{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,28]],"date-time":"2026-10-28T20:54:24Z","timestamp":1793220864944,"version":"4.5.0"},"reference-count":50,"publisher":"Springer Science and Business Media LLC","issue":"7","license":[{"start":{"date-parts":[[2024,6,6]],"date-time":"2024-06-06T00:00:00Z","timestamp":1717632000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,6,6]],"date-time":"2024-06-06T00:00:00Z","timestamp":1717632000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["3132019344"],"award-info":[{"award-number":["3132019344"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Leading Scholar Grant, Dalian Maritime University","award":["00253007"],"award-info":[{"award-number":["00253007"]}],"id":[{"id":"https:\/\/ror.org\/002b7nr53","id-type":"ROR","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Artif Intell Rev"],"abstract":"Abstract<\/jats:title>\n \n The practical application of object detection inevitably encounters challenges posed by small objects. In underwater object detection, a crucial method for marine exploration, the presence of small objects in underwater environments significantly hampers the performance of detection. In this paper, a dynamic YOLO detector is proposed as a solution to alleviate this problem. Specifically, a light-weight backbone network is first constructed based on deformable convolution v3, with some specialized designs for small object detection. Secondly, a unified feature fusion framework based on channel-wise, scale-wise, and spatial-aware attention is proposed to fuse feature maps from different scales. This is particularly critical for detecting small objects since it allows us to fully exploit the enhanced capabilities offered by our proposed backbone network. Finally, a simple but effective detection head is designed to handle the conflict between classification and localization by disentangling and aligning the two tasks. Extensive experiments are conducted on benchmark datasets to demonstrate the effectiveness of the proposed model. Without bells and whistles, dynamic YOLO outperforms the recent state-of-the-art methods by a large margin of\n \n \n $$+\\,0.8$$<\/jats:tex-math>\n \n \n +<\/mml:mo>\n \n 0.8<\/mml:mn>\n <\/mml:mrow>\n <\/mml:math>\n <\/jats:alternatives>\n <\/jats:inline-formula>\n \u00a0AP and\n \n \n $$+\\,1.8$$<\/jats:tex-math>\n \n \n +<\/mml:mo>\n \n 1.8<\/mml:mn>\n <\/mml:mrow>\n <\/mml:math>\n <\/jats:alternatives>\n <\/jats:inline-formula>\n \u00a0\n \n \n $$\\text {AP}_{S}$$<\/jats:tex-math>\n \n \n AP<\/mml:mtext>\n S<\/mml:mi>\n <\/mml:msub>\n <\/mml:math>\n <\/jats:alternatives>\n <\/jats:inline-formula>\n on the DUO dataset. Experimental results on Pascal VOC and MS COCO datasets also demonstrate the superiority of the proposed method. At last, ablation studies are conducted on DUO dataset to validate the effectiveness and efficiency of each design in dynamic YOLO. Source code will be available at\n https:\/\/github.com\/chenjie04\/Dynamic-YOLO<\/jats:ext-link>\n .\n <\/jats:p>","DOI":"10.1007\/s10462-024-10788-1","type":"journal-article","created":{"date-parts":[[2024,6,5]],"date-time":"2024-06-05T23:49:42Z","timestamp":1717631382000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":121,"title":["Dynamic YOLO for small underwater object detection"],"prefix":"10.1007","volume":"57","author":[{"given":"Jie","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Meng Joo","family":"Er","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,6,6]]},"reference":[{"key":"10788_CR1","doi-asserted-by":"crossref","unstructured":"Cai Z, Vasconcelos N (2018) 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":"10788_CR2","unstructured":"Chen K, Wang J, Pang J et\u00a0al (2019) MMDetection: open MMLAB detection toolbox and benchmark. arXiv preprint. arXiv:1906.07155"},{"issue":"2","key":"10788_CR3","doi-asserted-by":"publisher","first-page":"936","DOI":"10.1109\/TSMC.2020.3005231","volume":"52","author":"G Chen","year":"2020","unstructured":"Chen G, Wang H, Chen K et al (2020a) A survey of the four pillars for small object detection: multiscale representation, contextual information, super-resolution, and region proposal. IEEE Trans Syst Man Cybern Syst 52(2):936\u2013953","journal-title":"IEEE Trans Syst Man Cybern Syst"},{"key":"10788_CR4","doi-asserted-by":"crossref","unstructured":"Chen Y, Dai X, Liu M et\u00a0al (2020b) Dynamic ReLu. In: Proceedings of the European conference on computer vision. Springer, Cham, pp 351\u2013367","DOI":"10.1007\/978-3-030-58529-7_21"},{"key":"10788_CR5","doi-asserted-by":"crossref","unstructured":"Dai J, Qi H, Xiong Y et\u00a0al (2017) Deformable convolutional networks. In: Proceedings of the IEEE international conference on computer vision, pp 764\u2013773","DOI":"10.1109\/ICCV.2017.89"},{"key":"10788_CR6","doi-asserted-by":"crossref","unstructured":"Dai X, Chen Y, Xiao B et\u00a0al (2021) Dynamic head: unifying object detection heads with attentions. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 7373\u20137382","DOI":"10.1109\/CVPR46437.2021.00729"},{"key":"10788_CR7","doi-asserted-by":"publisher","unstructured":"Er MJ, Chen J, Zhang Y (2022) Marine robotics 4.0: present and future of real-time detection techniques for underwater objects. In: Industry 4.0\u2014perspectives and applications. IntechOpen, London. https:\/\/doi.org\/10.5772\/intechopen.107409","DOI":"10.5772\/intechopen.107409"},{"issue":"4","key":"10788_CR8","doi-asserted-by":"publisher","first-page":"1990","DOI":"10.3390\/s23041990","volume":"23","author":"MJ Er","year":"2023","unstructured":"Er MJ, Chen J, Zhang Y et al (2023) Research challenges, recent advances, and popular datasets in deep learning-based underwater marine object detection: a review. Sensors 23(4):1990","journal-title":"Sensors"},{"issue":"2","key":"10788_CR9","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","volume":"88","author":"M Everingham","year":"2010","unstructured":"Everingham M, Van Gool L, Williams CKI et al (2010) The pascal visual object classes (voc) challenge. Int J Comput Vision 88(2):303\u2013338","journal-title":"Int J Comput Vision"},{"issue":"15","key":"10788_CR10","doi-asserted-by":"publisher","first-page":"20871","DOI":"10.1007\/s11042-022-12502-1","volume":"81","author":"S Fayaz","year":"2022","unstructured":"Fayaz S, Parah SA, Qureshi G (2022) Underwater object detection: architectures and algorithms\u2014a comprehensive review. Multimedia Tools Appl 81(15):20871\u201320916","journal-title":"Multimedia Tools Appl"},{"key":"10788_CR11","doi-asserted-by":"crossref","unstructured":"Feng C, Zhong Y, Gao Y et\u00a0al (2021) TOOD: task-aligned one-stage object detection. In: Proceedings of the IEEE\/CVF international conference on computer vision (ICCV), pp 3490\u20133499","DOI":"10.1109\/ICCV48922.2021.00349"},{"key":"10788_CR12","doi-asserted-by":"crossref","unstructured":"Fu J, Liu J, Tian H et\u00a0al (2019) Dual attention network for scene segmentation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 3146\u20133154","DOI":"10.1109\/CVPR.2019.00326"},{"key":"10788_CR13","unstructured":"Ge Z, Liu S, Wang F et\u00a0al (2021) YOLOX: exceeding yolo series in 2021. arXiv preprint. arXiv:2107.08430"},{"key":"10788_CR14","doi-asserted-by":"crossref","unstructured":"Ghiasi G, Lin TY, Le QV (2019) NAS-FPN: learning scalable feature pyramid architecture for object detection. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 7036\u20137045","DOI":"10.1109\/CVPR.2019.00720"},{"key":"10788_CR15","doi-asserted-by":"publisher","unstructured":"Glenn J, Ayush C, Alex S et\u00a0al (2022) ultralytics\/yolov5: v7.0\u2014YOLOv5 SOTA realtime instance segmentation. https:\/\/doi.org\/10.5281\/zenodo.7347926","DOI":"10.5281\/zenodo.7347926"},{"issue":"3","key":"10788_CR16","doi-asserted-by":"publisher","first-page":"331","DOI":"10.1007\/s41095-022-0271-y","volume":"8","author":"MH Guo","year":"2022","unstructured":"Guo MH, Xu TX, Liu JJ et al (2022) Attention mechanisms in computer vision: a survey. Comput Vis Media 8(3):331\u2013368","journal-title":"Comput Vis Media"},{"issue":"1","key":"10788_CR17","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1109\/TPAMI.2022.3152247","volume":"45","author":"K Han","year":"2022","unstructured":"Han K, Wang Y, Chen H et al (2022) A survey on vision transformer. IEEE Trans Pattern Anal Mach Intell 45(1):87\u2013110","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"10788_CR18","doi-asserted-by":"crossref","unstructured":"Hu J, Shen L, Sun G (2018) Squeeze-and-excitation networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 7132\u20137141","DOI":"10.1109\/CVPR.2018.00745"},{"key":"10788_CR19","unstructured":"Huang T, Huang L, You S et\u00a0al (2022) LightViT: towards light-weight convolution-free vision transformers. arXiv preprint. arXiv:2207.05557"},{"key":"10788_CR20","unstructured":"Jocher G, Chaurasia A, Qiu J (2023) YOLO by ultralytics. https:\/\/github.com\/ultralytics\/ultralytics"},{"key":"10788_CR21","unstructured":"Li C, Li L, Jiang H et\u00a0al (2022) YOLOv6: a single-stage object detection framework for industrial applications. arXiv preprint. arXiv:2209.02976"},{"key":"10788_CR22","first-page":"21002","volume":"33","author":"X Li","year":"2020","unstructured":"Li X, Wang W, Wu L et al (2020) Generalized focal loss: learning qualified and distributed bounding boxes for dense object detection. Adv Neural Inf Process Syst 33:21002\u201321012","journal-title":"Adv Neural Inf Process Syst"},{"issue":"9","key":"10788_CR23","doi-asserted-by":"publisher","first-page":"3031","DOI":"10.3390\/s21093031","volume":"21","author":"J Lian","year":"2021","unstructured":"Lian J, Yin Y, Li L et al (2021) Small object detection in traffic scenes based on attention feature fusion. Sensors 21(9):3031","journal-title":"Sensors"},{"key":"10788_CR24","doi-asserted-by":"crossref","unstructured":"Lin TY, Maire M, Belongie SJ et\u00a0al (2014) Microsoft COCO: common objects in context. In: Proceedings of the European conference on computer vision, pp 740\u2013755","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"10788_CR25","doi-asserted-by":"crossref","unstructured":"Lin TY, Doll\u00e1r P, Girshick R et\u00a0al (2017a) Feature pyramid networks for object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2117\u20132125","DOI":"10.1109\/CVPR.2017.106"},{"key":"10788_CR26","doi-asserted-by":"crossref","unstructured":"Lin TY, Goyal P, Girshick R et\u00a0al (2017b) 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":"10788_CR27","doi-asserted-by":"crossref","unstructured":"Liu C, Li H, Wang S et\u00a0al (2021a) A dataset and benchmark of underwater object detection for robot picking. In: Proceedings of the IEEE international conference on multimedia & expo workshops (ICMEW), pp 1\u20136","DOI":"10.1109\/ICMEW53276.2021.9455997"},{"key":"10788_CR28","doi-asserted-by":"crossref","unstructured":"Liu S, Qi L, Qin H et\u00a0al (2018) Path aggregation network for instance segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 8759\u20138768","DOI":"10.1109\/CVPR.2018.00913"},{"key":"10788_CR29","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2021.114602","volume":"172","author":"Y Liu","year":"2021","unstructured":"Liu Y, Sun P, Wergeles N et al (2021) A survey and performance evaluation of deep learning methods for small object detection. Expert Syst Appl 172:114602","journal-title":"Expert Syst Appl"},{"key":"10788_CR30","unstructured":"Lyu C, Zhang W, Huang H et\u00a0al (2022) RTMDet: an empirical study of designing real-time object detectors. arXiv preprint. arXiv:2212.07784"},{"key":"10788_CR31","unstructured":"MMYOLO Contributors (2022) MMYOLO: OpenMMLab YOLO series toolbox and benchmark. https:\/\/github.com\/open-mmlab\/mmyolo"},{"key":"10788_CR32","doi-asserted-by":"crossref","unstructured":"Qin X, Wang Z, Bai Y et\u00a0al (2020) FFA-Net: feature fusion attention network for single image dehazing. In: Proceedings of the AAAI conference on artificial intelligence, pp 11908\u201311915","DOI":"10.1609\/aaai.v34i07.6865"},{"key":"10788_CR33","unstructured":"Redmon J, Farhadi A (2018) YOLOv3: an incremental improvement. arXiv preprint. arXiv:1804.02767"},{"key":"10788_CR34","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2015","unstructured":"Ren S, He K, Girshick RB et al (2015) Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans Pattern Anal Mach Intell 39:1137\u20131149","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"10788_CR35","doi-asserted-by":"crossref","unstructured":"Rezatofighi H, Tsoi N, Gwak J et\u00a0al (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":"10788_CR36","doi-asserted-by":"crossref","unstructured":"Song G, Liu Y, Wang X (2020) Revisiting the sibling head in object detector. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 11563\u201311572","DOI":"10.1109\/CVPR42600.2020.01158"},{"key":"10788_CR37","doi-asserted-by":"publisher","first-page":"3311","DOI":"10.1007\/s10489-020-01949-0","volume":"51","author":"C Sun","year":"2021","unstructured":"Sun C, Ai Y, Wang S et al (2021) Mask-guided SSD for small-object detection. Appl Intell 51:3311\u20133322","journal-title":"Appl Intell"},{"key":"10788_CR38","doi-asserted-by":"crossref","unstructured":"Tan M, Pang R, Le QV (2020) EfficientDet: scalable and efficient object detection. In: Proceedings of the IEEE\/CVF Conference on computer vision and pattern recognition, pp 10781\u201310790","DOI":"10.1109\/CVPR42600.2020.01079"},{"issue":"6","key":"10788_CR39","doi-asserted-by":"crossref","first-page":"172988142097630","DOI":"10.1177\/1729881420976307","volume":"17","author":"B Teng","year":"2020","unstructured":"Teng B, Zhao H (2020) Underwater target recognition methods based on the framework of deep learning: a survey. Int J Adv Rob Syst 17(6):1729881420976307","journal-title":"Int J Adv Rob Syst"},{"key":"10788_CR40","doi-asserted-by":"crossref","unstructured":"Tian Z, Shen C, Chen H et\u00a0al (2019) FCOS: fully convolutional one-stage object detection. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 9627\u20139636","DOI":"10.1109\/ICCV.2019.00972"},{"key":"10788_CR41","unstructured":"Vaswani A, Shazeer N, Parmar N et\u00a0al (2017) Attention is all you need. In: Proceedings of the Advances in neural information processing systems"},{"key":"10788_CR42","doi-asserted-by":"crossref","unstructured":"Wang W, Dai J, Chen Z et\u00a0al (2022) InternImage: exploring large-scale vision foundation models with deformable convolutions. arXiv preprint. arXiv:2211.05778","DOI":"10.1109\/CVPR52729.2023.01385"},{"key":"10788_CR43","doi-asserted-by":"crossref","unstructured":"Wang CY, Bochkovskiy A, Liao HYM (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":"10788_CR44","doi-asserted-by":"crossref","unstructured":"Wu Y, Chen Y, Yuan L et\u00a0al (2020) Rethinking classification and localization for object detection. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 10186\u201310195","DOI":"10.1109\/CVPR42600.2020.01020"},{"key":"10788_CR45","doi-asserted-by":"crossref","unstructured":"Wu H, Xiao B, Codella N et\u00a0al (2021) CvT: introducing convolutions to vision transformers. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 22\u201331","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"10788_CR46","unstructured":"Xu S, Wang X, Lv W et\u00a0al (2022) PP-YOLOE: an evolved version of yolo. arXiv preprint. arXiv:2203.16250"},{"key":"10788_CR47","doi-asserted-by":"publisher","first-page":"204","DOI":"10.1016\/j.neucom.2023.01.056","volume":"527","author":"S Xu","year":"2023","unstructured":"Xu S, Zhang M, Song W et al (2023) A systematic review and analysis of deep learning-based underwater object detection. Neurocomputing 527:204\u2013232","journal-title":"Neurocomputing"},{"key":"10788_CR48","doi-asserted-by":"crossref","unstructured":"Yang Z, Liu S, Hu H et\u00a0al (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":"10788_CR49","doi-asserted-by":"crossref","unstructured":"Zhang S, Chi C, Yao Y et\u00a0al (2020) Bridging 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":"10788_CR50","doi-asserted-by":"crossref","unstructured":"Zhu X, Hu H, Lin S et\u00a0al (2019) Deformable ConvNets V2: more deformable, better results. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 9308\u20139316","DOI":"10.1109\/CVPR.2019.00953"}],"container-title":["Artificial Intelligence Review"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10462-024-10788-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10462-024-10788-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10462-024-10788-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T06:08:22Z","timestamp":1721023702000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10462-024-10788-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,6]]},"references-count":50,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2024,7]]}},"alternative-id":["10788"],"URL":"https:\/\/doi.org\/10.1007\/s10462-024-10788-1","relation":{},"ISSN":["1573-7462"],"issn-type":[{"value":"1573-7462","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,6,6]]},"assertion":[{"value":"5 May 2024","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 June 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 no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"165"}}