{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T11:54:24Z","timestamp":1782474864219,"version":"3.54.5"},"reference-count":44,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T00:00:00Z","timestamp":1779062400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T00:00:00Z","timestamp":1779062400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"\u201cThe Leadership project for key technology\u201d of Taiyuan","award":["Z24203001"],"award-info":[{"award-number":["Z24203001"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Real-Time Image Proc"],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1007\/s11554-026-01900-5","type":"journal-article","created":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T03:47:59Z","timestamp":1779076079000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["MDAB-UNet: a lightweight and efficient improved UNet architecture for remote sensing image segmentation"],"prefix":"10.1007","volume":"23","author":[{"given":"Yunhui","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoxu","family":"Wei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongsheng","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,5,18]]},"reference":[{"key":"1900_CR1","doi-asserted-by":"publisher","DOI":"10.1080\/17538947.2024.2328827","author":"J Li","year":"2024","unstructured":"Li, J., Cai, Y., Li, Q., Kou, M., Zhang, T.: A review of remote sensing image segmentation by deep learning methods. Int. J. Digit. Earth (2024). https:\/\/doi.org\/10.1080\/17538947.2024.2328827","journal-title":"Int. J. Digit. Earth"},{"key":"1900_CR2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TGRS.2022.3186634","volume":"60","author":"L Wang","year":"2022","unstructured":"Wang, L., Fang, S., Meng, X., Li, R.: Building extraction with vision transformer. IEEE Trans. Geosci. Remote Sens. 60, 1\u201311 (2022). https:\/\/doi.org\/10.1109\/TGRS.2022.3186634","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"1900_CR3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/LGRS.2021.3086117","volume":"19","author":"R Zhang","year":"2022","unstructured":"Zhang, R., Chen, J., Feng, L., Li, S., Yang, W., Guo, D.: A refined pyramid scene parsing network for polarimetric SAR image semantic segmentation in agricultural areas. IEEE Geosci. Remote Sens. Lett. 19, 1\u20135 (2022). https:\/\/doi.org\/10.1109\/LGRS.2021.3086117","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"1900_CR4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TGRS.2022.3183080","volume":"60","author":"W Han","year":"2022","unstructured":"Han, W., Li, J., Wang, S., Zhang, X., Dong, Y., Fan, R., Zhang, X., Wang, L.: Geological remote sensing interpretation using deep learning feature and an adaptive multisource data fusion network. IEEE Trans. Geosci. Remote Sens. 60, 1\u201314 (2022). https:\/\/doi.org\/10.1109\/TGRS.2022.3183080","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"1900_CR5","doi-asserted-by":"publisher","first-page":"103858","DOI":"10.1016\/j.earscirev.2021.103858","volume":"223","author":"Z Ma","year":"2021","unstructured":"Ma, Z., Mei, G.: Deep learning for geological hazards analysis: data, models, applications, and opportunities. Earth-Sci. Rev. 223, 103858 (2021). https:\/\/doi.org\/10.1016\/j.earscirev.2021.103858","journal-title":"Earth-Sci. Rev."},{"issue":"3","key":"1900_CR6","doi-asserted-by":"publisher","first-page":"1224","DOI":"10.1109\/TGRS.2009.2029338","volume":"48","author":"G Ferraioli","year":"2010","unstructured":"Ferraioli, G.: Multichannel InSAR building edge detection. IEEE Trans. Geosci. Remote Sens. 48(3), 1224\u20131231 (2010). https:\/\/doi.org\/10.1109\/TGRS.2009.2029338","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"issue":"1","key":"1900_CR7","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1109\/TGRS.2012.2234755","volume":"52","author":"J Yuan","year":"2014","unstructured":"Yuan, J., Wang, D., Li, R.: Remote sensing image segmentation by combining spectral and texture features. IEEE Trans. Geosci. Remote Sens. 52(1), 16\u201324 (2014). https:\/\/doi.org\/10.1109\/TGRS.2012.2234755","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"1900_CR8","unstructured":"Simonyan, K., Zisserman, A.: Very Deep Convolutional Networks for Large-Scale Image Recognition. arXiv preprint, abs\/1409.1556, https:\/\/arxiv.org\/abs\/1409.1556 (2014)"},{"key":"1900_CR9","doi-asserted-by":"publisher","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3431\u20133440. https:\/\/doi.org\/10.1109\/CVPR.2015.7298965 (2015)","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"1900_CR10","doi-asserted-by":"publisher","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-Net: Convolutional Networks for Biomedical Image Segmentation. In: Medical Image Computing and Computer-Assisted Intervention, pp. 234\u2013241. https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28 (2015)","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"1900_CR11","unstructured":"Chen, L.C., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.L.: Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs. arXiv preprint (2014)"},{"issue":"4","key":"1900_CR12","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","volume":"40","author":"L-C Chen","year":"2018","unstructured":"Chen, L.-C., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.L.: DeepLab: semantic image segmentation with deep convolutional Nets, Atrous Convolution, and Fully Connected CRFs. IEEE Trans. Pattern Anal. Mach. Intell. 40(4), 834\u2013848 (2018). https:\/\/doi.org\/10.1109\/TPAMI.2017.2699184","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1900_CR13","unstructured":"Chen, L.-C., Papandreou, G., Schroff, F., Adam, H.: Rethinking Atrous Convolution for Semantic Image Segmentation. arXiv preprint, abs\/1706.05587, https:\/\/arxiv.org\/abs\/1706.05587 (2017)"},{"key":"1900_CR14","doi-asserted-by":"publisher","unstructured":"Chen, L.-C., Zhu, Y., Papandreou, G., Schroff, F., Adam, H.: Encoder\u2013Decoder with Atrous Separable Convolution for Semantic Image Segmentation. In: Proceedings of the European Conference on Computer Vision, pp. 833\u2013851. https:\/\/doi.org\/10.1007\/978-3-030-01234-2_49 (2018)","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"1900_CR15","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, L., Polosukhin, I.: Attention is Allyou Need. In: Advances in Neural Information Processing Systems 30, 5998\u20136008 (2017).https:\/\/doi.org\/10.48550\/arXiv.1706.03762"},{"key":"1900_CR16","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., Uszkoreit, J., Houlsby, N.: An Image is Worth $$16\\times 16$$ Words: Transformers for Image Recognition at Scale. arXiv preprint, abs\/2010.11929, https:\/\/arxiv.org\/abs\/2010.11929 (2020)"},{"key":"1900_CR17","doi-asserted-by":"publisher","unstructured":"Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., Guo, B.: Swin Transformer: Hierarchical Vision Transformer using Shifted Windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9992\u201310002. https:\/\/doi.org\/10.1109\/ICCV48922.2021.00986 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"1900_CR18","unstructured":"Xie, E., Wang, W., Yu, Z., Anandkumar, A., Alvarez, J.M., Luo, P.: SegFormer: Simple and Efficient Design forSemantic Segmentation with Transformers. In: Advances in Neural Information Processing Systems 34, 12077\u201312090, (2021). https:\/\/doi.org\/10.48550\/arXiv.2105.15203"},{"key":"1900_CR19","doi-asserted-by":"publisher","first-page":"196","DOI":"10.1016\/j.isprsjprs.2022.06.008","volume":"190","author":"L Wang","year":"2022","unstructured":"Wang, L., Li, R., Zhang, C., Fang, S., Duan, C., Meng, X., Atkinson, P.M.: UNetFormer: a UNet-like transformer for efficient semantic segmentation of remote sensing urban scene imagery. ISPRS J. Photogramm. Remote. Sens. 190, 196\u2013214 (2022). https:\/\/doi.org\/10.1016\/j.isprsjprs.2022.06.008","journal-title":"ISPRS J. Photogramm. Remote. Sens."},{"key":"1900_CR20","unstructured":"Chen, J., Lu, Y., Yu, Q., Luo, X., Adeli, E., Wang, Y., Lu, L., Yuille, A.L., Zhou, Y.: TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation. arXiv preprint, abs\/2102.04306, https:\/\/arxiv.org\/abs\/2102.04306 (2021)"},{"key":"1900_CR21","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TGRS.2023.3314641","volume":"61","author":"H Wu","year":"2023","unstructured":"Wu, H., Huang, P., Zhang, M., Tang, W., Yu, X.: CMTFNet: CNN and multiscale transformer fusion network for remote-sensing image semantic segmentation. IEEE Trans. Geosci. Remote Sens. 61, 1\u201312 (2023). https:\/\/doi.org\/10.1109\/TGRS.2023.3314641","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"1900_CR22","unstructured":"Gu, A., Dao, T.: Mamba: Linear-Time Sequence Modeling with Selective State Spaces. arXiv preprint, abs\/2312.00752, https:\/\/arxiv.org\/abs\/2312.00752 (2023)"},{"key":"1900_CR23","doi-asserted-by":"crossref","unstructured":"Ruan, J., Li, J., Xiang, S.: VM-UNet: Vision Mamba UNet for Medical Image Segmentation. arXiv preprint, 2402.02491, https:\/\/arxiv.org\/abs\/2402.02491 (2024)","DOI":"10.1145\/3767748"},{"key":"1900_CR24","first-page":"1","volume":"22","author":"E Zhu","year":"2024","unstructured":"Zhu, E., Chen, Z., Wang, D., Shi, H., Liu, X., Wang, L.: UNetMamba: an efficient UNet-like Mamba for semantic segmentation of high-resolution remote sensing images. IEEE Geosci. Remote Sens. Lett. 22, 1\u20135 (2024)","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"1900_CR25","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., Albanie, S., Sun, G., Wu, E.: Squeeze-and-Excitation Networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7132\u20137141 (2017)","DOI":"10.1109\/CVPR.2018.00745"},{"key":"1900_CR26","doi-asserted-by":"crossref","unstructured":"Wang, Q., Wu, B., Zhu, P., Li, P., Zuo, W., Hu, Q.: ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11531\u201311539 (2019)","DOI":"10.1109\/CVPR42600.2020.01155"},{"key":"1900_CR27","unstructured":"Jaderberg, M., Simonyan, K., Zisserman, A., Kavukcuoglu, K.: Spatial Transformer Networks. arXiv preprint, abs\/1506.02025, https:\/\/arxiv.org\/abs\/1506.02025 (2015)"},{"key":"1900_CR28","doi-asserted-by":"crossref","unstructured":"Fu, J., Liu, J., Tian, H., Fang, Z., Lu, H.: Dual Attention Network for Scene Segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3141\u20133149 (2018)","DOI":"10.1109\/CVPR.2019.00326"},{"key":"1900_CR29","unstructured":"Woo, S., Park, J., Lee, J.-Y., Kweon, I.-S.: CBAM: Convolutional Block Attention Module. arXiv preprint, abs\/1807.06521, https:\/\/arxiv.org\/abs\/1807.06521 (2018)"},{"key":"1900_CR30","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep Residual Learning for Image Recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2015)","DOI":"10.1109\/CVPR.2016.90"},{"key":"1900_CR31","doi-asserted-by":"publisher","unstructured":"Yu, J., Lin, Z., Yang, J., Shen, X., Lu, X., Huang, T.: Free-Form Image Inpainting With Gated Convolution. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4470\u20134479. https:\/\/doi.org\/10.1109\/ICCV.2019.00457 (2019)","DOI":"10.1109\/ICCV.2019.00457"},{"key":"1900_CR32","doi-asserted-by":"crossref","unstructured":"Liu, H., Jia, C., Shi, F., Cheng, X., Chen, S.: SCSegamba: Lightweight Structure-Aware Vision Mamba for Crack Segmentation in Structures. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 29406\u201329416 (2025)","DOI":"10.1109\/CVPR52734.2025.02738"},{"key":"1900_CR33","doi-asserted-by":"publisher","unstructured":"Li, J., Nie, Q., Fu, W., Lin, Y., Tao, G., Liu, Y., Wang, C.: LORS: Low-Rank Residual Structure for Parameter-Efficient Network Stacking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15866\u201315876. https:\/\/doi.org\/10.1109\/CVPR52733.2024.01502 (2024)","DOI":"10.1109\/CVPR52733.2024.01502"},{"key":"1900_CR34","unstructured":"Wang, J., Zheng, Z., Ma, A., Lu, X., Zhong, Y.: LoveDA: A Remote Sensing Land-Cover Dataset for Domain Adaptive Semantic Segmentation. arXiv preprint, abs\/2110.08733, https:\/\/arxiv.org\/abs\/2110.08733 (2022)"},{"issue":"6","key":"1900_CR35","doi-asserted-by":"publisher","first-page":"964","DOI":"10.3390\/rs10060964","volume":"10","author":"Z Shao","year":"2018","unstructured":"Shao, Z., Yang, K., Zhou, W.: Performance evaluation of single-label and multi-label remote sensing image retrieval using a dense labeling dataset. Remote Sens. 10(6), 964 (2018). https:\/\/doi.org\/10.3390\/rs10060964","journal-title":"Remote Sens."},{"key":"1900_CR36","doi-asserted-by":"publisher","first-page":"318","DOI":"10.1109\/JSTARS.2020.2967473","volume":"13","author":"Z Shao","year":"2020","unstructured":"Shao, Z., Zhou, W., Deng, X., Zhang, M., Cheng, Q.: Multilabel remote sensing image retrieval based on fully convolutional network. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 13, 318\u2013328 (2020). https:\/\/doi.org\/10.1109\/JSTARS.2020.2967473","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"1900_CR37","doi-asserted-by":"publisher","first-page":"3051","DOI":"10.1007\/s11263-021-01515-2","volume":"129","author":"C Yu","year":"2021","unstructured":"Yu, C., Gao, C., Wang, J., Yu, G., Shen, C., Sang, N.: BiSeNet V2: bilateral network with guided aggregation for real-time semantic segmentation. Int. J. Comput. Vis. 129, 3051\u20133068 (2021). https:\/\/doi.org\/10.1007\/s11263-021-01515-2","journal-title":"Int. J. Comput. Vis."},{"issue":"3","key":"1900_CR38","doi-asserted-by":"publisher","first-page":"1131","DOI":"10.1080\/01431161.2022.2030071","volume":"43","author":"R Li","year":"2022","unstructured":"Li, R., Wang, L., Zhang, C., Duan, C., Zheng, S.: A2-FPN for semantic segmentation of fine-resolution remotely sensed images. Int. J. Remote Sens. 43(3), 1131\u20131155 (2022). https:\/\/doi.org\/10.1080\/01431161.2022.2030071","journal-title":"Int. J. Remote Sens."},{"key":"1900_CR39","doi-asserted-by":"publisher","first-page":"7233","DOI":"10.1109\/JSTARS.2024.3375313","volume":"17","author":"H Wu","year":"2024","unstructured":"Wu, H., Zhang, M., Huang, P., Tang, W.: CMLFormer: CNN and multiscale local-context transformer network for remote sensing images semantic segmentation. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 17, 7233\u20137245 (2024). https:\/\/doi.org\/10.1109\/JSTARS.2024.3375313","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"1900_CR40","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1007\/s11554-024-01472-2","volume":"21","author":"C Bai","year":"2024","unstructured":"Bai, C., Zhang, L., Gao, L., Peng, L., Li, P., Yang, L.: Real-time segmentation algorithm of unstructured road scenes based on improved BiSeNet. J. Real-Time Image Process. 21, 91 (2024). https:\/\/doi.org\/10.1007\/s11554-024-01472-2","journal-title":"J. Real-Time Image Process."},{"key":"1900_CR41","doi-asserted-by":"publisher","first-page":"6011405","DOI":"10.1109\/LGRS.2024.3414293","volume":"21","author":"X Ma","year":"2024","unstructured":"Ma, X., Zhang, X., Pun, M.-O.: RS$$^3$$Mamba: visual state space model for remote sensing image semantic segmentation. IEEE Geosci. Remote Sens. Lett. 21, 6011405 (2024). https:\/\/doi.org\/10.1109\/LGRS.2024.3414293","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"1900_CR42","doi-asserted-by":"crossref","unstructured":"Li, J., Cheng, S.: AFENet: an attention-focused feature enhancement network for the efficient semantic segmentation of remote sensing images. Remote Sens. 16, 4392 (2024)","DOI":"10.3390\/rs16234392"},{"key":"1900_CR43","doi-asserted-by":"publisher","first-page":"2204","DOI":"10.1109\/ACCESS.2025.3650188","volume":"14","author":"Z Liang","year":"2026","unstructured":"Liang, Z., Li, M.: ScaleRSNet: advancing remote sensing image segmentation with multi-scale contextual attention mechanisms. IEEE Access 14, 2204\u20132220 (2026). https:\/\/doi.org\/10.1109\/ACCESS.2025.3650188","journal-title":"IEEE Access"},{"key":"1900_CR44","doi-asserted-by":"publisher","first-page":"5624615","DOI":"10.1109\/TGRS.2022.3179739","volume":"60","author":"P He","year":"2022","unstructured":"He, P., Jiao, L., Shang, R., Wang, S., Liu, X., Quan, D., Yang, K., Zhao, D.: MANet: multi-scale aware-relation network for semantic segmentation in aerial scenes. IEEE Trans. Geosci. Remote Sens. 60, 5624615 (2022). https:\/\/doi.org\/10.1109\/TGRS.2022.3179739","journal-title":"IEEE Trans. Geosci. Remote Sens."}],"container-title":["Journal of Real-Time Image Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11554-026-01900-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11554-026-01900-5","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11554-026-01900-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T13:40:29Z","timestamp":1782394829000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11554-026-01900-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,18]]},"references-count":44,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,6]]}},"alternative-id":["1900"],"URL":"https:\/\/doi.org\/10.1007\/s11554-026-01900-5","relation":{},"ISSN":["1861-8200","1861-8219"],"issn-type":[{"value":"1861-8200","type":"print"},{"value":"1861-8219","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,18]]},"assertion":[{"value":"21 November 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 April 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 May 2026","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 no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"103"}}