{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T14:56:51Z","timestamp":1783522611078,"version":"3.55.0"},"reference-count":201,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100005270","name":"Jilin Provincial Department of Science and Technology","doi-asserted-by":"publisher","award":["20230401104YY"],"award-info":[{"award-number":["20230401104YY"]}],"id":[{"id":"10.13039\/501100005270","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/access.2024.3496723","type":"journal-article","created":{"date-parts":[[2024,11,12]],"date-time":"2024-11-12T18:44:26Z","timestamp":1731437066000},"page":"175715-175741","source":"Crossref","is-referenced-by-count":11,"title":["Research Advances in Deep Learning for Image Semantic Segmentation Techniques"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6719-0652","authenticated-orcid":false,"given":"Zhiguo","family":"Xiao","sequence":"first","affiliation":[{"name":"College of Computer Science and Technology, Changchun University, Changchun, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tengfei","family":"Chai","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Changchun University, Changchun, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2450-5217","authenticated-orcid":false,"given":"Nianfeng","family":"Li","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Changchun University, Changchun, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2461-5419","authenticated-orcid":false,"given":"Xiangfeng","family":"Shen","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Changchun University, Changchun, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tong","family":"Guan","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Changchun University, Changchun, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jia","family":"Tian","sequence":"additional","affiliation":[{"name":"College of Cyber Security, Changchun University, Changchun, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinyuan","family":"Li","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Changchun University, Changchun, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.01.005"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.2972974"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2022.10.022"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-020-09854-1"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00200"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109557"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s12273-022-0953-5"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.3390\/s20061737"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3059968"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2022.09.031"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2024.104102"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2024.03.012"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s00778-022-00775-9"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-022-04064-4"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2023.3234257"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.03.062"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2022.12.008"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3446949"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s10670-022-00605-y"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-024-10862-8"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICECET61485.2024.10698602"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref24","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. 3rd Int. Conf. Learn. Represent. (ICLR)","author":"Simonyan"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2015.7298594"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2016.308"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref30","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"Howard","year":"2017","journal-title":"arXiv:1704.04861"},{"key":"ref31","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","author":"Tan","year":"2019","journal-title":"arXiv:1905.11946"},{"key":"ref32","first-page":"6848","article-title":"ShuffleNet: An extremely efficient convolutional neural network for mobile devices","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","author":"Zhang"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2019.2913372"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00060"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2024.02.003"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01538"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/MGRS.2022.3227056"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.paerosci.2023.100960"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/MGRS.2024.3383473"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3372639"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2021.3079459"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3144894"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3243042"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3373033"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3460081"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2023.09.013"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/s11119-023-10062-4"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2021.12.006"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.3390\/drones7060398"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.ecolind.2023.109965"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2023.107705"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1016\/j.agwat.2023.108142"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1016\/j.catena.2023.107450"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/s10712-022-09700-9"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2023.3288743"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1016\/j.seta.2023.103452"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3407838"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2024.106742"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3435571"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2023.107434"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2023.106959"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2022.106501"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.3389\/fphys.2023.1148717"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.126298"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.3390\/su13031224"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-37734-2_37"},{"key":"ref67","article-title":"A large annotated medical image dataset for the development and evaluation of segmentation algorithms","author":"Simpson","year":"2019","journal-title":"arXiv:1902.09063"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ISBI45749.2020.9098498"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-32248-9_38"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-024-71273-x"},{"key":"ref73","article-title":"STS MICCAI 2023 challenge: Grand challenge on 2D and 3D semi-supervised tooth segmentation","author":"Wang","year":"2024","journal-title":"arXiv:2407.13246"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-022-30695-9"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1117\/12.2582227"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2005.11.005"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3207665"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-022-10176-7"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2021.104184"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.107861"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00134"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2905081"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1007\/s11831-021-09591-w"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2015.7298965"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref86","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2020.107404","article-title":"U2-Net: Going deeper with nested U-structure for salient object detection","volume":"106","author":"Qin","year":"2020","journal-title":"Pattern Recognit."},{"key":"ref87","article-title":"SegNet: A deep convolutional encoder\u2013decoder architecture for robust semantic pixel-wise labelling","author":"Badrinarayanan","year":"2015","journal-title":"arXiv:1505.07293"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2015.178"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.189"},{"key":"ref90","article-title":"ParseNet: Looking wider to see better","author":"Liu","year":"2015","journal-title":"arXiv:1506.04579"},{"key":"ref91","article-title":"FastFCN: Rethinking dilated convolution in the backbone for semantic segmentation","author":"Wu","year":"2019","journal-title":"arXiv:1903.11816"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00028"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46723-8_48"},{"key":"ref94","doi-asserted-by":"crossref","first-page":"50","DOI":"10.1016\/j.isprsjprs.2020.02.004","article-title":"Directionally constrained fully convolutional neural network for airborne LiDAR point cloud classification","volume":"162","author":"Wen","year":"2020","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2983686"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2019.2895460"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/VCIP.2017.8305148"},{"key":"ref98","article-title":"W-Net: A deep model for fully unsupervised image segmentation","author":"Xia","year":"2017","journal-title":"arXiv:1711.08506"},{"key":"ref99","first-page":"1","article-title":"Multi-scale context aggregation by dilated convolutions","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Yu"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/ICSP48669.2020.9321067"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.75"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00163"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00747"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2017.634"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/cvprw50498.2020.00203"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10578-9_23"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_32"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/TCOM.1983.1095851"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2017.549"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2017.660"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2017.106"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_26"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1109\/ICAIIC57133.2023.10067062"},{"key":"ref115","article-title":"DeepLab: Semantic image segmentation with deep convolutional nets, Atrous convolution, and fully connected CRFs","author":"Chen","year":"2016","journal-title":"arXiv:1606.00915"},{"key":"ref116","article-title":"Rethinking Atrous convolution for semantic image segmentation","author":"Chen","year":"2017","journal-title":"arXiv:1706.05587"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00388"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00770"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.396"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01240-3_17"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00326"},{"key":"ref123","article-title":"OCNet: Object context network for scene parsing","author":"Yuan","year":"2018","journal-title":"arXiv:1809.00916"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00069"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00926"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01308"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref128","first-page":"4203","article-title":"Focal modulation networks","volume-title":"Proc. 36th Int. Conf. Neural Inf. Process. Syst.","author":"Yang"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3206108"},{"key":"ref130","article-title":"Pyramid attention network for semantic segmentation","author":"Li","year":"2018","journal-title":"arXiv:1805.10180"},{"key":"ref131","article-title":"SERNet-former: Semantic segmentation by efficient residual network with attention-boosting gates and attention-fusion networks","author":"Erisen","year":"2024","journal-title":"arXiv:2401.15741"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00060"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00356"},{"key":"ref135","article-title":"A\u00b2-Nets: Double attention networks","author":"Chen","year":"2018","journal-title":"arXiv:1810.11579"},{"key":"ref136","first-page":"6511","article-title":"Compact generalized non-local network","volume-title":"Proc. 32nd Int. Conf. Neural Inf. Process. Syst.","author":"Yue"},{"key":"ref137","first-page":"1","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Vaswani"},{"key":"ref138","first-page":"1","article-title":"An image is worth 16 \u00d716 words: Transformers for image recognition at scale","volume-title":"Proc. 9th Int. Conf. Learn. Represent. (ICLR)","author":"Dosovitskiy"},{"key":"ref139","article-title":"Vision transformers with patch diversification","author":"Gong","year":"2021","journal-title":"arXiv:2104.12753"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.00986"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01170"},{"key":"ref142","doi-asserted-by":"publisher","DOI":"10.1007\/s13042-024-02110-w"},{"key":"ref143","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref144","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01548"},{"key":"ref145","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.00681"},{"key":"ref146","first-page":"1","article-title":"Per-pixel classification is not all you need for semantic segmentation","volume-title":"Proc. 35th Int. Conf. Neural Inf. Process. Syst.","author":"Cheng"},{"key":"ref147","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01733"},{"key":"ref149","first-page":"1","article-title":"SegViT: Semantic segmentation with plain vision transformers","volume-title":"Proc. 36th Int. Conf. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref150","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01894-8"},{"key":"ref151","article-title":"TransNeXt: Robust foveal visual perception for vision transformers","author":"Shi","year":"2023","journal-title":"arXiv:2311.17132"},{"key":"ref152","article-title":"DAT++: Spatially dynamic vision transformer with deformable attention","author":"Xia","year":"2023","journal-title":"arXiv:2309.01430"},{"key":"ref153","first-page":"1","article-title":"HorNet: Efficient high-order spatial interactions with recursive gated convolutions","volume-title":"Proc. 36th Int. Conf. Neural Inf. Process. Syst.","author":"Rao"},{"key":"ref154","article-title":"Vision transformer adapter for dense predictions","author":"Chen","year":"2022","journal-title":"arXiv:2205.08534"},{"key":"ref155","article-title":"Dilated neighborhood attention transformer","author":"Hassani","year":"2022","journal-title":"arXiv:2209.15001"},{"key":"ref156","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19818-2_17"},{"key":"ref157","article-title":"Minimalist and high-performance semantic segmentation with plain vision transformers","author":"Hong","year":"2023","journal-title":"arXiv:2310.12755"},{"key":"ref158","article-title":"Mamba: Linear-time sequence modeling with selective state spaces","author":"Gu","year":"2023","journal-title":"arXiv:2312.00752"},{"key":"ref159","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3485721"},{"key":"ref160","article-title":"Scalable visual state space model with fractal scanning","author":"Tang","year":"2024","journal-title":"arXiv:2405.14480"},{"key":"ref161","article-title":"EfficientVMamba: Atrous selective scan for light weight visual mamba","author":"Pei","year":"2024","journal-title":"arXiv:2403.09977"},{"key":"ref162","article-title":"Multi-scale VMamba: Hierarchy in hierarchy visual state space model","author":"Shi","year":"2024","journal-title":"arXiv:2405.14174"},{"key":"ref163","article-title":"PlainMamba: Improving non-hierarchical mamba in visual recognition","author":"Yang","year":"2024","journal-title":"arXiv:2403.17695"},{"key":"ref164","article-title":"LocalMamba: Visual state space model with windowed selective scan","author":"Huang","year":"2024","journal-title":"arXiv:2403.09338"},{"key":"ref165","article-title":"U-mamba: Enhancing long-range dependency for biomedical image segmentation","author":"Ma","year":"2024","journal-title":"arXiv:2401.04722"},{"key":"ref166","article-title":"Mamba-UNet: UNet-like pure visual mamba for medical image segmentation","author":"Wang","year":"2024","journal-title":"arXiv:2402.05079"},{"key":"ref167","article-title":"VMamba: Visual state space model","author":"Liu","year":"2024","journal-title":"arXiv:2401.10166"},{"key":"ref168","article-title":"VM-UNet: Vision mamba UNet for medical image segmentation","author":"Ruan","year":"2024","journal-title":"arXiv:2402.02491"},{"key":"ref169","article-title":"Semi-mamba-UNet: Pixel-level contrastive and pixel-level cross-supervised visual mamba-based UNet for semi-supervised medical image segmentation","author":"Ma","year":"2024","journal-title":"arXiv:2402.07245"},{"key":"ref170","article-title":"Integrating mamba sequence model and hierarchical upsampling network for accurate semantic segmentation of multiple sclerosis legion","author":"Sanjid","year":"2024","journal-title":"arXiv:2403.17432"},{"key":"ref171","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-97-5128-0_27"},{"key":"ref172","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72114-4_59"},{"key":"ref173","article-title":"SpectralMamba: Efficient mamba for hyperspectral image classification","author":"Yao","year":"2024","journal-title":"arXiv:2404.08489"},{"key":"ref174","article-title":"Mamba-in-Mamba: Centralized mamba-cross-scan in tokenized mamba model for hyperspectral image classification","author":"Zhou","year":"2024","journal-title":"arXiv:2405.12003"},{"key":"ref175","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2024.3417253"},{"key":"ref176","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3425540"},{"key":"ref177","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01229"},{"key":"ref178","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref179","article-title":"DINOv2: Learning robust visual features without supervision","author":"Oquab","year":"2023","journal-title":"arXiv:2304.07193"},{"key":"ref180","article-title":"Mask DINO: Towards a unified transformer-based framework for object detection and segmentation","author":"Li","year":"2022","journal-title":"arXiv:2206.02777"},{"key":"ref181","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01855"},{"key":"ref182","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.119"},{"key":"ref183","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref184","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475217"},{"key":"ref185","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref186","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913491297"},{"key":"ref187","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2010.147"},{"key":"ref188","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459211"},{"key":"ref189","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"ref190","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298655"},{"key":"ref191","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"ref192","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2001.937655"},{"key":"ref193","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2014.254"},{"key":"ref194","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248065"},{"key":"ref195","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.352"},{"key":"ref196","first-page":"1","article-title":"SegFormer: Simple and efficient design for semantic segmentation with transformers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Xie"},{"key":"ref197","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00717"},{"key":"ref198","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00987"},{"key":"ref199","article-title":"SwinMTL: A shared architecture for simultaneous depth estimation and semantic segmentation from monocular camera images","author":"Taghavi","year":"2024","journal-title":"arXiv:2403.10662"},{"key":"ref200","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00406"},{"key":"ref201","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01513"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10380310\/10750790.pdf?arnumber=10750790","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,29]],"date-time":"2024-11-29T07:56:41Z","timestamp":1732867001000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10750790\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":201,"URL":"https:\/\/doi.org\/10.1109\/access.2024.3496723","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}