optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934 (2020)"},{"key":"1803_CR3","doi-asserted-by":"crossref","unstructured":"Cai, Z., Vasconcelos, N.: Cascade r-cnn: delving into high quality object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 6154\u20136162 (2018)","DOI":"10.1109\/CVPR.2018.00644"},{"key":"1803_CR4","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1016\/j.isprsjprs.2016.03.014","volume":"117","author":"G Cheng","year":"2016","unstructured":"Cheng, G., Han, J.: A survey on object detection in optical remote sensing images. ISPRS J. Photogramm. Remote. Sens. 117, 11\u201328 (2016)","journal-title":"ISPRS J. Photogramm. Remote. Sens."},{"key":"1803_CR5","doi-asserted-by":"crossref","unstructured":"Choi, J., Chun, D., Kim, H., Lee, H.-J.: Gaussian yolov3: an accurate and fast object detector using localization uncertainty for autonomous driving. In: Proceedings of the IEEE\/CVF International conference on computer vision, pp. 502\u2013511 (2019)","DOI":"10.1109\/ICCV.2019.00059"},{"issue":"5","key":"1803_CR6","doi-asserted-by":"publisher","first-page":"564","DOI":"10.1109\/TPAMI.2003.1195991","volume":"25","author":"D Comaniciu","year":"2003","unstructured":"Comaniciu, D., Ramesh, V., Meer, P.: Kernel-based object tracking. IEEE Trans. Pattern Anal. Mach. Intell. 25(5), 564\u2013577 (2003)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1803_CR7","unstructured":"Gevorgyan, Z.: Siou loss: more powerful learning for bounding box regression. arxiv 2022. arXiv preprint arXiv:2205.12740 (2022)"},{"key":"1803_CR8","doi-asserted-by":"crossref","unstructured":"Girshick., R.: Fast r-cnn. In: Proceedings of the IEEE international conference on computer vision, pp. 1440\u20131448 (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"1803_CR9","first-page":"20230","volume":"34","author":"J He","year":"2021","unstructured":"He, J., Erfani, S., Ma, X., Bailey, J., Chi, Y., Hua, X.-S.: $$\\alpha $$-IoU: a family of power intersection over union losses for bounding box regression. Adv. Neural. Inf. Process. Syst. 34, 20230\u201320242 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"issue":"6","key":"1803_CR10","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(6), 1\u201367 (2025)","journal-title":"Artif. Intell. Rev."},{"key":"1803_CR11","unstructured":"Jocher, G.: Yolov5 by ultralytics. GitHub Repository 1(1), 1\u201310 (2020). https:\/\/github.com\/ultralytics\/yolov5"},{"key":"1803_CR12","doi-asserted-by":"crossref","unstructured":"Kailath, T.: The divergence and bhattacharyya distance measures in signal selection. IEEE Trans. Commun. Technol. 15(1), 52\u201360 (1967). https:\/\/ieeexplore.ieee.org\/document\/1089532","DOI":"10.1109\/TCOM.1967.1089532"},{"key":"1803_CR13","unstructured":"Li, C., Li, L., Jiang, H., Weng, K., Geng, Y., Li, L., Ke, Z., Li, Q., Cheng, M., Nie, W., et al.: Yolov6: a single-stage object detection framework for industrial applications. arXiv preprint arXiv:2209.02976 (2022)"},{"key":"1803_CR14","doi-asserted-by":"crossref","unstructured":"Li, D., Hu, J., Wang, C., Li, X., She, Q., Zhu, L., Zhang, T., Chen, Q.: Involution: inverting the inherence of convolution for visual recognition. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 12321\u201312330 (2021)","DOI":"10.1109\/CVPR46437.2021.01214"},{"key":"1803_CR15","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017). https:\/\/openaccess.thecvf.com\/content_cvpr_2017\/papers\/Lin_Feature_Pyramid_Networks_CVPR_2017_paper.pdf","DOI":"10.1109\/CVPR.2017.106"},{"key":"1803_CR16","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: Proceedings of the IEEE international conference on computer vision, pp. 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"1803_CR17","doi-asserted-by":"crossref","unstructured":"Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C., Berg, A.: Ssd: single shot multibox detector. In: European Conference on Computer Vision (ECCV) (2016). https:\/\/arxiv.org\/abs\/1512.02325","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"1803_CR18","doi-asserted-by":"crossref","unstructured":"Liu, Y., Sun, P., Wergeles, N., Shang, Y.: A survey and performance evaluation of deep learning methods for small object detection. Expert Syst. Appl. 172, 114602 (2021). https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0957417421000439","DOI":"10.1016\/j.eswa.2021.114602"},{"key":"1803_CR19","doi-asserted-by":"crossref","unstructured":"Nielsen, F.: Generalized bhattacharyya and chernoff upper bounds on bayes error using quasi-arithmetic means. Pattern Recogn. Lett. 42, 25\u201334 (2014). https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0167865514000166","DOI":"10.1016\/j.patrec.2014.01.002"},{"key":"1803_CR20","doi-asserted-by":"crossref","unstructured":"Redmon, J., Farhadi, A.: Yolo9000: Better, faster, stronger. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 77(1), 6517\u20136525 (2017). https:\/\/arxiv.org\/abs\/1612.08242","DOI":"10.1109\/CVPR.2017.690"},{"key":"1803_CR21","unstructured":"Redmon, J., Farhadi, A.: Yolov3: an incremental improvement. arXiv preprint abs\/1804.02767 arxiv:abs\/1804.02767 (2018)"},{"key":"1803_CR22","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 (CVPR) (2016). https:\/\/www.academis.eu\/machine_learning\/_downloads\/51a67e9194f116abefff5192f683e3d8\/yolo.pdf"},{"key":"1803_CR23","doi-asserted-by":"crossref","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(6), 1137\u20131149 (2016). https:\/\/ieeexplore.ieee.org\/document\/7485869","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"1803_CR24","doi-asserted-by":"crossref","unstructured":"Rezatofighi, H., Tsoi, N., Gwak, J., Sadeghian, A., Reid, I., Savarese, S.: 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 (CVPR) (2019). https:\/\/arxiv.org\/abs\/1902.09630","DOI":"10.1109\/CVPR.2019.00075"},{"key":"1803_CR25","doi-asserted-by":"crossref","unstructured":"Singh, B., Davis, L.S.: An analysis of scale invariance in object detection snip. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 3578\u20133587 (2018)","DOI":"10.1109\/CVPR.2018.00377"},{"issue":"4","key":"1803_CR26","doi-asserted-by":"publisher","first-page":"1680","DOI":"10.3390\/make5040083","volume":"5","author":"J Terven","year":"2023","unstructured":"Terven, J., C\u00f3rdova-Esparza, D.-M., Romero-Gonz\u00e1lez, J.-A.: A comprehensive review of yolo architectures in computer vision: from yolov1 to yolov8 and yolo-nas. Mach. Learn. knowl. Extr. 5(4), 1680\u20131716 (2023)","journal-title":"Mach. Learn. knowl. Extr."},{"key":"1803_CR27","unstructured":"Tian, Y., Ye, Q., Doermann, D.: Yolov12: attention-centric real-time object detectors. arXiv preprint arXiv:2502.12524 (2025)"},{"key":"1803_CR28","doi-asserted-by":"crossref","unstructured":"Tong, K., Wu, Y., Zhou, F.: Recent advances in small object detection based on deep learning: a review. Image Vis. Comput. 97, 103910 (2020). https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0262885620300421","DOI":"10.1016\/j.imavis.2020.103910"},{"key":"1803_CR29","doi-asserted-by":"crossref","unstructured":"Wang, C.Y., Liao, H.Y.M., Wu, Y.H., Chen, PY., Hsieh, JW., Yeh, I.H.: Cspnet: a new backbone that can enhance learning capability of cnn. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. 390\u2013391 (2020). https:\/\/openaccess.thecvf.com\/content_CVPRW_2020\/html\/w28\/Wang_CSPNet_A_New_Backbone_That_Can_Enhance_Learning_Capability_of_CVPRW_2020_paper.html","DOI":"10.1109\/CVPRW50498.2020.00203"},{"key":"1803_CR30","doi-asserted-by":"crossref","unstructured":"Wang, C.-Y., Bochkovskiy, A., Liao, H.-Y.M.: 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 (2023)","DOI":"10.1109\/CVPR52729.2023.00721"},{"key":"1803_CR31","unstructured":"Wang, X., Yu, J., Zhu, X., Shen, W., Yang, W., Hu, K., Ling, H.: A wasserstein distance based loss function for object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020). https:\/\/openaccess.thecvf.com\/content_CVPRW_2020\/html\/w60\/Han_Wasserstein_Loss-Based_Deep_Object_Detection_CVPRW_2020_paper.html"},{"key":"1803_CR32","doi-asserted-by":"crossref","unstructured":"Xia, G.-S., Bai, X., Ding, J., Zhu, Z., Belongie, S., Luo, J., Datcu, M., Pelillo, M., Zhang, L.: Dota: a large-scale dataset for object detection in aerial images. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 3974\u20133983 (2018)","DOI":"10.1109\/CVPR.2018.00418"},{"key":"1803_CR33","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1016\/j.isprsjprs.2022.06.002","volume":"190","author":"C Xu","year":"2022","unstructured":"Xu, C., Wang, J., Yang, W., Yu, H., Yu, L., Xia, G.-S.: Detecting tiny objects in aerial images: a normalized wasserstein distance and a new benchmark. ISPRS J. Photogramm. Remote. Sens. 190, 79\u201393 (2022)","journal-title":"ISPRS J. Photogramm. Remote. Sens."},{"key":"1803_CR34","doi-asserted-by":"crossref","unstructured":"Yang, Y., Newsam, S.: Bag-of-visual-words and spatial extensions for land-use classification. In: Proceedings of the 18th SIGSPATIAL international conference on advances in geographic information systems, pp. 270\u2013279 (2010)","DOI":"10.1145\/1869790.1869829"},{"key":"1803_CR35","doi-asserted-by":"publisher","first-page":"146","DOI":"10.1016\/j.neucom.2022.07.042","volume":"506","author":"Y-F Zhang","year":"2022","unstructured":"Zhang, Y.-F., Ren, W., Zhang, Z., Jia, Z., Wang, L., Tan, T.: Focal and efficient iou loss for accurate bounding box regression. Neurocomputing 506, 146\u2013157 (2022)","journal-title":"Neurocomputing"},{"key":"1803_CR36","doi-asserted-by":"publisher","first-page":"155","DOI":"10.1016\/j.isprsjprs.2016.01.004","volume":"113","author":"W Zhao","year":"2016","unstructured":"Zhao, W., Du, S.: Learning multiscale and deep representations for classifying remotely sensed imagery. ISPRS J. Photogramm. Remote. Sens. 113, 155\u2013165 (2016)","journal-title":"ISPRS J. Photogramm. Remote. Sens."},{"key":"1803_CR37","doi-asserted-by":"crossref","unstructured":"Zheng, Z., Wang, P., Liu, W., Li, J., Ye, R., Ren, D.: Distance-iou loss: faster and better learning for bounding box regression. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 12993\u201313000 (2020)","DOI":"10.1609\/aaai.v34i07.6999"},{"issue":"8","key":"1803_CR38","doi-asserted-by":"publisher","first-page":"8574","DOI":"10.1109\/TCYB.2021.3095305","volume":"52","author":"Z Zheng","year":"2021","unstructured":"Zheng, Z., Wang, P., Ren, D., Liu, W., Ye, R., Hu, Q., Zuo, W.: Enhancing geometric factors in model learning and inference for object detection and instance segmentation. IEEE Trans. Cybern. 52(8), 8574\u20138586 (2021)","journal-title":"IEEE Trans. Cybern."}],"container-title":["Machine Vision and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00138-026-01803-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00138-026-01803-2","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00138-026-01803-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T14:30:49Z","timestamp":1778855449000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00138-026-01803-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,2]]},"references-count":38,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,5]]}},"alternative-id":["1803"],"URL":"https:\/\/doi.org\/10.1007\/s00138-026-01803-2","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-7359475\/v1","asserted-by":"object"}]},"ISSN":["0932-8092","1432-1769"],"issn-type":[{"value":"0932-8092","type":"print"},{"value":"1432-1769","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,2]]},"assertion":[{"value":"12 August 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 January 2026","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 February 2026","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 March 2026","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Data repository link will be added after peer review to preserve anonymity.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Code availability"}},{"value":"The authors declare no conflict of interest.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"The authors declare no conflict of interest.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"42"}}