The DOI matches its Crossref record; 23 of the 27 references it cites were found in a registry or an index.
Road Extraction by Deep Residual U-Net
Open accessAbstract
Road extraction from aerial images has been a hot research topic in the field of remote sensing image analysis. In this letter, a semantic segmentation neural network, which combines the strengths of residual learning and U-Net, is proposed for road area extraction. The network is built with residual units and has similar architecture to that of U-Net. The benefits of this model are twofold: first, residual units ease training of deep networks. Second, the rich skip connections within the network could facilitate information propagation, allowing us to design networks with fewer parameters, however, better performance. We test our network on a public road data set and compare it with U-Net and other two state-of-the-art deep-learning-based road extraction methods. The proposed approach outperforms all the comparing methods, which demonstrates its superiority over recently developed state of the arts.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“In this study, we opt for a deep residual U-Net [15], [44], which has already been successfully used for retinal OCT images.”
From Interactive Deep Learning-Based Retinal OCT Layer Segmentation Refinement by Regressing Translation Maps (2024) · cites this paper as [44]
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · cited 5×
“This somehow shares similar idea to that of residual neural network [21].”
BackgroundMethodResultInfluentialVery Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1409.1556 · Cited by 114,148 · cited 1×
“Recently, lots of works have suggested that a deeper network would have better performance [19], [20].”
BackgroundU-Net: Convolutional Networks for Biomedical Image Segmentation
Ronneberger, O., Fischer, P., & Brox, T. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-24574-4_28 · Cited by 99,404 · cited 7×
“1) U-Net: In semantic segmentation, to get a finer result, it is very important to use low-level details, while retaining high-level semantic information [23], [24].”
BackgroundMethodInfluentialFaster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2577031 · Cited by 73,472 · cited 1×
“of-the-art performance on a variety of computer vision tasks, such as scene recognition [13] and object detection [14].”
BackgroundFaster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2015) · arXiv · doi:10.48550/arxiv.1506.01497 · Cited by 70,812
Going deeper with convolutions
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298594 · Cited by 48,562 · cited 1×
“Recently, lots of works have suggested that a deeper network would have better performance [19], [20].”
BackgroundFully convolutional networks for semantic segmentation
Long, J., Shelhamer, E., & Darrell, T. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298965 · Cited by 38,834 · cited 3×
“One way to solve this problem is employing a pretrained network and then finetuning it on the target data set, as done in [23].”
BackgroundMethodIdentity mappings in deep residual networks
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46493-0_38 · Cited by 10,741 · cited 2×
“[22] presented a detailed discussion on impacts of different combinations and suggested a full preactivation design as shown in Fig.”
BackgroundMethodDeep Learning for Remote Sensing Data: A Technical Tutorial on the State of the Art
Zhang, L., Zhang, L., & Du, B. (2016) · IEEE Geoscience and Remote Sensing Magazine · doi:10.1109/mgrs.2016.2540798 · Cited by 2,272
Learning to Detect Roads in High-Resolution Aerial Images
Mnih, V., & Hinton, G. E. (2010) · European Conference on Computer Vision · doi:10.1007/978-3-642-15567-3_16 · Cited by 681 · cited 11×
“To demonstrate the accuracy and efficiency of the proposed deep ResUnet, we test it on Massachusetts roads data set2 and compare it with three state of the art methods, including Mnih’s [2] method, Saito’s method [5], and U-Net [24].”
BackgroundMethodResultInfluential
Flagged first, then by citations
4 of the 27 references couldn’t be matched to a known paper.
Research works printed but not linked: 4
- zhou, 2014, Learning deep features for scene recognition using places database, Proc NIPS, 487
- mnih, 2012, Learning to label aerial images from noisy data, Proc ICML, 567
- ehrig, 2005, Relaxed precision and recall for ontology matching, Proc Workshop Integr Ontol, 25
- chollet, 2015, Keras
Cited by
Sorted by citations
Items 101–200 of 1,001
AdaResU-Net: Multiobjective adaptive convolutional neural network for medical image segmentation
Baldeon-Calisto, M., & Lai-Yuen, S. K. (2019) · Neurocomputing · doi:10.1016/j.neucom.2019.01.110 · Cited by 136
A Survey of Computer Vision Methods for 2D Object Detection from Unmanned Aerial Vehicles
Cazzato, D., Cimarelli, C., Sánchez-López, J. L., Voos, H., & Leo, M. (2020) · Journal of Imaging · doi:10.3390/jimaging6080078 · Cited by 147
DDU-Net: Dual-Decoder-U-Net for Road Extraction Using High-Resolution Remote Sensing Images
Wang, Y., Peng, Y., Liu, X.-R., Li, W., Alexandropoulos, G. C., Yu, J., Ge, D., & Xiang, W.-X. (2022) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2022.3197546 · Cited by 128
“For example, ResUnet [23] replaces the common convolution layer by a residual unit in the encoder of U-Net; Stacked U-Nets [24] stack two U-Nets to yield road structure features and segmentation mask, respectively; D-LinkNet [16] improves the original LinkNet by adding a cascaded dilated…”
Self-citationNL-LinkNet: Toward Lighter But More Accurate Road Extraction With Nonlocal Operations
Wang, Y., Seo, J., & Jeon, T. (2019) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2021.3050477 · Cited by 127
Self-citationGlobal context based automatic road segmentation via dilated convolutional neural network
Lan, M., Zhang, Y., Zhang, L., & Du, B. (2020) · Information Sciences · doi:10.1016/j.ins.2020.05.062 · Cited by 147
Spatial Information Inference Net: Road Extraction Using Road-Specific Contextual Information
Qi, J., Tao, C., Wang, H., Tang, Y.-Q., & Cui, Z. (2019) · IEEE International Geoscience and Remote Sensing Symposium · doi:10.1109/igarss.2019.8900507 · Cited by 123
“On each dataset, our SIIS will be integrated in DeepLabv3+ as SII-Net and compares to three states of the art methods, including Deep Residual U-Net [4], original DeepLabv3+ [8] and U-Net [11].”
BackgroundMethodResultInfluentialGao, L., Wei-dong, S., Dai, J., & Chen, Y. (2019) · Remote Sensing · doi:10.3390/rs11050552 · Cited by 138
“Zhang et al. [1] combined deep residual networks (ResNets) [25] and U Net [26] which allowed networks to be designed with few Alexander V. Buslaev et al. [27] proposed a fully convolutional neural network of the U-Net family via ResNet34 and decoding adapted from vanilla U-Net. parameters but…”
BackgroundMethodYao, W., Zhang, K., & Ji, S. (2020) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2020.2991733 · Cited by 151
“We compared our proposed algorithms with U-Net [13], ResUnet [19], ASPP-Unet [20], RCNN-Unet [22], and LinkNet [24], as well as D-LinkNet [23].”
BackgroundResultAutomatic choroidal segmentation in OCT images using supervised deep learning methods
Kugelman, J., Alonso‐Caneiro, D., Read, S. A., Hamwood, J., Vincent, S. J., Chen, F. K., & Collins, M. J. (2019) · Scientific Reports · doi:10.1038/s41598-019-49816-4 · Cited by 135
VecRoad: Point-Based Iterative Graph Exploration for Road Graphs Extraction
Tan, Y.-Q., Gao, S., Li, X.-Y., Cheng, M.-M., & Ren, B. (2020) · Computer Vision and Pattern Recognition · doi:10.1109/cvpr42600.2020.00893 · Cited by 118
“[32] apply residual connections [10] to the U-Net [19] to learn more delicate features for road segmentation.”
Leveraging Crowdsourced GPS Data for Road Extraction From Aerial Imagery
Sun, T., Di, Z., Che, P., Liu, C., & Wang, Y. (2019) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2019.00769 · Cited by 135
“Like the Deep-5 [8] 47.65 - U-Net [24] 43.63 48.10 Res U-Net [38] 45.33 48.52 LinkNet [7] 49.98 51.06 D-LinkNet [39] 48 Globe dataset, we manually created the training labels by masking out road pixels in the images.”
InfluentialSelf-citationDeep learning for processing and analysis of remote sensing big data: a technical review
Zhang, X., Zhou, Y., & Luo, J. (2021) · Big Earth Data · doi:10.1080/20964471.2021.1964879 · Cited by 122
“Graph neural networks (GNNs) are fit for dealing with data with irregular structures (Zhou, Cui, & Zhang et al., 2018), e.g. graphs and networks.”
BackgroundLearning Cartographic Building Generalization with Deep Convolutional Neural Networks
Feng, Y., Thiemann, F., & Sester, M. (2019) · ISPRS International Journal of Geo-Information · doi:10.3390/ijgi8060258 · Cited by 112
Chen, H., Li, Z., Wu, J., Xiong, W. H., & Du, C. (2023) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2023.03.012 · Cited by 115
Deep Convolutional Dictionary Learning for Image Denoising
Zheng, H., Yong, H., & Lei Zhang, A. (2021) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr46437.2021.00069 · Cited by 129
“We adopt the UNet [43] architecture for its effectiveness in image restoration tasks [66, 73, 57].”
MethodCCBANet: Cascading Context and Balancing Attention for Polyp Segmentation
Nguyen, T.-C., Nguyen, T.-P., Diep, G., Tran-Dinh, A.-H., Nguyen, T., & Tran, M. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-87193-2_60 · Cited by 129
Ullah, A., Elahi, H., Sun, Z., Khatoon, A., & Ahmad, I. (2021) · Arabian Journal for Science and Engineering · doi:10.1007/s13369-021-06182-6 · Cited by 104
Lee, C.-H., Khan, A., Luo, D., Santos, T. P., Shi, C.-Q., Janicek, B., Kang, S., Zhu, W., Sobh, N., Schleife, A., et al. (2020) · Nano letters (Print) · doi:10.1021/acs.nanolett.0c00269 · Cited by 110
“S.; Lehtinen, O.; Kaiser, U.; Krasheninnikov, A. V. From point to extended defects in two-dimensional MoS2: Evolution of atomic structure under electron irradiation. Physical Review B 2013 , 88, 1{8. (8)Algara-Siller, G.; Kurasch, S.; Sedighi, M.; Lehtinen, O.; Kaiser, U. The pristine atomic structure of MoS2 monolaye…”
BackgroundYao, W., & Ji, S. (2021) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2021.3061213 · Cited by 101
“[15] proposed an improved DCNN, which combined ResNet [16] and U-Net [17] to extract roads from remote sensing images.”
MethodZhou, M.-T., Sui, H., Chen, S.-X., Wang, J.-D., & Chen, X. (2020) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2020.08.019 · Cited by 109
Wang, J., Ruhaiyem, N., & Fu, P. (2025) · IET Image Processing · doi:10.48550/arxiv.2502.06895 · Cited by 106
CAFE-Net: Cross-Attention and Feature Exploration Network for polyp segmentation
Liu, G.-Q., Yao, S., Liu, D., Chang, B., Chen, Z., Wang, J., & Wei, J.-Q. (2023) · Expert systems with applications · doi:10.1016/j.eswa.2023.121754 · Cited by 106
Zhang, H., Liu, M., Wang, Y., Shang, J., Liu, X., Li, B., Song, A., & Li, Q. (2021) · International Journal of Applied Earth Observation and Geoinformation · doi:10.1016/j.jag.2021.102557 · Cited by 106
Self-citationLo, J., Yu, T. T., Ma, D., Zang, P., Owen, J. P., Zhang, Q., Wang, R. K., Beg, M. F., Lee, A. Y., Jia, Y., et al. (2021) · Ophthalmology Science · doi:10.1016/j.xops.2021.100069 · Cited by 105
“The architecture used on each client was the residual U-Net, 31 which is shown in Figure S2.”
MethodYi, Y., & Zhang, W. (2020) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2020.3028855 · Cited by 145
“Therefore, in order to validate the effectiveness of LandsNet, two state-of-the-art deep networks, i.e., ResUNet [71] and DeepUNet [72], were selected for comparisons.”
MethodAli, S., Ghatwary, N., Jha, D., Isik-Polat, E., Polat, G., Chen, Y., Li, W., Galdrán, A., Ballester, M.-Á. G., Thambawita, V. L., et al. (2024) · Scientific Reports · doi:10.1038/s41598-024-52063-x · Cited by 84
Building extraction from remote sensing images using deep residual U-Net
Wang, H., & Miao, F. (2022) · European Journal of Remote Sensing · doi:10.1080/22797254.2021.2018944 · Cited by 116
“The degradation problem can be addressed using the residual neural network (He et al. 2016; Z. Zhang et al., 2018), which we integrated into our method.”
MethodRoad Extraction of High-Resolution Remote Sensing Images Derived from DenseUNet
Jiang, X., Zhang, X., Zhang, Z., & Wu, F. (2019) · Remote Sensing · doi:10.3390/rs11212499 · Cited by 120
Self-citationFlood, N., Watson, F., & Collett, L. J. (2019) · International Journal of Applied Earth Observation and Geoinformation · doi:10.1016/j.jag.2019.101897 · Cited by 113
Extracting apple tree crown information from remote imagery using deep learning
Wu, J.-T., Yang, G.-J., Yang, H., Zhu, Y.-H., Li, Z.-H., Lei, L., & Zhao, C.-J. (2020) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2020.105504 · Cited by 103
Physics-Informed Computer Vision: A Review and Perspectives
Banerjee, C., Nguyen, K., Fookes, C., & Karniadakis, G. E. (2024) · ACM Computing Surveys · doi:10.1145/3689037 · Cited by 111
“slew rate) [205] Fluorescence microscopy Image denoising Custom RESUNET[230] Physical loss [159] Diffraction tomography Tomograhic reconstruction Custom PINN PDE (Maxwell’s equation)”
Chen, T.-H. K., Qiu, C., Schmitt, M., Zhu, X. X., Sabel, C. E., & Prishchepov, A. V. (2020) · Remote Sensing of Environment · doi:10.1016/j.rse.2020.112096 · Cited by 104
Water-Body Segmentation for SAR Images: Past, Current, and Future
Guo, Z.-S., Wu, L., Huang, Y.-B., Guo, Z., Zhao, J.-H., & Li, N. (2022) · Remote Sensing · doi:10.3390/rs14071752 · Cited by 99
“the good performance of U-Net small sample training [102].”
BackgroundOptimized deep encoder-decoder methods for crack segmentation
König, J., Jenkins, M. D., Mannion, M., Barrie, P., & Morison, G. (2020) · Digital Signal Processing · doi:10.1016/j.dsp.2020.102907 · Cited by 95
“Adding those residual connections for semantic segmentation tasks in convolutional blocks has shown to improve the performance in U-Net based architectures [50, 51].”
BackgroundRCNet: road classification convolutional neural networks for intelligent vehicle system
Dewangan, D., & Sahu, S. (2021) · Intelligent Service Robotics · doi:10.1007/s11370-020-00343-6 · Cited by 98
CloudFCN: Accurate and Robust Cloud Detection for Satellite Imagery with Deep Learning
Francis, A., Sidiropoulos, P., & Muller, J. (2019) · Remote Sensing · doi:10.3390/rs11192312 · Cited by 98
CSCA U-Net: A channel and space compound attention CNN for medical image segmentation
Shu, X., Wang, J., Zhang, A., Shi, J., & Wu, X. (2024) · Artificial Intelligence in Medicine · doi:10.1016/j.artmed.2024.102800 · Cited by 97
Bai, Y., Mas, E., & Koshimura, S. (2018) · Remote Sensing · doi:10.3390/rs10101626 · Cited by 96
“Specifically, the U-net architecture adopted in this study is slightly different from U-net(Ronneberger, et al., 2015) [26] and Deep Residual U-net(Zhang, et al., 2018) [33] as follows.”
InfluentialHe, J., Zhang, L. M., Xiao, T., Wang, H., & Luo, H. (2023) · Water Research · doi:10.1016/j.watres.2023.120057 · Cited by 99
MedCLIP-SAM: Bridging Text and Image Towards Universal Medical Image Segmentation
Koleilat, T., Asgariandehkordi, H., Rivaz, H., & Xiao, Y. (2024) · International Conference on Medical Image Computing and Computer-Assisted Intervention · doi:10.48550/arxiv.2403.20253 · Cited by 94
“In the attempt to further enhance the accuracy of zero-shot segmentation, we used the resulting pseudo-masks to train a Residual UNet [34] in a weakly supervised setting.”
MethodZhang, C., Atkinson, P., George, C. T., Wen, Z., Diazgranados, M., & Gerard, F. (2020) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2020.09.025 · Cited by 94
BDG-Net: boundary distribution guided network for accurate polyp segmentation
Qiu, Z., Wang, Z., Zhang, M., Xu, Z., Fan, J., & Xu, L. (2022) · SPIE Medical Imaging: Image Processing · doi:10.1117/12.2606785 · Cited by 92
Road Extraction From Satellite Images Using Attention-Assisted UNet
Akhtarmanesh, A., Abbasi-Moghadam, D., Sharifi, A., Yadkouri, M. H., Tariq, A., & Lu, L.-L. (2024) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2023.3336924 · Cited by 92
“Various extensions and adaptations of UNet have been developed to address specific challenges in road extraction, such as SegNet [35] and Res-UNet [36], which is an enhancement of the UNet architecture achieved by integrating a residual module [37].”
MethodDai, L., Zhang, G.-Y., & Zhang, R. (2023) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2023.3237561 · Cited by 92
“Some studies [40], [41], [42], [43], [44] extracted roads adopting CNN-based models.”
BackgroundCAT-Net: A Cross-Slice Attention Transformer Model for Prostate Zonal Segmentation in MRI
Hung, A. L. Y., Zheng, H., Miao, Q., Raman, S. S., Terzopoulos, D., & Sung, K. (2022) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2022.3211764 · Cited by 99
“ResUNet [21] applied the residual connections from ResNet [22], and the combination of ResNet with U-Net has also proven effective outside of medical image segmentation [23], [24].”
MethodReconstruction Bias U-Net for Road Extraction From Optical Remote Sensing Images
Chen, Z., Wang, C., Li, J., Xie, N., Han, Y. B., & Du, J. (2021) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2021.3053603 · Cited by 110
“Road area extraction methods produce pixel-level labeling of roads [1], [4], [29]–[38], while skeletons of roads are extracted for road centerline extraction [8], [27], [28], [39]–[46].”
BackgroundMethodEff-UNet++: A novel architecture for plant leaf segmentation and counting
Bhagat, S., Kokare, M., Haswani, V., Hambarde, P., & Kamble, R. M. (2022) · Ecological Informatics · doi:10.1016/j.ecoinf.2022.101583 · Cited by 90
Uni-Temporal Multispectral Imagery for Burned Area Mapping with Deep Learning
Hu, X., Yifang Ban, A., & Nascetti, A. (2021) · Remote Sensing · doi:10.3390/rs13081509 · Cited by 101
“A similar U-Net architecture with residual units was employed for road area extraction with relatively high accuracy [50].”
MethodA Multi-Attention UNet for Semantic Segmentation in Remote Sensing Images
Sun, Y., Bi, F., Gao, Y., Chen, L., & Feng, S. (2022) · Symmetry · doi:10.3390/sym14050906 · Cited by 90
Self-Supervised SAR-Optical Data Fusion of Sentinel-1/-2 Images
Chen, Y.-X., & Bruzzone, L. (2022) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2021.3128072 · Cited by 88
“Each branch contains a ResUnet [42] block followed by a linear layer projector.”
MethodΦ-Net: Deep Residual Learning for InSAR Parameters Estimation
Sica, F., Gobbi, G., Rizzoli, P., & Bruzzone, L. (2021) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2020.3020427 · Cited by 87
DiResNet: Direction-Aware Residual Network for Road Extraction in VHR Remote Sensing Images
Ding, L., & Bruzzone, L. (2020) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2020.3034011 · Cited by 87
“In [23], the UNet is combined with the residual design in the ResNet [24] architecture.”
MethodA Novel Weakly Supervised Multitask Architecture for Retinal Lesions Segmentation on Fundus Images
Playout, C., Duval, R., & Cheriet, F. (2019) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2019.2906319 · Cited by 87
“Residual connection for UNeT architecture were proved to be effective in [33].”
GAMSNet: Globally aware road detection network with multi-scale residual learning
Lu, X.-Y., Zhong, Y.-F., Zheng, Z., & Zhang, L.-P. (2021) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2021.03.008 · Cited by 86
Safarov, S., & Whangbo, T. (2021) · Italian National Conference on Sensors · doi:10.3390/s21041441 · Cited by 84
“Four state-of-the-art deep learning models, U-Net [7], wide U-Net [35], ResUNet [8], and UNet++ [35], were selected for comparative analysis of the proposed method.”
BackgroundMethodResultInfluentialImage segmentation review: Theoretical background and recent advances
Brar, K. K., Goyal, B., Dogra, A., Mustafa, M. A., Majumdar, R., Alkhayyat, A. H., & Kukreja, V. (2024) · Information Fusion · doi:10.1016/j.inffus.2024.102608 · Cited by 102
Liu, R., Wu, J., Lu, W., Miao, Q., Zhang, H., Liu, X., Lu, Z., & Li, L. (2024) · Remote Sensing · doi:10.3390/rs16122056 · Cited by 89
“Zhang et al. [140] combined the advantages of residual learning and UNet to propose a new network for road extraction.”
BackgroundMultiscale Deep Learning for Detection and Recognition: A Comprehensive Survey
Jiao, L., Wang, M., Liu, X., Li, L., Liu, F., Feng, Z., Yang, S., & Hou, B. (2024) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2024.3389454 · Cited by 83
“U-Net was initially applied to medical image segmentation, but its simple and effective network structure made it quickly generalized to various semantic segmentation tasks [131], [132], and many variants have been proposed one after another.”
A Unified Framework for U-Net Design and Analysis
Williams, C., Falck, F., Deligiannidis, G., Holmes, C. C., Doucet, A., & Syed, S. (2023) · Neural Information Processing Systems · doi:10.48550/arxiv.2305.19638 · Cited by 83
“[62] Zhengxin Zhang, Qingjie Liu, and Yunhong Wang.”
BackgroundC-UNet: Complement UNet for Remote Sensing Road Extraction
Hou, Y., Liu, Z., Zhang, T., & Li, Y. (2021) · Sensors · doi:10.3390/s21062153 · Cited by 92
“CNN-based models can automatically explore road characteristics by using strong generalization ability, the arbitrary function fitting ability and high stability, then predict the probability value of pixel-level road images through discriminant function [36,37].”
BackgroundMethodInfluentialPrecipitation Nowcasting with Satellite Imagery
Lebedev, V., Ivashkin, V., Rudenko, I., Ganshin, A., Molchanov, A., Ovcharenko, S., Grokhovetskiy, R., Bushmarinov, I., & Solomentsev, D. (2019) · Knowledge Discovery and Data Mining · doi:10.1145/3292500.3330762 · Cited by 83
“natural to apply the same approaches for precipitation detection. Convolutional neural networks have been successfully applied to a variety of satellite image processing tasks, such as road extraction[19,32,39]andbuildingdetection[14].Publicchallenges[8,13] brought a lot of attention to the topic, and a variety of arc…”
BackgroundCryptanalysis of random-phase-encoding-based optical cryptosystem via deep learning.
Han, H., Pan, S.-X., Liao, M., Lu, D.-J., He, W.-Q., & Peng, X. (2019) · Optics Express · doi:10.1364/oe.27.021204 · Cited by 82
Morales, G., Kemper, G., Sevillano, G., Arteaga, D., Ortega, I., & Telles, J. (2018) · Forests · doi:10.3390/f9120736 · Cited by 82
Liu, G., Ding, Q., Luo, H., Sha, M., Li, X., & Ju, M. (2022) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2022.106194 · Cited by 81
The importance of resource awareness in artificial intelligence for healthcare
Jia, Z., Chen, J., Xu, X., Kheir, J. N., Hu, J., Xiao, H., Peng, S., Hu, X. S., Chen, D., & Shi, Y. (2023) · Nature Machine Intelligence · doi:10.1038/s42256-023-00670-0 · Cited by 93
Kugelman, J., Allman, J., Read, S. A., Vincent, S. J., Tong, J., Kalloniatis, M., Chen, F. K., Collins, M. J., & Alonso‐Caneiro, D. (2022) · Scientific Reports · doi:10.1038/s41598-022-18646-2 · Cited by 84
Common-azimuth seismic data fault analysis using residual UNet
Liu, N.-H., He, T., Tian, Y., Wu, B.-Y., Gao, J.-H., & Xu, Z.-B. (2020) · Interpretation · doi:10.1190/int-2019-0173.1 · Cited by 81
Retinal image synthesis from multiple-landmarks input with generative adversarial networks
Yu, Z.-K., Xiang, Q., Meng, J.-H., Kou, C., Ren, Q., & Lu, Y.-Y. (2019) · BioMedical Engineering OnLine · doi:10.1186/s12938-019-0682-x · Cited by 81
JointNet: A Common Neural Network for Road and Building Extraction
Zhang, Z.-X., & Wang, Y.-H. (2019) · Remote Sensing · doi:10.3390/rs11060696 · Cited by 81
“In the Massachusett building dat base valuation, the comparison methods include MTMS [24], U-Net [19], and Res-U-Net [18].”
BackgroundMethodInfluentialSelf-citationRehman, A., Mahmood, T., & Saba, T. (2024) · Applied Soft Computing · doi:10.1016/j.asoc.2024.112518 · Cited by 80
Dai, Y., Pan, P., Qian, Y., Li, Y., Li, X., Yang, J., & Wang, H. (2024) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2024.3458896 · Cited by 80
“The backbone has evolved with improved encoder blocks; for instance, residual U-Net leveraged skip connections akin to ResNet [33], enabling the construction of deeper architectures [34].”
BackgroundA comparative study of loss functions for road segmentation in remotely sensed road datasets
Xu, H.-Z., He, H.-J., Zhang, Y., Ma, L.-F., & Li, J. (2023) · International Journal of Applied Earth Observation and Geoinformation · doi:10.1016/j.jag.2022.103159 · Cited by 80
Defects Inspection in Polycrystalline Solar Cells Electroluminescence Images Using Deep Learning
Rahman, M. R. U., & Chen, H.-Y. (2020) · IEEE Access · doi:10.1109/access.2020.2976843 · Cited by 80
“Despite having symmetric skip connections to fuse encoder and decoder features, U-net like architecture still faces degradation problem which can be solved by adding residual connections within encoder and decoder [17].”
BackgroundWen, Q., Jiang, K., Wang, W., Liu, Q., Guo, Q., Li, L., & Wang, P. (2019) · Sensors · doi:10.3390/s19020333 · Cited by 88
“General segmentation methods such as U-Net-style networks [32] cannot distinguish different instances.”
MethodSelf-citationTao, J., Chen, Z., Sun, Z., Guo, H., Leng, B., Yu, Z., Wang, Y., He, Z., Lei, X., & Yang, J. (2023) · Remote Sensing · doi:10.3390/rs15061602 · Cited by 85
Self-citationDeepa, N., & Chokkalingam, S. P. (2022) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2021.103455 · Cited by 92
“Deep Residual U-Net architecture [17] is used along with an adaptive ROI thereby performing better performance in terms of brain nodule segmentation.”
MethodRoad Extraction from Very-High-Resolution Remote Sensing Images via a Nested SE-Deeplab Model
Lin, Y., Xu, D., Wang, N., Shi, Z., & Chen, Q.-X. (2020) · Remote Sensing · doi:10.3390/rs12182985 · Cited by 79
Volumetric lung nodule segmentation using adaptive ROI with multi-view residual learning
Usman, M., Lee, B.-D., Byon, S.-S., Kim, S.-H., Lee, B.-I., & Shin, Y.-G. (2019) · Scientific Reports · doi:10.1038/s41598-020-69817-y · Cited by 79
“This VOI is further utilized to create coronal and sagittal views of the nodule, and slices of both are investigated with two Deep Residual U-Nets.”
MethodInfluentialHe, Z., Wang, P., Zou, Y., Huang, B., Zhu, D., Lee, H. F., & Leung, H. (2025) · Information Fusion · doi:10.1016/j.inffus.2025.103487 · Cited by 84
Lagree, A., Mohebpour, M., Meti, N., Saednia, K., Lu, F., Slodkowska, E. A., Gandhi, S., Rakovitch, E., Shenfield, A., Naini, A. S., et al. (2021) · Scientific Reports · doi:10.1038/s41598-021-87496-1 · Cited by 83
Spatio-Temporal Deep Learning Approach to Map Deforestation in Amazon Rainforest
Maretto, R., Fonseca, L. M. G., Jacobs, N., Körting, T., Bendini, H., & Parente, L. (2020) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2020.2986407 · Cited by 78
“Zhang et al. [14] proposed a Residual U-Net to perform road extraction on high-resolution aerial images from the Massachusetts roads data set.”
BackgroundZhao, W., Bo, Y.-C., Chen, J.-G., Tiede, D., Blaschke, T., & Emery, W. (2019) · Isprs Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2019.03.019 · Cited by 78
A Novel 3D Unsupervised Domain Adaptation Framework for Cross-Modality Medical Image Segmentation
Yao, K., Su, Z., Huang, K., Yang, X., Sun, J., Hussain, A., & Coenen, F. (2022) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2022.3162118 · Cited by 87
“To maximize the semantic mining in such meaningful data, we propose DAR-UNet which is adapted from the classic 2D ResU-Net [29], [30] to volumetric data by replacing part of the 2D convolutions with 3D convolutions, providing accurate segmentation masks and efficient computation.”
MethodMahmud, S., Ibtehaz, N., Khandakar, A. A., Tahir, A., Rahman, T., Islam, K. R., Hossain, M. S., Rahman, M. S., Musharavati, F., Ayari, M. A., et al. (2022) · Sensors · doi:10.3390/s22030919 · Cited by 86
“Many studies used U-Net to perform tasks, such as biomedical image segmentation [29], shape regeneration [30], road shape extraction from satellite maps [31], etc.”
MethodNanoNet: Real-Time Polyp Segmentation in Video Capsule Endoscopy and Colonoscopy
Jha, D., Tomar, N. K., Ali, S., Riegler, M. A., Johansen, H. D., Johansen, D., de Lange, T., & Halvorsen, P. (2021) · Proceedings - IEEE Symposium on Computer-Based Medical Systems · doi:10.1109/cbms52027.2021.00014 · Cited by 87
“Method Parameters DSC mIoU Recall Precision F2 Accuracy FPS ResUNet (GRSL’18) [38] 8,227,393 0.”
MethodInfluentialTrophectoderm segmentation in human embryo images via inceptioned U-Net
Rad, R. M., Saeedi, P., Au, J., & Havelock, J. C. (2020) · Medical Image Analysis · doi:10.1016/j.media.2019.101612 · Cited by 75
LeaNet: Lightweight U-shaped architecture for high-performance skin cancer image segmentation
Hu, B., Zhou, P., Yu, H.-F., Dai, Y.-Y., Wang, M., Tan, S., & Sun, Y. (2024) · Comput. Biol. Medicine · doi:10.1016/j.compbiomed.2024.107919 · Cited by 76
RAAGR2-Net: A brain tumor segmentation network using parallel processing of multiple spatial frames
Rehman, M. U., Ryu, J., Nizami, I., & Chong, K. (2023) · Comput. Biol. Medicine · doi:10.1016/j.compbiomed.2022.106426 · Cited by 76
The application of ResU-net and OBIA for landslide detection from multi-temporal Sentinel-2 images
Ghorbanzadeh, O., Gholamnia, K., & Ghamisi, P. (2022) · Big Earth Data · doi:10.1080/20964471.2022.2031544 · Cited by 76
“The ResU-Net network structure comprises three main parts: downsampling, bridge, and upsampling (Zhang, Liu, & Wang, 2018).”
BackgroundAn improved U-Net method for the semantic segmentation of remote sensing images
Su, Z., Li, W., Ma, Z., & Gao, R. (2021) · Applied intelligence (Boston) · doi:10.1007/s10489-021-02542-9 · Cited by 76
“This design not only considers the efficiency of the gradient backpropagation and multiscale feature fusion [31] but also avoids the problem of the excessively rapid growth of the feature map dimension.”
BackgroundMethodLou, A., Guan, S., & Loew, M. H. (2023) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2023.106579 · Cited by 86
“Then, residual connection [6] has been applied to those encoder-decoder based models to help training and to improve the efficiency of networks [7].”
MethodLi, L., Wang, C., Zhang, H., Zhang, B., & Wu, F. (2019) · Remote Sensing · doi:10.3390/rs11091091 · Cited by 76
“Thus, Zhang [37] introduced residual block into U-Net and proposed residual U-Net to extract road in optical remote sensing images.”
BackgroundInfluentialDeepCMB: Lensing reconstruction of the cosmic microwave background with deep neural networks
Caldeira, J., Wu, W. L. K., Nord, B., Avestruz, C., Trivedi, S., & Story, K. T. (2019) · Astronomy and Computing · doi:10.1016/j.ascom.2019.100307 · Cited by 99
“We employ an instance from a family of network architectures, ResUNets (Kayalıbay et al., 2017; Zhang et al., 2017), which learns a transformation between images.”
MethodRobust chest CT image segmentation of COVID-19 lung infection based on limited data
Müller, D., Soto‐Rey, I., & Krämer, F. (2021) · Informatics in Medicine Unlocked · doi:10.1016/j.imu.2021.100681 · Cited by 113
“In this work, we implemented the standard 3D U-Net as architecture without any custom modification in order to avoid unnecessary parameter increase by more complex architectures like the residual variant of the 3D U-Net [26,61,62].”
Wang, Z., Yang, P., Liang, H., Zheng, C., Yin, J., Tian, Y., & Cui, W. (2021) · Remote Sensing · doi:10.3390/rs14010045 · Cited by 75
“CNNs have successfully been employed in variety remote sensing fields such as road detection [36], cloud detection [37] and smoke classification [38].”
MethodDirscherl, M., Dietz, A., Kneisel, C., & Kuenzer, C. (2021) · Remote Sensing · doi:10.3390/rs13020197 · Cited by 74
LM-Net: A light-weight and multi-scale network for medical image segmentation
Lu, Z., She, C., Wang, W., & Huang, Q. (2023) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2023.107717 · Cited by 81
Yalçın, S., & Vural, H. (2022) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2022.105941 · Cited by 78
A full resolution deep learning network for paddy rice mapping using Landsat data
Xia, L., Zhao, F., Chen, J., Yu, L., Lu, M., Yu, Q., Liang, S., Fan, L., Sun, X. M., Wu, S., et al. (2022) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2022.10.005 · Cited by 75
Torres, D. L., Turnes, J. N., Vega, P. J. S., Feitosa, R., Silva, D. E., Marcato, J., & de Almeida, C. A. (2021) · Remote Sensing · doi:10.3390/rs13245084 · Cited by 72
“ResU-Net [30] is a fully convolutional neural network that takes advantage of both the U-Net architecture and the so-called residual block introduced by the ResNet architecture first conceived for image classification [31].”
Metadata
- Authors
- Zhang, Z., Liu, Q., & Wang, Y.
- Affiliations
- State Key Laboratory of Virtual Reality Technology and Systems (CN)
- Venue
- IEEE Geoscience and Remote Sensing Letters
- Published
- 2018-05
- Volume
- 15
- Issue
- 5
- Pages
- 749-753
- ISSN
- 1545-598X (ISSN-L)
- 1558-0571
- OpenAlex
- W2774320778
- Cited by
- 3,179
- References
- 27
- Citations by year
- 2026: 331 · 2025: 526 · 2024: 616 · 2023: 510 · 2022: 441 · 2021: 342 · 2020: 241 · 2019: 147 · 2018: 25
- FWCI
- 151.19
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- IEEE Geoscience and Remote Sensing Letters (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University) (cc-by)
- Funders
- Natural Science Foundation of China (61601011)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Automated Road and Building Extraction
- Physical Sciences › Engineering › Civil and Structural Engineering › Infrastructure Maintenance and Monitoring
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Keywords
- road extraction, aerial images, semantic segmentation, residual learning, U-Net, skip connections
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
