{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T21:35:21Z","timestamp":1782423321025,"version":"3.54.5"},"reference-count":58,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100004735","name":"Natural Science Foundation of Hunan Province","doi-asserted-by":"publisher","award":["2026JJ60168"],"award-info":[{"award-number":["2026JJ60168"]}],"id":[{"id":"10.13039\/501100004735","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004735","name":"Natural Science Foundation of Hunan Province","doi-asserted-by":"publisher","award":["2024JJ8367"],"award-info":[{"award-number":["2024JJ8367"]}],"id":[{"id":"10.13039\/501100004735","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004832","name":"Changsha University of Science and Technology","doi-asserted-by":"publisher","award":["2025ZKPT057"],"award-info":[{"award-number":["2025ZKPT057"]}],"id":[{"id":"10.13039\/501100004832","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neurocomputing"],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1016\/j.neucom.2026.133714","type":"journal-article","created":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T23:19:50Z","timestamp":1776467990000},"page":"133714","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":1,"special_numbering":"C","title":["YOSAM2: A lightweight framework for joint underwater instance segmentation and benchmarking on the DSUO dataset"],"prefix":"10.1016","volume":"686","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-5312-8533","authenticated-orcid":false,"given":"Zhicheng","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5671-8551","authenticated-orcid":false,"given":"Bin","family":"Chu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhipan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nan","family":"Wei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weijie","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neucom.2026.133714_bib0005","doi-asserted-by":"crossref","first-page":"145","DOI":"10.1016\/j.oceaneng.2019.04.011","article-title":"Advancements in the field of autonomous underwater vehicle","volume":"181","author":"Sahoo","year":"2019","journal-title":"Ocean Eng."},{"key":"10.1016\/j.neucom.2026.133714_bib0010","doi-asserted-by":"crossref","first-page":"1077","DOI":"10.1016\/j.scitotenv.2018.04.049","article-title":"Eyes in the sea: unlocking the mysteries of the ocean using industrial, remotely operated vehicles (rovs)","volume":"634","author":"Macreadie","year":"2018","journal-title":"Sci. Total Environ."},{"key":"10.1016\/j.neucom.2026.133714_bib0015","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"6723","article-title":"A revised underwater image formation model","author":"Akkaynak","year":"2018"},{"key":"10.1016\/j.neucom.2026.133714_bib0020","article-title":"Samrs: scaling-up remote sensing segmentation dataset with segment anything model","volume":"36","author":"Wang","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.133714_bib0025","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"4015","article-title":"Segment anything","author":"Kirillov","year":"2023"},{"key":"10.1016\/j.neucom.2026.133714_bib0030","author":"Ravi"},{"key":"10.1016\/j.neucom.2026.133714_bib0035","article-title":"Hismamba: positive noise guided structural\u2013color collaborative modeling for underwater image enhancement","author":"Ma","year":"2025","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neucom.2026.133714_bib0040","doi-asserted-by":"crossref","first-page":"3640","DOI":"10.1109\/JSTARS.2024.3522202","article-title":"Sustainable environmental monitoring: multistage fusion algorithm for remotely sensed underwater super-resolution image enhancement and classification","volume":"18","author":"Ghaban","year":"2024","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"10.1016\/j.neucom.2026.133714_bib0045","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2025.131582","article-title":"Waterbox: weakly supervised underwater instance segmentation and a new benchmark","volume":"657","author":"Wu","year":"2025","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neucom.2026.133714_bib0050","doi-asserted-by":"crossref","DOI":"10.1016\/j.apor.2024.104356","article-title":"Semi-supervised learning network for deep-sea nodule mineral image segmentation","volume":"154","author":"Ding","year":"2025","journal-title":"Appl. Ocean Res."},{"key":"10.1016\/j.neucom.2026.133714_bib0055","series-title":"2024 International Conference on Machine Learning and Applications (ICMLA)","first-page":"1404","article-title":"Edge-centric real-time segmentation for autonomous underwater cave exploration","author":"Mohammadi","year":"2024"},{"key":"10.1016\/j.neucom.2026.133714_bib0060","series-title":"2021 IEEE International Conference on Multimedia & Expo Workshops (ICMEW)","first-page":"1","article-title":"A dataset and benchmark of underwater object detection for robot picking","author":"Liu","year":"2021"},{"key":"10.1016\/j.neucom.2026.133714_bib0065","series-title":"Proceedings of the 29th ACM International Conference on Multimedia","first-page":"4259","article-title":"Underwater species detection using channel sharpening attention","author":"Jiang","year":"2021"},{"key":"10.1016\/j.neucom.2026.133714_bib0070","doi-asserted-by":"crossref","first-page":"4861","DOI":"10.1109\/TCSVT.2019.2963772","article-title":"Real-world underwater enhancement: challenges, benchmarks, and solutions under natural light","volume":"30","author":"Liu","year":"2020","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.neucom.2026.133714_bib0075","doi-asserted-by":"crossref","first-page":"2831","DOI":"10.1109\/TCSVT.2021.3100059","article-title":"A new dataset, Poisson GAN and Aquanet for underwater object grabbing","volume":"32","author":"Liu","year":"2021","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.neucom.2026.133714_bib0080","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"1305","article-title":"Watermask: instance segmentation for underwater imagery","author":"Lian","year":"2023"},{"key":"10.1016\/j.neucom.2026.133714_bib0085","author":"Lian"},{"key":"10.1016\/j.neucom.2026.133714_bib0090","doi-asserted-by":"crossref","first-page":"150","DOI":"10.1016\/j.neucom.2023.01.088","article-title":"Boosting r-Cnn: reweighting r-Cnn samples by rpn\u2019s error for underwater object detection","volume":"530","author":"Song","year":"2023","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neucom.2026.133714_bib0095","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2022.108926","article-title":"Swipenet: object detection in noisy underwater scenes","volume":"132","author":"Chen","year":"2022","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.neucom.2026.133714_bib0100","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2024.123253","article-title":"Pe-transformer: path enhanced transformer for improving underwater object detection","volume":"246","author":"Gao","year":"2024","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.neucom.2026.133714_bib0105","article-title":"Su-Yolo: spiking neural network for efficient underwater object detection","author":"Li","year":"2025","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neucom.2026.133714_bib0110","doi-asserted-by":"crossref","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","article-title":"Faster r-Cnn: towards real-time object detection with region proposal networks","volume":"39","author":"Ren","year":"2016","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.neucom.2026.133714_bib0115","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"6154","article-title":"Cascade r-Cnn: delving into high quality object detection","author":"Cai","year":"2018"},{"key":"10.1016\/j.neucom.2026.133714_bib0120","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"821","article-title":"Libra R-Cnn: towards balanced learning for object detection","author":"Pang","year":"2019"},{"key":"10.1016\/j.neucom.2026.133714_bib0125","series-title":"Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part XV 16","first-page":"260","article-title":"Dynamic r-Cnn: towards high quality object detection via dynamic training","author":"Zhang","year":"2020"},{"key":"10.1016\/j.neucom.2026.133714_bib0130","series-title":"Proceedings of the IEEE International Conference on Computer Vision","first-page":"2980","article-title":"Focal loss for dense object detection","author":"Lin","year":"2017"},{"key":"10.1016\/j.neucom.2026.133714_bib0135","series-title":"Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part XXV 16","first-page":"355","article-title":"Probabilistic anchor assignment with IOU prediction for object detection","author":"Kim","year":"2020"},{"key":"10.1016\/j.neucom.2026.133714_bib0140","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"9627","article-title":"FCOS: fully convolutional one-stage object detection","author":"Tian","year":"2019"},{"key":"10.1016\/j.neucom.2026.133714_bib0145","author":"Li"},{"key":"10.1016\/j.neucom.2026.133714_bib0150","series-title":"European Conference on Computer Vision","first-page":"1","article-title":"Yolov9: learning what you want to learn using programmable gradient information","author":"Wang","year":"2024"},{"key":"10.1016\/j.neucom.2026.133714_bib0155","author":"Tian"},{"key":"10.1016\/j.neucom.2026.133714_bib0160","author":"Lei"},{"key":"10.1016\/j.neucom.2026.133714_bib0165","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","article-title":"You only look once: unified, real-time object detection","author":"Redmon","year":"2016"},{"key":"10.1016\/j.neucom.2026.133714_bib0170","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"7263","article-title":"Yolo9000: better, faster, stronger","author":"Redmon","year":"2017"},{"key":"10.1016\/j.neucom.2026.133714_bib0175","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"16965","article-title":"Detrs beat yolos on real-time object detection","author":"Zhao","year":"2024"},{"key":"10.1016\/j.neucom.2026.133714_bib0180","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"8205","article-title":"Mamba YOLO: a simple baseline for object detection with state space model","volume":"vol. 39","author":"Wang","year":"2025"},{"key":"10.1016\/j.neucom.2026.133714_bib0185","first-page":"107984","article-title":"Yolov10: real-time end-to-end object detection","volume":"37","author":"Wang","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.133714_bib0190","series-title":"2008 3rd IEEE Conference on Industrial Electronics and Applications","first-page":"2507","article-title":"A method of underwater image segmentation based on discrete fractional brownian random field","author":"Tiedong","year":"2008"},{"key":"10.1016\/j.neucom.2026.133714_bib0195","doi-asserted-by":"crossref","first-page":"72420","DOI":"10.1109\/ACCESS.2019.2919711","article-title":"Underwater object segmentation integrating transmission and saliency features","volume":"7","author":"Chen","year":"2019","journal-title":"IEEE Access"},{"key":"10.1016\/j.neucom.2026.133714_bib0200","series-title":"Proceedings of the IEEE International Conference on Computer Vision","first-page":"2961","article-title":"Mask R-Cnn","author":"He","year":"2017"},{"key":"10.1016\/j.neucom.2026.133714_bib0205","author":"Jocher"},{"key":"10.1016\/j.neucom.2026.133714_bib0210","author":"Khanam"},{"key":"10.1016\/j.neucom.2026.133714_bib0215","author":"Dosovitskiy"},{"key":"10.1016\/j.neucom.2026.133714_bib0220","series-title":"Proceedings of the Computer Vision and Pattern Recognition Conference","first-page":"14046","article-title":"Mass13k: a matting-level semantic segmentation benchmark","author":"Xie","year":"2025"},{"key":"10.1016\/j.neucom.2026.133714_bib0225","first-page":"103031","article-title":"Vmamba: visual state space model","volume":"37","author":"Liu","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.133714_bib0230","author":"Zhu"},{"key":"10.1016\/j.neucom.2026.133714_bib0235","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"2578","article-title":"Fantastic animals and where to find them: segment any marine animal with dual SAM","author":"Zhang","year":"2024"},{"key":"10.1016\/j.neucom.2026.133714_bib0240","doi-asserted-by":"crossref","first-page":"654","DOI":"10.1038\/s41467-024-44824-z","article-title":"Segment anything in medical images","volume":"15","author":"Ma","year":"2024","journal-title":"Nat. Commun."},{"key":"10.1016\/j.neucom.2026.133714_bib0245","doi-asserted-by":"crossref","first-page":"14820","DOI":"10.1109\/JSTARS.2025.3576285","article-title":"A decoupled segmentation-classification strategy based on semantic-sam for precise semantic segmentation in coal mine areas","volume":"18","author":"Wang","year":"2025","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"10.1016\/j.neucom.2026.133714_bib0250","article-title":"Sam-guided multi-level collaborative transformer for infrared and visible image fusion","author":"Guo","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.neucom.2026.133714_bib0255","author":"Zhao"},{"key":"10.1016\/j.neucom.2026.133714_bib0260","author":"Zhang"},{"key":"10.1016\/j.neucom.2026.133714_bib0265","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"16111","article-title":"Efficientsam: leveraged masked image pretraining for Efficient segment anything","author":"Xiong","year":"2024"},{"key":"10.1016\/j.neucom.2026.133714_bib0270","series-title":"Advanced auto labeling solution with added features","author":"Wang","year":"2023"},{"key":"10.1016\/j.neucom.2026.133714_bib0275","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"5652","article-title":"Efficient deformable convnets: rethinking dynamic and sparse operator for vision applications","author":"Xiong","year":"2024"},{"key":"10.1016\/j.neucom.2026.133714_bib0280","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"6185","article-title":"Neighborhood attention transformer","author":"Hassani","year":"2023"},{"key":"10.1016\/j.neucom.2026.133714_bib0285","author":"Dao"},{"key":"10.1016\/j.neucom.2026.133714_bib0290","series-title":"Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision","first-page":"7778","article-title":"Reverse knowledge distillation: training a large model using a small one for retinal image matching on limited data","author":"Nasser","year":"2024"}],"container-title":["Neurocomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226011112?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226011112?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T13:54:05Z","timestamp":1778766845000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0925231226011112"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":58,"alternative-id":["S0925231226011112"],"URL":"https:\/\/doi.org\/10.1016\/j.neucom.2026.133714","relation":{},"ISSN":["0925-2312"],"issn-type":[{"value":"0925-2312","type":"print"}],"subject":[],"published":{"date-parts":[[2026,7]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"YOSAM2: A lightweight framework for joint underwater instance segmentation and benchmarking on the DSUO dataset","name":"articletitle","label":"Article Title"},{"value":"Neurocomputing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neucom.2026.133714","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"133714"}}