{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T15:19:27Z","timestamp":1773415167243,"version":"3.50.1"},"reference-count":51,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2024,10,7]],"date-time":"2024-10-07T00:00:00Z","timestamp":1728259200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,7]],"date-time":"2024-10-07T00:00:00Z","timestamp":1728259200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100004739","name":"Youth Innovation Promotion Association of the Chinese Academy of Sciences","doi-asserted-by":"publisher","award":["Y202072"],"award-info":[{"award-number":["Y202072"]}],"id":[{"id":"10.13039\/501100004739","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int. J. Mach. Learn. & Cyber."],"published-print":{"date-parts":[[2025,3]]},"DOI":"10.1007\/s13042-024-02357-3","type":"journal-article","created":{"date-parts":[[2024,10,7]],"date-time":"2024-10-07T14:02:32Z","timestamp":1728309752000},"page":"1643-1660","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["YOLO-SDH: improved YOLOv5 using scaled decoupled head for object detection"],"prefix":"10.1007","volume":"16","author":[{"given":"Zhijie","family":"Ren","sequence":"first","affiliation":[]},{"given":"Kang","family":"Yao","sequence":"additional","affiliation":[]},{"given":"Silong","family":"Sheng","sequence":"additional","affiliation":[]},{"given":"Beibei","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Xianli","family":"Lang","sequence":"additional","affiliation":[]},{"given":"Dahang","family":"Wan","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7192-3118","authenticated-orcid":false,"given":"Weiwei","family":"Fu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,10,7]]},"reference":[{"issue":"7","key":"2357_CR1","doi-asserted-by":"publisher","first-page":"2542","DOI":"10.3390\/s22072542","volume":"22","author":"Z Wei","year":"2022","unstructured":"Wei Z, Zhang F, Chang S, Liu Y, Wu H, Feng Z (2022) MmWave radar and vision fusion for object detection in autonomous driving: a review. Sensors 22(7):2542","journal-title":"Sensors"},{"issue":"22","key":"2357_CR2","doi-asserted-by":"publisher","first-page":"9026","DOI":"10.3390\/s22229026","volume":"22","author":"J Woo","year":"2022","unstructured":"Woo J, Baek J-H, Jo S-H, Kim SY, Jeong J-H (2022) A study on object detection performance of YOLOv4 for autonomous driving of tram. Sensors 22(22):9026","journal-title":"Sensors"},{"key":"2357_CR3","doi-asserted-by":"publisher","DOI":"10.1016\/j.epsr.2022.108806","volume":"214","author":"X Li","year":"2023","unstructured":"Li X, Wang J, Lu Z, Cai Y (2023) A cloud edge computing method for economic dispatch of active distribution network with multi-microgrids. Electr Power Syst Res 214:108806","journal-title":"Electr Power Syst Res"},{"key":"2357_CR4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1155\/2022\/5863782","volume":"2022","author":"Y Shou","year":"2022","unstructured":"Shou Y, Meng T, Ai W, Xie C, Liu H, Wang Y (2022) Object detection in medical images based on hierarchical transformer and mask mechanism. Comput Intell Neurosci 2022:1\u201312","journal-title":"Comput Intell Neurosci"},{"key":"2357_CR5","doi-asserted-by":"crossref","unstructured":"Girshick R, Donahue J, Darrell T, Malik J (2014) Rich feature hierarchies for accurate object detection and semantic segmentation. arXiv:1311.2524","DOI":"10.1109\/CVPR.2014.81"},{"key":"2357_CR6","doi-asserted-by":"crossref","unstructured":"Girshick R (2015) Fast R-CNN. arXiv:1504.08083","DOI":"10.1109\/ICCV.2015.169"},{"key":"2357_CR7","doi-asserted-by":"publisher","unstructured":"Redmon J, Divvala S, Girshick R, Farhadi A (2016) You only look once: unified, real-time object detection. https:\/\/doi.org\/10.48550\/arXiv.1506.02640","DOI":"10.48550\/arXiv.1506.02640"},{"key":"2357_CR8","doi-asserted-by":"crossref","unstructured":"Liu W, Anguelov D, Erhan D, Szegedy C, Reed S, Fu C-Y, Berg AC (2016) SSD: single shot MultiBox detector, vol 9905. arXiv:1512.02325","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"2357_CR9","doi-asserted-by":"crossref","unstructured":"Redmon J, Farhadi A (2016) YOLO9000: better, faster, stronger. arXiv:1612.08242","DOI":"10.1109\/CVPR.2017.690"},{"key":"2357_CR10","doi-asserted-by":"publisher","unstructured":"Redmon J, Farhadi A (2018) YOLOv3: an incremental improvement. https:\/\/doi.org\/10.48550\/arXiv.1804.02767","DOI":"10.48550\/arXiv.1804.02767"},{"key":"2357_CR11","unstructured":"Bochkovskiy A, Wang C-Y, Liao H-YM (2020) YOLOv4: optimal speed and accuracy of object detection. arXiv:2004.10934"},{"key":"2357_CR12","unstructured":"Ultralytics: YOLOv5 (2020) https:\/\/github.com\/ultralytics\/yolov5. Accessed 1 Sept 2022"},{"key":"2357_CR13","unstructured":"Li C, Li L, Jiang H, Weng K, Geng Y, Li L, Ke Z, Li Q, Cheng M, Nie W, Li Y, Zhang B, Liang Y, Zhou L, Xu X, Chu X, Wei X, Wei X. YOLOv6: a single-stage object detection framework for industrial applications. arXiv:2209.02976"},{"key":"2357_CR14","doi-asserted-by":"crossref","unstructured":"Wang C-Y, Bochkovskiy A, Liao H-YM (2022) YOLOv7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. arXiv:2207.02696","DOI":"10.1109\/CVPR52729.2023.00721"},{"key":"2357_CR15","unstructured":"Ultralytics: YOLOv8 (2023) https:\/\/github.com\/ultralytics\/ultralytics. Accessed 1 Apr 2023"},{"key":"2357_CR16","doi-asserted-by":"publisher","unstructured":"Ge Z, Liu S, Wang F, Li Z, Sun J (2021) YOLOX: exceeding YOLO series in 2021. https:\/\/doi.org\/10.48550\/arXiv.2107.08430","DOI":"10.48550\/arXiv.2107.08430"},{"key":"2357_CR17","unstructured":"Benjumea A, Teeti I, Cuzzolin F, Bradley A (2021) YOLO-Z: improving small object detection in YOLOv5 for autonomous vehicles. arXiv:2112.11798"},{"issue":"2","key":"2357_CR18","doi-asserted-by":"publisher","first-page":"2083","DOI":"10.1007\/s40747-023-01256-4","volume":"10","author":"Y Wan","year":"2024","unstructured":"Wan Y, Li J (2024) LGP-YOLO: an efficient convolutional neural network for surface defect detection of light guide plate. Complex Intell Syst 10(2):2083\u20132105. https:\/\/doi.org\/10.1007\/s40747-023-01256-4","journal-title":"Complex Intell Syst"},{"key":"2357_CR19","doi-asserted-by":"publisher","unstructured":"Howard AG, Zhu M, Chen B, Kalenichenko D, Wang W, Weyand T, Andreetto M, Adam H (2017) MobileNets: efficient convolutional neural networks for mobile vision applications.https:\/\/doi.org\/10.48550\/arXiv.1704.04861","DOI":"10.48550\/arXiv.1704.04861"},{"key":"2357_CR20","doi-asserted-by":"publisher","unstructured":"Sandler M, Howard A, Zhu M, Zhmoginov A, Chen L-C (2019) MobileNetV2: inverted residuals and linear bottlenecks. https:\/\/doi.org\/10.48550\/arXiv.1801.04381","DOI":"10.48550\/arXiv.1801.04381"},{"key":"2357_CR21","doi-asserted-by":"publisher","unstructured":"Howard A, Sandler M, Chu G, Chen L-C, Chen B, Tan M, Wang W, Zhu Y, Pang R, Vasudevan V, Le QV, Adam H (2019) Searching for MobileNetV3. https:\/\/doi.org\/10.48550\/arXiv.1905.02244","DOI":"10.48550\/arXiv.1905.02244"},{"key":"2357_CR22","doi-asserted-by":"crossref","unstructured":"Zhang X, Zhou X, Lin M, Sun J (2017) ShuffleNet: an extremely efficient convolutional neural network for mobile devices. arXiv:1707.01083","DOI":"10.1109\/CVPR.2018.00716"},{"key":"2357_CR23","doi-asserted-by":"crossref","unstructured":"Ma N, Zhang X, Zheng H-T, Sun J (2018) ShuffleNet V2: practical guidelines for efficient CNN architecture design. arXiv:1801.04381","DOI":"10.1007\/978-3-030-01264-9_8"},{"key":"2357_CR24","doi-asserted-by":"publisher","unstructured":"Hou Q, Zhou D, Feng J (2021) Coordinate attention for efficient mobile network design. https:\/\/doi.org\/10.48550\/arXiv.2103.02907","DOI":"10.48550\/arXiv.2103.02907"},{"key":"2357_CR25","doi-asserted-by":"crossref","unstructured":"Ghiasi G, Lin T-Y, Pang R, Le QV (2019) NAS-FPN: learning scalable feature pyramid architecture for object detection. arXiv:1904.07392","DOI":"10.1109\/CVPR.2019.00720"},{"key":"2357_CR26","unstructured":"Liu S, Huang D, Wang Y (2019) Learning spatial fusion for single-shot object detection. arXiv:1911.09516"},{"key":"2357_CR27","doi-asserted-by":"publisher","unstructured":"Cristianini N, Ricci E (2008) Support vector machines. In: Kao M-Y (ed). Springer, US. pp. 928\u2013932. https:\/\/doi.org\/10.1007\/978-0-387-30162-4_415","DOI":"10.1007\/978-0-387-30162-4_415"},{"key":"2357_CR28","doi-asserted-by":"publisher","unstructured":"He K, Zhang X, Ren S, Sun J (2014) Spatial pyramid pooling in deep convolutional networks for visual recognition. 8691:346\u2013361. https:\/\/doi.org\/10.1007\/978-3-319-10578-9_23. arXiv:1406.4729","DOI":"10.1007\/978-3-319-10578-9_23"},{"issue":"6","key":"2357_CR29","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2017","unstructured":"Ren S, He K, Girshick R, Sun J (2017) Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans Pattern Anal Mach Intell 39(6):1137\u20131149. https:\/\/doi.org\/10.1109\/TPAMI.2016.2577031","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2357_CR30","doi-asserted-by":"crossref","unstructured":"Cai Z, Vasconcelos N (2017) Cascade R-CNN: delving into high quality object detection. arXiv:1712.00726","DOI":"10.1109\/CVPR.2018.00644"},{"key":"2357_CR31","doi-asserted-by":"crossref","unstructured":"Chen Q, Wang Y, Yang T, Zhang X, Cheng J, Sun J (2021) You only look one-level feature. arXiv:2103.09460","DOI":"10.1109\/CVPR46437.2021.01284"},{"key":"2357_CR32","doi-asserted-by":"crossref","unstructured":"Tian Z, Shen C, Chen H, He T (2019) FCOS: fully convolutional one-stage object detection. arXiv:1904.01355","DOI":"10.1109\/ICCV.2019.00972"},{"key":"2357_CR33","doi-asserted-by":"crossref","unstructured":"Erhan D, Szegedy C, Toshev A, Anguelov D (2013) Scalable object detection using deep neural networks. arXiv:1312.2249","DOI":"10.1109\/CVPR.2014.276"},{"key":"2357_CR34","doi-asserted-by":"crossref","unstructured":"Duan K, Bai S, Xie L, Qi H, Huang Q, Tian Q (2019) CenterNet: keypoint triplets for object detection. arXiv:1904.08189","DOI":"10.1109\/ICCV.2019.00667"},{"key":"2357_CR35","unstructured":"Law H, Deng J. CornerNet: detecting objects as paired keypoints"},{"key":"2357_CR36","doi-asserted-by":"publisher","first-page":"384","DOI":"10.1016\/j.neucom.2019.06.032","volume":"359","author":"W Chen","year":"2019","unstructured":"Chen W, Shi K (2019) A deep learning framework for time series classification using relative position matrix and convolutional neural network. Neurocomputing 359:384\u2013394","journal-title":"Neurocomputing"},{"issue":"10","key":"2357_CR37","doi-asserted-by":"publisher","first-page":"13715","DOI":"10.1007\/s12652-022-04025-2","volume":"14","author":"EH Hssayni","year":"2023","unstructured":"Hssayni EH, Joudar N-E, Ettaouil M (2023) Localization and reduction of redundancy in CNN using L1-sparsity induction. J Ambient Intell Human Comput 14(10):13715\u201313727. https:\/\/doi.org\/10.1007\/s12652-022-04025-2","journal-title":"J Ambient Intell Human Comput"},{"issue":"11","key":"2357_CR38","doi-asserted-by":"publisher","first-page":"5358","DOI":"10.3390\/s23115358","volume":"23","author":"B Janakiraman","year":"2023","unstructured":"Janakiraman B, Shanmugam S, P\u00e9rez De Prado R, Wozniak M (2023) 3D road lane classification with improved texture patterns and optimized deep classifier. Sensors 23(11):5358","journal-title":"Sensors"},{"issue":"3","key":"2357_CR39","doi-asserted-by":"publisher","first-page":"1501","DOI":"10.3390\/s23031501","volume":"23","author":"W Si\u0142ka","year":"2023","unstructured":"Si\u0142ka W, Wieczorek M, Si\u0142ka J, Wo\u017aniak M (2023) Malaria detection using advanced deep learning architecture. Sensors 23(3):1501","journal-title":"Sensors"},{"key":"2357_CR40","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.109567","volume":"253","author":"EH Hssayni","year":"2022","unstructured":"Hssayni EH, Joudar N-E, Ettaouil M (2022) An adaptive drop method for deep neural networks regularization: estimation of dropconnect hyperparameter using generalization gap. Knowl Bases Syst 253:109567","journal-title":"Knowl Bases Syst"},{"key":"2357_CR41","doi-asserted-by":"crossref","unstructured":"Zhu X, Hu H, Lin S, Dai J (2018) Deformable ConvNets v2: more deformable, better results. arXiv:1811.11168","DOI":"10.1109\/CVPR.2019.00953"},{"key":"2357_CR42","doi-asserted-by":"crossref","unstructured":"Zheng Z, Wang P, Liu W, Li J, Ye R, Ren D (2019) Distance-IoU loss: faster and better learning for bounding box regression. arXiv:1911.08287","DOI":"10.1609\/aaai.v34i07.6999"},{"key":"2357_CR43","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1155\/2021\/5592878","volume":"2021","author":"W Zhao","year":"2021","unstructured":"Zhao W, Chen F, Huang H, Li D, Cheng W (2021) A new steel defect detection algorithm based on deep learning. Comput Intell Neurosci 2021:1\u201313. https:\/\/doi.org\/10.1155\/2021\/5592878","journal-title":"Comput Intell Neurosci"},{"issue":"1","key":"2357_CR44","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1007\/s11263-014-0733-5","volume":"111","author":"M Everingham","year":"2015","unstructured":"Everingham M, Eslami SMA, Van Gool L, Williams CKI, Winn J, Zisserman A (2015) The Pascal visual object classes challenge: a retrospective. Int J Comput Vis 111(1):98\u2013136. https:\/\/doi.org\/10.1007\/s11263-014-0733-5","journal-title":"Int J Comput Vis"},{"key":"2357_CR45","doi-asserted-by":"crossref","unstructured":"Li K, Wan G, Cheng G, Meng L, Han J (2020) Object detection in optical remote sensing images: a survey and a new benchmark. ISPRS J Photogramm Remote Sens 159 (2020) arXiv:1909.00133","DOI":"10.1016\/j.isprsjprs.2019.11.023"},{"key":"2357_CR46","doi-asserted-by":"crossref","unstructured":"Ren S, He K, Girshick R, Sun J (2016) Faster R-CNN: towards real-time object detection with region proposal networks. arXiv:1506.01497","DOI":"10.1109\/TPAMI.2016.2577031"},{"issue":"3","key":"2357_CR47","doi-asserted-by":"publisher","first-page":"614","DOI":"10.3390\/rs15030614","volume":"15","author":"D Wan","year":"2023","unstructured":"Wan D, Lu R, Wang S, Shen S, Xu T, Lang X (2023) YOLO-HR: improved YOLOv5 for object detection in high-resolution optical remote sensing images. Remote Sens 15(3):614. https:\/\/doi.org\/10.3390\/rs15030614","journal-title":"Remote Sens"},{"key":"2357_CR48","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2022.105628","volume":"117","author":"Y Zhang","year":"2023","unstructured":"Zhang Y, Wang W, Li Z, Shu S, Lang X, Zhang T, Dong J (2023) Development of a cross-scale weighted feature fusion network for hot-rolled steel surface defect detection. Eng Appl Artif Intell 117:105628. https:\/\/doi.org\/10.1016\/j.engappai.2022.105628","journal-title":"Eng Appl Artif Intell"},{"key":"2357_CR49","doi-asserted-by":"crossref","unstructured":"Zhu X, Lyu S, Wang X, Zhao Q (2021) TPH-YOLOv5: improved YOLOv5 based on transformer prediction head for object detection on drone-captured scenarios. arXiv:2108.11539","DOI":"10.1109\/ICCVW54120.2021.00312"},{"key":"2357_CR50","doi-asserted-by":"publisher","DOI":"10.1016\/j.measurement.2023.112776","volume":"214","author":"C Zhao","year":"2023","unstructured":"Zhao C, Shu X, Yan X, Zuo X, Zhu F (2023) RDD-YOLO: a modified YOLO for detection of steel surface defects. Measurement 214:112776 (https:\/\/www.sciencedirect.com\/science\/article\/abs\/2023.112776)","journal-title":"Measurement"},{"key":"2357_CR51","doi-asserted-by":"crossref","unstructured":"Yang Z, Liu S, Hu H, Wang L, Lin S (2019) RepPoints: point set representation for object detection. arXiv:1904.11490","DOI":"10.1109\/ICCV.2019.00975"}],"container-title":["International Journal of Machine Learning and Cybernetics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13042-024-02357-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s13042-024-02357-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13042-024-02357-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,19]],"date-time":"2025-02-19T18:27:20Z","timestamp":1739989640000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s13042-024-02357-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,7]]},"references-count":51,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2025,3]]}},"alternative-id":["2357"],"URL":"https:\/\/doi.org\/10.1007\/s13042-024-02357-3","relation":{},"ISSN":["1868-8071","1868-808X"],"issn-type":[{"value":"1868-8071","type":"print"},{"value":"1868-808X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,7]]},"assertion":[{"value":"23 August 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 July 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 October 2024","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 the following financial interests\/personal relationships which may be considered as potential conflict of interest: WeiWei Fu reports financial support was provided by Youth Innovation Promotion Association of Chinese Academy of Sciences (No. Y202072).","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}