{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T04:16:35Z","timestamp":1783570595593,"version":"3.55.0"},"reference-count":52,"publisher":"Public Library of Science (PLoS)","issue":"3","license":[{"start":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T00:00:00Z","timestamp":1773964800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Guangxi Science and Technology Major Project","award":["Grant No. AA19254016"],"award-info":[{"award-number":["Grant No. AA19254016"]}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>As the spatial resolution of remote sensing imagery continues to be improved, the complexity of the information also increases. Remote sensing images generally have characteristics such as wide imaging ranges, dispersed distribution of similar land objects, complex boundary shapes, and dense small targets, which pose severe challenges to semantic segmentation tasks. To address these challenges, we propose a channel reconstruction and dual attention dynamic fusion network (CRDFNet), which is a semantic segmentation network for remote sensing image that can effectively integrate global and local contexts. To better handle complex boundary shapes, we designed a channel feature aggregation module (CFAM), which can extract spatially redundant information during feature fusion and enhance high-resolution detail features. Through a channel reconstruction block, it promotes the alignment of fine-grained information from the encoder with high-level semantic information from the decoder, effectively aggregating multi-scale features extracted by the encoder and significantly improving segmentation accuracy. At the same time, to optimize the segmentation performance of small targets, we propose a dual attention feature refinement module (DAFRM), which achieves precise segmentation of small targets by effectively fuses the shallow spatial features of the encoder and the deep semantic features of the decoder through a dynamic fusion mechanism guided by dual attention. Experimental results on the Potsdam, Vaihingen, UAVid, and MSIDBG datasets demonstrate that CRDFNet outperforms existing methods in terms of F1 score, OA, and mIoU (Intersection over Union), validating its excellent performance.<\/jats:p>","DOI":"10.1371\/journal.pone.0343777","type":"journal-article","created":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T17:23:41Z","timestamp":1774027421000},"page":"e0343777","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":1,"title":["Channel reconstruction and dual attention dynamic fusion for remote sensing image semantic segmentation"],"prefix":"10.1371","volume":"21","author":[{"given":"Xin","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Longxing","family":"Niu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-8092-2370","authenticated-orcid":true,"given":"Zhiwen","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qun","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jia","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qin","family":"Qin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guan","family":"Lian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiawei","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,3,20]]},"reference":[{"key":"pone.0343777.ref001","doi-asserted-by":"crossref","first-page":"110415","DOI":"10.1016\/j.knosys.2023.110415","article-title":"Orientation Attention Network for semantic segmentation of remote sensing images","volume":"267","author":"J Wang","year":"2023","journal-title":"Knowledge-Based Systems"},{"key":"pone.0343777.ref002","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TGRS.2024.3369720","article-title":"RRSIS: Referring Remote Sensing Image Segmentation","volume":"62","author":"Z Yuan","year":"2024","journal-title":"IEEE Trans Geosci Remote Sensing"},{"issue":"9","key":"pone.0343777.ref003","doi-asserted-by":"crossref","first-page":"1514","DOI":"10.3390\/rs16091514","article-title":"A bio-inspired visual perception transformer for cross-domain semantic segmentation of high-resolution remote sensing images","volume":"16","author":"X Wang","year":"2024","journal-title":"Remote Sensing"},{"key":"pone.0343777.ref004","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/LGRS.2024.3354175","article-title":"Spatial-gated multilayer perceptron for land use and land cover mapping","volume":"21","author":"A Jamali","year":"2024","journal-title":"IEEE Geosci Remote Sensing Lett"},{"issue":"6","key":"pone.0343777.ref005","doi-asserted-by":"crossref","first-page":"1019","DOI":"10.3390\/rs17061019","article-title":"GLFFNet: global\u2013local feature fusion network for high-resolution remote sensing image semantic segmentation","volume":"17","author":"S Zhu","year":"2025","journal-title":"Remote Sensing"},{"issue":"1","key":"pone.0343777.ref006","doi-asserted-by":"crossref","first-page":"013026","DOI":"10.1117\/1.JEI.23.1.013026","article-title":"Image classification using a new set of separable two-dimensional discrete orthogonal invariant moments","volume":"23","author":"A Hmimid","year":"2014","journal-title":"J Electron Imaging"},{"key":"pone.0343777.ref007","volume-title":"Simple convolutional neural network on image classification","author":"T Guo","year":"2017"},{"key":"pone.0343777.ref008","doi-asserted-by":"crossref","first-page":"103536","DOI":"10.1016\/j.jag.2023.103536","article-title":"Lithological mapping of geological remote sensing via adversarial semi-supervised segmentation network","volume":"125","author":"S Wang","year":"2023","journal-title":"International Journal of Applied Earth Observation and Geoinformation"},{"key":"pone.0343777.ref009","doi-asserted-by":"crossref","first-page":"111819","DOI":"10.1016\/j.knosys.2024.111819","article-title":"A serial semantic segmentation model based on encoder-decoder architecture","volume":"295","author":"Y Zhou","year":"2024","journal-title":"Knowledge-Based Systems"},{"issue":"9","key":"pone.0343777.ref010","doi-asserted-by":"crossref","first-page":"5961","DOI":"10.1007\/s11042-024-19175-y","article-title":"Semantic road segmentation using encoder-decoder architectures","volume":"84","author":"B Latsaheb","year":"2024","journal-title":"Multimed Tools Appl"},{"key":"pone.0343777.ref011","volume-title":"U-net: Convolutional networks for biomedical image segmentation. In: Medical image computing and computer-assisted intervention\u2013MICCAI 2015: 18th international conference, Munich, Germany, October 5-9, 2015, proceedings, part III","author":"O Ronneberger","year":"2015"},{"key":"pone.0343777.ref012","first-page":"833","article-title":"Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation","author":"L-C Chen","year":"2018","journal-title":"Lecture Notes in Computer Science. Springer International Publishing"},{"issue":"5","key":"pone.0343777.ref013","doi-asserted-by":"crossref","first-page":"1926","DOI":"10.1109\/TCSVT.2020.3015866","article-title":"Encoder-Decoder With Cascaded CRFs for Semantic Segmentation","volume":"31","author":"J Ji","year":"2021","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"issue":"15","key":"pone.0343777.ref014","doi-asserted-by":"crossref","first-page":"2190","DOI":"10.1111\/mice.13443","article-title":"Pixel\u2010wise anomaly detection on road by encoder\u2013decoder semantic segmentation framework with driving vigilance","volume":"40","author":"Y Liu","year":"2025","journal-title":"Computer aided Civil Eng"},{"key":"pone.0343777.ref015","first-page":"3141","author":"J Fu","year":"2019","journal-title":"Dual Attention Network for Scene Segmentation. In: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)"},{"key":"pone.0343777.ref016","volume-title":"Agent attention: On the integration of softmax and linear attention","author":"D Han","year":"2024"},{"key":"pone.0343777.ref017","doi-asserted-by":"crossref","first-page":"5534","DOI":"10.1109\/JSTARS.2022.3188515","article-title":"HCRB-MSAN: Horizontally Connected Residual Blocks-Based Multiscale Attention Network for Semantic Segmentation of Buildings in HSR Remote Sensing Images","volume":"15","author":"Z Li","year":"2022","journal-title":"IEEE J Sel Top Appl Earth Observations Remote Sensing"},{"key":"pone.0343777.ref018","volume-title":"Dyfadet: Dynamic feature aggregation for temporal action detection","author":"L Yang","year":"2024"},{"issue":"23","key":"pone.0343777.ref019","doi-asserted-by":"crossref","first-page":"5610","DOI":"10.3390\/rs15235610","article-title":"SSCNet: A Spectrum-Space Collaborative Network for Semantic Segmentation of Remote Sensing Images","volume":"15","author":"X Li","year":"2023","journal-title":"Remote Sensing"},{"key":"pone.0343777.ref020","first-page":"1","article-title":"CACFTNet: A Hybrid Cov-Attention and Cross-Layer Fusion Transformer Network for Hyperspectral Image Classification","volume":"62","author":"S Cheng","year":"2024","journal-title":"IEEE Trans Geosci Remote Sensing"},{"key":"pone.0343777.ref021","doi-asserted-by":"crossref","first-page":"112134","DOI":"10.1016\/j.ymssp.2024.112134","article-title":"Surrogate modeling of pantograph-catenary system interactions","volume":"224","author":"Y Cheng","year":"2025","journal-title":"Mechanical Systems and Signal Processing"},{"key":"pone.0343777.ref022","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TGRS.2023.3290411","article-title":"Distilling Segmenters From CNNs and Transformers for Remote Sensing Images\u2019 Semantic Segmentation","volume":"61","author":"Z Dong","year":"2023","journal-title":"IEEE Trans Geosci Remote Sensing"},{"issue":"9","key":"pone.0343777.ref023","doi-asserted-by":"crossref","first-page":"2363","DOI":"10.3390\/rs15092363","article-title":"ACTNet: A Dual-Attention Adapter with a CNN-Transformer Network for the Semantic Segmentation of Remote Sensing Imagery","volume":"15","author":"Z Zhang","year":"2023","journal-title":"Remote Sensing"},{"key":"pone.0343777.ref024","doi-asserted-by":"crossref","first-page":"4689","DOI":"10.1109\/JSTARS.2024.3361927","article-title":"CTMANet: A CNN-Transformer Hybrid Semantic Segmentation Network for Fine-Grained Airport Extraction in Complex SAR Scenes","volume":"17","author":"K Wu","year":"2024","journal-title":"IEEE J Sel Top Appl Earth Observations Remote Sensing"},{"issue":"1","key":"pone.0343777.ref025","doi-asserted-by":"crossref","first-page":"6110","DOI":"10.1038\/s41598-025-90518-x","article-title":"Semantic segmentation feature fusion network based on transformer","volume":"15","author":"T Li","year":"2025","journal-title":"Sci Rep"},{"key":"pone.0343777.ref026","doi-asserted-by":"crossref","first-page":"196","DOI":"10.1016\/j.isprsjprs.2022.06.008","article-title":"UNetFormer: A UNet-like transformer for efficient semantic segmentation of remote sensing urban scene imagery","volume":"190","author":"L Wang","year":"2022","journal-title":"ISPRS Journal of Photogrammetry and Remote Sensing"},{"key":"pone.0343777.ref027","doi-asserted-by":"crossref","first-page":"103280","DOI":"10.1016\/j.media.2024.103280","article-title":"TransUNet: Rethinking the U-Net architecture design for medical image segmentation through the lens of transformers","volume":"97","author":"J Chen","year":"2024","journal-title":"Med Image Anal"},{"key":"pone.0343777.ref028","doi-asserted-by":"crossref","first-page":"7233","DOI":"10.1109\/JSTARS.2024.3375313","article-title":"CMLFormer: CNN and Multiscale Local-Context Transformer Network for Remote Sensing Images Semantic Segmentation","volume":"17","author":"H Wu","year":"2024","journal-title":"IEEE J Sel Top Appl Earth Observations Remote Sensing"},{"key":"pone.0343777.ref029","doi-asserted-by":"crossref","first-page":"3023","DOI":"10.1109\/JSTARS.2024.3349657","article-title":"SSNet: A Novel Transformer and CNN Hybrid Network for Remote Sensing Semantic Segmentation","volume":"17","author":"M Yao","year":"2024","journal-title":"IEEE J Sel Top Appl Earth Observations Remote Sensing"},{"issue":"2","key":"pone.0343777.ref030","doi-asserted-by":"crossref","first-page":"1159","DOI":"10.1109\/TCSVT.2023.3292156","article-title":"An Adaptive Post-Processing Network With the Global-Local Aggregation for Semantic Segmentation","volume":"34","author":"G Zhu","year":"2023","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"pone.0343777.ref031","doi-asserted-by":"crossref","first-page":"110962","DOI":"10.1016\/j.knosys.2023.110962","article-title":"Scene sketch semantic segmentation with hierarchical Transformer","volume":"280","author":"J Yang","year":"2023","journal-title":"Knowledge-Based Systems"},{"key":"pone.0343777.ref032","doi-asserted-by":"crossref","first-page":"129915","DOI":"10.1016\/j.neucom.2025.129915","article-title":"SARFormer: Segmenting Anything Guided Transformer for semantic segmentation","volume":"635","author":"L Zhang","year":"2025","journal-title":"Neurocomputing"},{"key":"pone.0343777.ref033","first-page":"1","article-title":"Multimodal Imitation Learning for Arc Detection in Complex Railway Environments","volume":"74","author":"J Yan","year":"2025","journal-title":"IEEE Trans Instrum Meas"},{"key":"pone.0343777.ref034","article-title":"Research on multimodal techniques for arc detection in railway systems with limited data","author":"J Yan","year":"2025","journal-title":"Structural Health Monitoring"},{"key":"pone.0343777.ref035","first-page":"3431","author":"J Long","year":"2015","journal-title":"Fully convolutional networks for semantic segmentation. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)"},{"issue":"12","key":"pone.0343777.ref036","doi-asserted-by":"crossref","first-page":"2481","DOI":"10.1109\/TPAMI.2016.2644615","article-title":"SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation","volume":"39","author":"V Badrinarayanan","year":"2017","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"pone.0343777.ref037","volume-title":"Pyramid scene parsing network. Proceedings of the IEEE conference on computer vision and pattern recognition","author":"H Zhao","year":"2017"},{"key":"pone.0343777.ref038","first-page":"6877","article-title":"Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers. In: 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"S Zheng","year":"2021"},{"key":"pone.0343777.ref039","doi-asserted-by":"crossref","unstructured":"Liu Z, Lin Y, Cao Y, Hu H, Wei Y, Zhang Z. Swin transformer: hierarchical vision transformer using shifted windows. 2021.","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"pone.0343777.ref040","article-title":"Transunet: Transformers make strong encoders for medical image segmentation. arXiv preprint","author":"J Chen","year":"2021"},{"key":"pone.0343777.ref041","first-page":"1","article-title":"Transformer and CNN Hybrid Deep Neural Network for Semantic Segmentation of Very-High-Resolution Remote Sensing Imagery","volume":"60","author":"C Zhang","year":"2022","journal-title":"IEEE Trans Geosci Remote Sensing"},{"key":"pone.0343777.ref042","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TGRS.2023.3314641","article-title":"CMTFNet: CNN and Multiscale Transformer Fusion Network for Remote-Sensing Image Semantic Segmentation","volume":"61","author":"H Wu","year":"2023","journal-title":"IEEE Trans Geosci Remote Sensing"},{"issue":"3","key":"pone.0343777.ref043","doi-asserted-by":"crossref","first-page":"1131","DOI":"10.1080\/01431161.2022.2030071","article-title":"A2-FPN for semantic segmentation of fine-resolution remotely sensed images","volume":"43","author":"R Li","year":"2022","journal-title":"International J Remote Sensing"},{"key":"pone.0343777.ref044","article-title":"Boundary-aware segmentation network for mobile and web applications. arXiv preprint","author":"X Qin","year":"2021"},{"issue":"23","key":"pone.0343777.ref045","doi-asserted-by":"crossref","first-page":"4392","DOI":"10.3390\/rs16234392","article-title":"AFENet: An Attention-Focused Feature Enhancement Network for the Efficient Semantic Segmentation of Remote Sensing Images","volume":"16","author":"J Li","year":"2024","journal-title":"Remote Sensing"},{"key":"pone.0343777.ref046","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TGRS.2022.3179379","article-title":"MANet: Multi-Scale Aware-Relation Network for Semantic Segmentation in Aerial Scenes","volume":"60","author":"P He","year":"2022","journal-title":"IEEE Trans Geosci Remote Sensing"},{"key":"pone.0343777.ref047","doi-asserted-by":"crossref","first-page":"6789","DOI":"10.1109\/TIP.2022.3216216","article-title":"BANet: A Blur-Aware Attention Network for Dynamic Scene Deblurring","volume":"31","author":"F-J Tsai","year":"2022","journal-title":"IEEE Trans Image Process"},{"key":"pone.0343777.ref048","doi-asserted-by":"crossref","unstructured":"Radosavovic I, Kosaraju RP, Girshick R, He K, Dollar P. Designing Network Design Spaces. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020. 10425\u201333. https:\/\/doi.org\/10.1109\/cvpr42600.2020.01044","DOI":"10.1109\/CVPR42600.2020.01044"},{"key":"pone.0343777.ref049","first-page":"770","author":"K He","year":"2016"},{"key":"pone.0343777.ref050","unstructured":"Potsdam and Vaihingen Datasets. https:\/\/www.isprs.org\/education\/benchmarks\/UrbanSemLab. 2024."},{"key":"pone.0343777.ref051","doi-asserted-by":"crossref","first-page":"108","DOI":"10.1016\/j.isprsjprs.2020.05.009","article-title":"UAVid: A semantic segmentation dataset for UAV imagery","volume":"165","author":"Y Lyu","year":"2020","journal-title":"ISPRS Journal of Photogrammetry and Remote Sensing"},{"key":"pone.0343777.ref052","doi-asserted-by":"crossref","first-page":"107638","DOI":"10.1016\/j.engappai.2023.107638","article-title":"Frequency-aware robust multidimensional information fusion framework for remote sensing image segmentation","volume":"129","author":"J Fan","year":"2024","journal-title":"Eng Applications of Artificial Intelligence"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0343777","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T17:23:52Z","timestamp":1774027432000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0343777"}},"subtitle":[],"editor":[{"given":"Xiaoyong","family":"Sun","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,3,20]]},"references-count":52,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2026,3,20]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0343777","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,20]]}}}