{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,14]],"date-time":"2026-03-14T18:07:02Z","timestamp":1773511622783,"version":"3.50.1"},"reference-count":39,"publisher":"MDPI AG","issue":"21","license":[{"start":{"date-parts":[[2024,10,23]],"date-time":"2024-10-23T00:00:00Z","timestamp":1729641600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"National Defense Science and Technology Outstanding Youth Science Fund","award":["2021-JCJQ-ZQ-017"],"award-info":[{"award-number":["2021-JCJQ-ZQ-017"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>Road extraction techniques based on remote sensing image have significantly advanced. Currently, fully supervised road segmentation neural networks based on remote sensing images require a significant number of densely labeled road samples, limiting their applicability in large-scale scenarios. Consequently, semi-supervised methods that utilize fewer labeled data have gained increasing attention. However, the imbalance between a small quantity of labeled data and a large volume of unlabeled data leads to local detail errors and overall cognitive mistakes in semi-supervised road extraction. To address this challenge, this paper proposes a novel consistency self-training semi-supervised method (CSSnet), which effectively learns from a limited number of labeled data samples and a large amount of unlabeled data. This method integrates self-training semi-supervised segmentation with semi-supervised classification. The semi-supervised segmentation component relies on an enhanced generative adversarial network for semantic segmentation, which significantly reduces local detail errors. The semi-supervised classification component relies on an upgraded mean-teacher network to handle overall cognitive errors. Our method exhibits excellent performance with a modest amount of labeled data. This study was validated on three separate road datasets comprising high-resolution remote sensing satellite images and UAV photographs. Experimental findings showed that our method consistently outperformed state-of-the-art semi-supervised methods and several classic fully supervised methods.<\/jats:p>","DOI":"10.3390\/rs16213945","type":"journal-article","created":{"date-parts":[[2024,10,23]],"date-time":"2024-10-23T09:07:04Z","timestamp":1729674424000},"page":"3945","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Consistency Self-Training Semi-Supervised Method for Road Extraction from Remote Sensing Images"],"prefix":"10.3390","volume":"16","author":[{"given":"Xingjian","family":"Gu","sequence":"first","affiliation":[{"name":"College of Artificial Intelligence, Nanjing Agricultural University, Nanjing 210095, China"}]},{"given":"Supeng","family":"Yu","sequence":"additional","affiliation":[{"name":"College of Artificial Intelligence, Nanjing Agricultural University, Nanjing 210095, China"}]},{"given":"Fen","family":"Huang","sequence":"additional","affiliation":[{"name":"College of Artificial Intelligence, Nanjing Agricultural University, Nanjing 210095, China"}]},{"given":"Shougang","family":"Ren","sequence":"additional","affiliation":[{"name":"College of Artificial Intelligence, Nanjing Agricultural University, Nanjing 210095, China"}]},{"given":"Chengcheng","family":"Fan","sequence":"additional","affiliation":[{"name":"Innovation Academy for Microsatellites of CAS, Shanghai 201210, China"},{"name":"Shanghai Engineering Center for Microsatellites, Shanghai 201210, China"}]}],"member":"1968","published-online":{"date-parts":[[2024,10,23]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"2207","DOI":"10.1109\/JPROC.2016.2598228","article-title":"Big Data for Remote Sensing: Challenges and Opportunities","volume":"104","author":"Chi","year":"2016","journal-title":"Proc. IEEE"},{"key":"ref_2","first-page":"206","article-title":"Automatic Road Network Recognition and Extraction for Urban Planning","volume":"3","author":"Bong","year":"2009","journal-title":"World Acad. Sci. Eng. Technol. Int. J. Civ. Environ. Struct. Constr. Archit. Eng."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Manandhar, P., Marpu, P.R., Aung, Z., and Melgani, F. (2019). Towards Automatic Extraction and Updating of VGI-Based Road Networks Using Deep Learning. Remote Sens., 11.","DOI":"10.3390\/rs11091012"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"6306","DOI":"10.1016\/j.matpr.2021.05.537","article-title":"Road extraction using Aerial images for future Navigation","volume":"47","year":"2021","journal-title":"Mater. Today Proc."},{"key":"ref_5","first-page":"102833","article-title":"Road extraction in remote sensing data: A survey","volume":"112","author":"Chen","year":"2022","journal-title":"Int. J. Appl. Earth Obs. Geoinf."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Hu, A., Chen, S., Wu, L., Xie, Z., Qiu, Q., and Xu, Y. (2021). WSGAN: An Improved Generative Adversarial Network for Remote Sensing Image Road Network Extraction by Weakly Supervised Processing. Remote Sens., 13.","DOI":"10.3390\/rs13132506"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"5602312","DOI":"10.1109\/TGRS.2021.3061213","article-title":"Scribble-Based Weakly Supervised Deep Learning for Road Surface Extraction From Remote Sensing Images","volume":"60","author":"Wei","year":"2022","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"155","DOI":"10.1016\/j.isprsjprs.2019.10.001","article-title":"Spatial information inference net: Road extraction using road-specific contextual information","volume":"158","author":"Tao","year":"2019","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Dai, J., He, K., and Sun, J. (2015). BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation. arXiv.","DOI":"10.1109\/ICCV.2015.191"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Bearman, A., Russakovsky, O., Ferrari, V., and Li, F.-F. (2015). What\u2019s the Point: Semantic Segmentation with Point Supervision. arXiv.","DOI":"10.1007\/978-3-319-46478-7_34"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Khoreva, A., Benenson, R., Hosang, J., Hein, M., and Schiele, B. (2016). Simple Does It: Weakly Supervised Instance and Semantic Segmentation. arXiv.","DOI":"10.1109\/CVPR.2017.181"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Ahn, J., and Kwak, S. (2018). Learning Pixel-level Semantic Affinity with Image-level Supervision for Weakly Supervised Semantic Segmentation. arXiv.","DOI":"10.1109\/CVPR.2018.00523"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Wu, S., Du, C., Chen, H., Xu, Y., Guo, N., and Jing, N. (2019). Road Extraction from Very High Resolution Images Using Weakly labeled OpenStreetMap Centerline. ISPRS Int. J. Geo-Inf., 8.","DOI":"10.3390\/ijgi8110478"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Zhang, J., Yu, X., Li, A., Song, P., Liu, B., and Dai, Y. (2020). Weakly-Supervised Salient Object Detection via Scribble Annotations. arXiv.","DOI":"10.1109\/CVPR42600.2020.01256"},{"key":"ref_15","first-page":"549","article-title":"Weakly Supervised Network with Scribble-Supervised and Edge-Mask for Road Extraction from High-Resolution Remote Sensing Images","volume":"79","author":"Yu","year":"2024","journal-title":"Comput. Mater. Contin."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"4501013","DOI":"10.1109\/TGRS.2021.3059088","article-title":"Weakly Supervised Road Segmentation in High-Resolution Remote Sensing Images Using Point Annotations","volume":"60","author":"Lian","year":"2022","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"1856","DOI":"10.1109\/LGRS.2014.2312000","article-title":"A Semi-Automatic Method for Road Centerline Extraction From VHR Images","volume":"11","author":"Miao","year":"2014","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"6805","DOI":"10.1109\/TGRS.2017.2734697","article-title":"Unsupervised-Restricted Deconvolutional Neural Network for Very High Resolution Remote-Sensing Image Classification","volume":"55","author":"Tao","year":"2017","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"2341","DOI":"10.1109\/JSTARS.2021.3049905","article-title":"MapGen-GAN: A Fast Translator for Remote Sensing Image to Map Via Unsupervised Adversarial Learning","volume":"14","author":"Song","year":"2021","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"ref_20","unstructured":"Hung, W.C., Tsai, Y.H., Liou, Y.T., Lin, Y.Y., and Yang, M.H. (2018). Adversarial Learning for Semi-Supervised Semantic Segmentation. arXiv."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Desai, S., and Ghose, D. (2022, January 3\u20138). Active Learning for Improved Semi-Supervised Semantic Segmentation in Satellite Images. Proceedings of the 2022 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), Waikoloa, HI, USA.","DOI":"10.1109\/WACV51458.2022.00155"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"He, Y., Wang, J., Liao, C., Shan, B., and Zhou, X. (2022). ClassHyPer: ClassMix-Based Hybrid Perturbations for Deep Semi-Supervised Semantic Segmentation of Remote Sensing Imagery. Remote Sens., 14.","DOI":"10.3390\/rs14040879"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"5570","DOI":"10.1109\/JSTARS.2022.3188025","article-title":"FMWDCT: Foreground Mixup Into Weighted Dual-Network Cross Training for Semisupervised Remote Sensing Road Extraction","volume":"15","author":"You","year":"2022","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"ref_24","unstructured":"Zou, Y., Zhang, Z., Zhang, H., Li, C.L., Bian, X., Huang, J.B., and Pfister, T. (2020). PseudoSeg: Designing Pseudo Labels for Semantic Segmentation. arXiv."},{"key":"ref_25","first-page":"5615811","article-title":"Semisupervised Semantic Segmentation of Remote Sensing Images With Consistency Self-Training","volume":"60","author":"Li","year":"2022","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"2284","DOI":"10.1109\/JSTARS.2021.3053603","article-title":"Reconstruction Bias U-Net for Road Extraction From Optical Remote Sensing Images","volume":"14","author":"Chen","year":"2021","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"ref_27","unstructured":"Zhang, B., Wang, Y., Hou, W., Wu, H., Wang, J., Okumura, M., and Shinozaki, T. (2021). FlexMatch: Boosting Semi-Supervised Learning with Curriculum Pseudo Labeling. arXiv."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Sun, C., Wu, J., Chen, H., and Du, C. (2022). SemiSANet: A Semi-Supervised High-Resolution Remote Sensing Image Change Detection Model Using Siamese Networks with Graph Attention. Remote Sens., 14.","DOI":"10.3390\/rs14122801"},{"key":"ref_29","unstructured":"Mittal, S., Tatarchenko, M., and Brox, T. (2019). Semi-Supervised Semantic Segmentation with High- and Low-level Consistency. arXiv."},{"key":"ref_30","unstructured":"Tarvainen, A., and Valpola, H. (2017). Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results. arXiv."},{"key":"ref_31","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, L., and Polosukhin, I. (2017). Attention Is All You Need. arXiv."},{"key":"ref_32","unstructured":"Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., and Chen, X. (2016). Improved Techniques for Training GANs. arXiv."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"353","DOI":"10.1016\/j.isprsjprs.2021.03.016","article-title":"A Global Context-aware and Batch-independent Network for road extraction from VHR satellite imagery","volume":"175","author":"Zhu","year":"2021","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"6054","DOI":"10.1109\/TGRS.2017.2719738","article-title":"Learning Aerial Image Segmentation From Online Maps","volume":"55","author":"Kaiser","year":"2017","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Zhou, L., Zhang, C., and Wu, M. (2018, January 18\u201322). D-LinkNet: LinkNet with Pretrained Encoder and Dilated Convolution for High Resolution Satellite Imagery Road Extraction. Proceedings of the 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Salt Lake City, UT, USA.","DOI":"10.1109\/CVPRW.2018.00034"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Qi, J., Tao, C., Wang, H., Tang, Y., and Cui, Z. (August, January 28). Spatial Information Inference Net: Road Extraction Using Road-Specific Contextual Information. Proceedings of the IGARSS 2019\u20142019 IEEE International Geoscience and Remote Sensing Symposium, Yokohama, Japan.","DOI":"10.1109\/IGARSS.2019.8900507"},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Yang, L., Zhuo, W., Qi, L., Shi, Y., and Gao, Y. (2021). ST++: Make Self-training Work Better for Semi-supervised Semantic Segmentation. arXiv.","DOI":"10.1109\/CVPR52688.2022.00423"},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., and Brox, T. (2015). U-Net: Convolutional Networks for Biomedical Image Segmentation. arXiv.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref_39","unstructured":"Chen, L.C., Papandreou, G., Kokkinos, I., Murphy, K., and Yuille, A.L. (2016). DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs. arXiv."}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/16\/21\/3945\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T16:18:46Z","timestamp":1760113126000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/16\/21\/3945"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,23]]},"references-count":39,"journal-issue":{"issue":"21","published-online":{"date-parts":[[2024,11]]}},"alternative-id":["rs16213945"],"URL":"https:\/\/doi.org\/10.3390\/rs16213945","relation":{},"ISSN":["2072-4292"],"issn-type":[{"value":"2072-4292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,23]]}}}