遥感图像半监督语义分割方法研究综述

doi:10.3778/j.issn.1002-8331.2504-0043

摘要/Abstract

摘要： 遥感图像语义分割作为遥感技术领域的重要研究方向，旨在对遥感图像进行像素级的分割并精确分类至预定义的地物类别中。传统方法依赖于大量的像素级标注数据，但人工标注耗时且费力。为解决这一问题，半监督学习方法被引入，通过结合少量标注样本和大量无标注数据进行模型训练，显著降低了标注需求。通过分析和总结近年来关于遥感图像半监督语义分割的相关研究，系统梳理现有方法的分类体系，并深入剖析其优势与不足：从核心思想和技术策略出发，对现有的遥感图像半监督语义分割方法进行了体系归纳和类别划分，并分别讨论了其创新与局限性；介绍了遥感图像半监督语义分割研究广泛使用的数据集；基于常用实验设置和评价指标，在不同数据集上开展了多方法对比分析；探讨了遥感图像半监督语义分割的未来研究趋势。

关键词: 遥感图像, 语义分割, 深度学习, 半监督学习

Abstract: As an important research direction in the field of remote sensing technology, semantic segmentation of remote sensing images aims to segment remote sensing images at the pixel level and accurately classify them into predefined ground object categories. Traditional methods rely on a large number of pixel-level annotation data, but manual annotation is time-consuming and laborious. In order to solve this problem, a semi-supervised learning method is introduced. By combining a small number of labeled samples and a large number of unlabeled data for model training, the labeling requirements are significantly reduced. By analyzing and summarizing the related research on semi-supervised semantic segmentation of remote sensing images in recent years, the classification system of existing methods is systematically sorted out, and its advantages and disadvantages are deeply analyzed. Starting from the core ideas and technical strategies, the existing semi-supervised semantic segmentation methods of remote sensing images are systematically summarized and classified, and their innovations and limitations are discussed respectively. The datasets widely used in the research of semi-supervised semantic segmentation of remote sensing images are introduced. Based on the commonly used experimental settings and evaluation indicators, multi-method comparative analysis is carried out on different datasets. Finally, the future research trends of semi-supervised semantic segmentation of remote sensing images are discussed.

Key words: remote sensing image, semantic segmentation, deep learning, semi-supervised learning

董亦凡, 孙文礼, 赵洋, 黄平平. 遥感图像半监督语义分割方法研究综述[J]. 计算机工程与应用, 2025, 61(24): 86-102.

DONG Yifan, SUN Wenli, ZHAO Yang, HUANG Pingping. Survey on Semi-Supervised Semantic Segmentation Methods for Remote Sensing Images[J]. Computer Engineering and Applications, 2025, 61(24): 86-102.

参考文献

[1] ZHU F Z, CUI J Y, ZHU B, et al. Semantic segmentation of urban street scene images based on improved U-Net network[J]. Optoelectronics Letters, 2023, 19(3): 179-185.
[2] AJIBOLA S, CABRAL P. A systematic literature review and bibliometric analysis of semantic segmentation models in land cover mapping[J]. Remote Sensing, 2024, 16(12): 2222.
[3] ZHAO Y, WANG S C, LIU S Y, et al. Real time light-independent slope-failure monitoring using LiDAR and 2D-3D semantic segmentation[C]//Proceedings of the 2022 IEEE Sensors. Piscataway: IEEE, 2022: 1-4.
[4] DU B W, ZHAO Z R, HU X, et al. Landslide susceptibility prediction based on image semantic segmentation[J]. Computers & Geosciences, 2021, 155: 104860.
[5] 孙博远, 刘夏雷, 侯淇彬. 基于深度学习的半监督语义分割综述[J]. 北京交通大学学报, 2024, 48(2): 10-22.
SUN B Y, LIU X L, HOU Q B. Review of deep learning-based semi-supervised semantic segmentation[J]. Journal of Beijing Jiaotong University, 2024, 48(2): 10-22.
[6] 吴坚. 半监督的语义分割综述[J]. 电脑知识与技术, 2021, 17(32): 131-133.
WU J. A survey of semi-supervised semantic segmentation[J]. Computer Knowledge and Technology, 2021, 17(32): 131-133.
[7] 项伟康, 周全, 崔景程, 等. 基于深度学习的弱监督语义分割方法综述[J]. 中国图象图形学报, 2024, 29(5): 1146-1168.
XIANG W K, ZHOU Q, CUI J C, et al. Weakly supervised semantic segmentation based on deep learning[J]. Journal of Image and Graphics, 2024, 29(5): 1146-1168.
[8] RAN L Y, LI Y L, LIANG G Q, et al. Pseudo labeling methods for semi-supervised semantic segmentation: a review and future perspectives[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2025, 35(4): 3054-3080.
[9] HAO S J, ZHOU Y, GUO Y R. A brief survey on semantic segmentation with deep learning[J]. Neurocomputing, 2020, 406: 302-321.
[10] ZHANG M, ZHOU Y, ZHAO J Q, et al. A survey of semi- and weakly supervised semantic segmentation of images[J]. Artificial Intelligence Review, 2020, 53(6): 4259-4288.
[11] LU H, LIU Q, LIU X D, et al. A survey of semantic construction and application of satellite remote sensing images and data[J]. Journal of Organizational and End User Computing, 2021, 33(6): 1-20.
[12] YU A Z, QUAN Y J, YU R, et al. Deep learning methods for semantic segmentation in remote sensing with small data: a survey[J]. Remote Sensing, 2023, 15(20): 4987.
[13] WANG X, JIN X Z, DAI Z, et al. Deep learning-based methods for road extraction from remote sensing images: a vision, survey, and future directions[J]. IEEE Geoscience and Remote Sensing Magazine, 2025, 13(1): 55-78.
[14] HUANG L W, JIANG B T, LV S Y, et al. Deep-learning-based semantic segmentation of remote sensing images: a survey[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2024, 17: 8370-8396.
[15] HE Y J, WANG J F, LIAO C H, et al. ClassHyPer: ClassMix-based hybrid perturbations for deep semi-supervised semantic segmentation of remote sensing imagery[J]. Remote Sensing, 2022, 14(4): 879.
[16] ZHANG M M, XUE Y A, ZHAN Y Y, et al. Semi-supervised semantic segmentation-based remote sensing identification method for winter wheat planting area extraction[J]. Agronomy, 2023, 13(12): 2868.
[17] MIAO W, XU Z, GENG J, et al. ECAE: edge-aware class activation enhancement for semisupervised remote sensing image semantic segmentation[J]. IEEE Transactions on Geoscience and Remote Sensing, 2023, 61: 5625014.
[18] XIN Y, FAN Z D, QI X Y, et al. Enhancing semi-supervised semantic segmentation of remote sensing images via feature perturbation-based consistency regularization methods[J]. Sensors, 2024, 24(3): 730.
[19] XIAO R, WANG Y Z, TAO C. Fine-grained road scene understanding from aerial images based on semisupervised semantic segmentation networks[J]. IEEE Geoscience and Remote Sensing Letters, 2022, 19: 3001705.
[20] WANG S W, SUN X, CHEN C R, et al. Semi-supervised semantic segmentation for remote sensing images via multiscale uncertainty consistency and cross-teacher student atten-tion[J]. IEEE Transactions on Geoscience and Remote Sen-sing, 2025, 63: 5517115.
[21] LV L, ZHANG L F. Advancing data-efficient exploitation for semi-supervised remote sensing images semantic segmentation[J]. IEEE Transactions on Geoscience and Remote Sensing, 2024, 62: 5619213.
[22] CUI M T, LI K, LI Y L, et al. Semi-supervised semantic segmentation of remote sensing images based on dual cross-entropy consistency[J]. Entropy, 2023, 25(4): 681.
[23] GUO Y J, WANG F, XIANG Y M, et al. Semisupervised sem-antic segmentation with certainty-aware consistency training for remote sensing imagery[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2023, 16: 2900-2914.
[24] BAI L B, WANG H Y, ZHANG X Y, et al. AP-semi: impro-ving the semi-supervised semantic segmentation for VHR images through adaptive data augmentation and prototypical sample guidance[J]. IEEE Transactions on Geoscience and Remote Sensing, 2024, 62: 5631813.
[25] XIN Y, FAN Z D, QI X Y, et al. Confidence-weighted dual-teacher networks with biased contrastive learning for semi-supervised semantic segmentation in remote sensing images[J]. IEEE Transactions on Geoscience and Remote Sensing, 2024, 62: 5614416.
[26] LU Y J, ZHANG Y J, CUI Z W, et al. Multi-dimensional manifolds consistency regularization for semi-supervised remote sensing semantic segmentation[J]. Knowledge-Based Systems, 2024, 299: 112032.
[27] ZHANG B, ZHANG Y J, LI Y S, et al. Semi-supervised deep learning via transformation consistency regularization for remote sensing image semantic segmentation[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2023, 16: 5782-5796.
[28] YUN S, HAN D, CHUN S, et al. CutMix: regularization strategy to train strong classifiers with localizable features[C]//Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision. Piscataway: IEEE, 2020: 6022-6031.
[29] OLSSON V, TRANHEDEN W, PINTO J, et al. ClassMix: segmentation-based data augmentation for semi-supervised learning[C]//Proceedings of the 2021 IEEE Winter Conference on Applications of Computer Vision. Piscataway: IEEE, 2021: 1368-1377.
[30] ARAZO E, ORTEGO D, ALBERT P, et al. Pseudo-labeling and confirmation bias in deep semi-supervised learning[C]//Proceedings of the 2020 International Joint Conference on Neural Networks. Piscataway: IEEE, 2020: 1-8.
[31] LI Y B, YI Z Y, WANG Y B, et al. Adaptive context transformer for semisupervised remote sensing image segmentation[J]. IEEE Transactions on Geoscience and Remote Sensing, 2023, 61: 5621714.
[32] QI X Y, MAO Y Q, ZHANG Y D, et al. PICS: paradigms integration and contrastive selection for semisupervised remote sensing images semantic segmentation[J]. IEEE Transactions on Geoscience and Remote Sensing, 2023, 61: 5602119.
[33] SUN X, SHI A J, HUANG H, et al. BAS-net: boundary-aware semi-supervised semantic segmentation network for very high resolution remote sensing images[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2020, 13: 5398-5413.
[34] HAN W Q, JIANG W, GENG J, et al. Difference-complementary learning and label reassignment for multimodal semi-supervised semantic segmentation of remote sensing images[J]. IEEE Transactions on Image Processing, 2025, 34: 566-580.
[35] LI L H, ZHANG W J, ZHANG X Y, et al. Semi-supervised remote sensing image semantic segmentation method based on deep learning[J]. Electronics, 2023, 12(2): 348.
[36] SARPONG K, QIN Z, ADDO D, et al. Semi-supervised semantic segmentation in remote sensing images using active learning and deep global second order pooling network[C]//Proceedings of the 2023 20th International Computer Conference on Wavelet Active Media Technology and Information Processing. Piscataway: IEEE, 2024: 1-9.
[37] CHEN J F, SUN B Y, WANG L Z, et al. Semi-supervised sema-ntic segmentation framework with pseudo supervisions for land-use/land-cover mapping in coastal areas[J]. International Journal of Applied Earth Observation and Geoinformation, 2022, 112: 102881.
[38] GAO L P, ZHOU Y Q, TIAN J T, et al. MCMCNet: a semi-supervised road extraction network for high-resolution remote sensing images via multiple consistency and multitask constraints[J]. IEEE Transactions on Geoscience and Remote Sensing, 2024, 62: 4410416.
[39] WANG J X, DING C H Q, CHEN S B, et al. Semi-supervised remote sensing image semantic segmentation via consistency regularization and average update of pseudo-label[J]. Remote Sensing, 2020, 12(21): 3603.
[40] WANG J X, CHEN S B, DING C H Q, et al. RanPaste: paste consistency and pseudo label for semisupervised remote sensing image semantic segmentation[J]. IEEE Transactions on Geoscience and Remote Sensing, 2022, 60: 2002916.
[41] ZHANG L J, YANG Z C, ZHOU G X, et al. MDMASNet: a dual-task interactive semi-supervised remote sensing image segmentation method[J]. Signal Processing, 2023, 212: 109152.
[42] ZHENG Y L, YANG M Y, WANG M, et al. Semi-supervised adversarial semantic segmentation network using transformer and multiscale convolution for high-resolution remote sensing imagery[J]. Remote Sensing, 2022, 14(8): 1786.
[43] ZHI H B, YANG B H, ZHU Y. Collaborative wheat lodging segmentation semi-supervised learning model based on RSE-BiSeNet using UAV imagery[J]. Agronomy, 2023, 13(11): 2772.
[44] ZHANG L, TAN Z S, ZHENG Y Z, et al. A bias correction semi-supervised semantic segmentation framework for remote sensing images[J]. IEEE Transactions on Geoscience and Remote Sensing, 2025, 63: 5604414.
[45] FU Y J, WANG M Y, VIVONE G, et al. An alternating guidance with cross-view teacher student framework for remote sensing semi-supervised semantic segmentation[J]. IEEE Transactions on Geoscience and Remote Sensing, 2025, 63: 4402012.
[46] GAO K L, YU A Z, YOU X, et al. Cross-domain multi-prototypes with contradictory structure learning for semi-supervised domain adaptation segmentation of remote sensing images[J]. Remote Sensing, 2023, 15(13): 3398.
[47] YANG Z J, YAN Z Y, DIAO W H, et al. Label propagation and contrastive regularization for semisupervised semantic segmentation of remote sensing images[J]. IEEE Transactions on Geoscience and Remote Sensing, 2023, 61: 5609818.
[48] WANG J X, CHEN S B, DING C H Q, et al. Semi-supervised semantic segmentation of remote sensing images with iterative contrastive network[J]. IEEE Geoscience and Remote Sensing Letters, 2022, 19: 2504005.
[49] GOODFELLOW I J, POUGET-ABADIE J, MIRZA M, et al. Generative adversarial nets[C]//Proceedings of the 28th Conference on Neural Information Processing Systems, 2014: 2672-2680.
[50] CHEN H, LI Z H, WU J J, et al. SemiRoadExNet: a semi-supervised network for road extraction from remote sensing imagery via adversarial learning[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2023, 198: 169-183.
[51] NIE W, GOU P, LIU Y, et al. A semi-supervised image segmentation method based on generative adversarial network[C]//Proceedings of the 2022 IEEE 10th Joint International Information Technology and Artificial Intelligence Conference. Piscataway: IEEE, 2022: 1217-1223.
[52] WANG J Q, LIU B, ZHOU Y, et al. Semisupervised multiscale generative adversarial network for semantic segmentation of remote sensing image[J]. IEEE Geoscience and Remote Sensing Letters, 2022, 19: 8003805.
[53] LI J H, SUN B, LI S T, et al. Semisupervised semantic segmentation of remote sensing images with consistency self-training[J]. IEEE Transactions on Geoscience and Remote Sensing, 2022, 60: 5615811.
[54] CHEN L C, PAPANDREOU G, KOKKINOS I, et al. DeepLab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2018, 40(4): 834-848.
[55] LU W X, JIN J D, SUN X, et al. Semi-supervised semantic generative networks for remote sensing image segmentation[C]//Proceedings of the 2023 IEEE International Geoscience and Remote Sensing Symposium. Piscataway: IEEE, 2023: 6386-6389.
[56] JIN J D, LU W X, YU H F, et al. Dynamic and adaptive self-training for semi-supervised remote sensing image semantic segmentation[J]. IEEE Transactions on Geoscience and Remote Sensing, 2024, 62: 5639814.
[57] YU A Z, LIU B, CAO X F, et al. Pixel-level self-supervised learning for semi-supervised building extraction from remote sensing images[J]. IEEE Geoscience and Remote Sensing Letters, 2022, 19: 2507105.
[58] JIANG Y, LU W X, GUO Z. Multi-stage semi-supervised transformer for remote sensing semantic segmentation with various data augmentation[C]//Proceedings of the 2023 IEEE International Geoscience and Remote Sensing Symposium. Piscataway: IEEE, 2023: 6924-6927.
[59] LU X Q, JIAO L C, LIU F, et al. Simple and efficient: a semisupervised learning framework for remote sensing image semantic segmentation[J]. IEEE Transactions on Geoscience and Remote Sensing, 2022, 60: 5543516.
[60] LUO Y, SUN B, LI S T, et al. Hierarchical augmentation and region-aware contrastive learning for semi-supervised semantic segmentation of remote sensing images[J]. IEEE Transactions on Geoscience and Remote Sensing, 2025, 63: 4401311.
[61] ROTTENSTEINER F, SOHN G, GERKE M, et al. Results of the ISPRS benchmark on urban object detection and 3D building reconstruction[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2014, 93: 256-271.
[62] ZAMIR S W, ARORA A, GUPTA A, et al. iSAID: a large-scale dataset for instance segmentation in aerial images[J]. arXiv:abs/1905.12886, 2019.
[63] XIA G S, BAI X, DING J, et al. DOTA: a large-scale dataset for object detection in aerial images[C]//Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2018: 3974-3983.
[64] TONG X Y, XIA G S, LU Q K, et al. Land-cover classification with high-resolution remote sensing images using transferable deep models[J]. Remote Sensing of Environment, 2020, 237: 111322.
[65] DEMIR I, KOPERSKI K, LINDENBAUM D, et al. DeepGlobe 2018: a challenge to parse the Earth through satellite images[C]//Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops. Piscataway: IEEE, 2018: 172-181.