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 601–700 of 1,001
Yu, Y., Zhong, G., Zhou, Y. X., & Chen, L. (2023) · Information Sciences · doi:10.1016/j.ins.2023.119114 · Cited by 26
U-Netmer: U-Net meets Transformer for medical image segmentationPreprint
He, S., Bao, R., Grant, P. E., & Ou, Y.-M. (2023) · arXiv.org · doi:10.48550/arxiv.2304.01401 · Cited by 25
Open-Source Data-Driven Cross-Domain Road Detection From Very High Resolution Remote Sensing Imagery
Lu, X., Zhong, Y., & Zhang, L. (2022) · IEEE Transactions on Image Processing · doi:10.1109/tip.2022.3216481 · Cited by 24
“have become the mainstream approach [4], [5], [6], which can greatly improve the accuracy when compared to most of the traditional pixel-based and object-based algorithms [7],”
Artificial Intelligence Approach for Estimating Dairy Methane Emissions.
Jeong, S., Fischer, M., Breunig, H., Marklein, A., Hopkins, F., & Biraud, S. (2022) · Environmental Science and Technology · doi:10.1021/acs.est.1c08802 · Cited by 25
Satellite imagery analysis for road segmentation using U-Net architecture
Chaudhary, V., Buttar, P. K., & Sachan, M. (2022) · Journal of Supercomputing · doi:10.1007/s11227-022-04379-6 · Cited by 25
“The stateof-the-art models in the remote sensing road segmentation task, namely U-Net [23], ResUNet [25], AttUNet [34], D-LinkNet [16], and C-UNet [6] were selected for comparison.”
MethodConvolutional Neural Network Modelling for MODIS Land Surface Temperature Super-Resolution
Nguyen, B., Tian, G., Во, М. Т. Л., Michel, A., Corpetti, T., & Granero-Belinchón, C. (2022) · European Signal Processing Conference · doi:10.23919/eusipco55093.2022.9909569 · Cited by 25
“Moreover, it is a universal network which can be modified and employed in number of remote sensing applications such as pansharpening [14] or even road extraction [15].”
HumanGPS: Geodesic PreServing Feature for Dense Human Correspondences
Tan, F., Tang, D., Dou, M., Guo, K., Pandey, R., Keskin, C., Du, R., Sun, D., Bouaziz, S., Fanello, S., et al. (2021) · Computer Vision and Pattern Recognition · doi:10.1109/cvpr46437.2021.00186 · Cited by 25
“To improve the capacity without significantly increasing the model size, we add residual blocks inspired by [77].”
Automated Method of Road Extraction from Aerial Images Using a Deep Convolutional Neural Network
Alshaikhli, T., Liu, W., & Maruyama, Y. (2019) · Applied Sciences · doi:10.3390/app9224825 · Cited by 25
“U-Net has provided remarkable results in semantic segmentation tasks, and it has been combined with other architectures in many studies [33–38]. model, and the Res-Unet model failed to make a correct prediction.”
BackgroundMethodResultInfluentialRoad Detection via Deep Residual Dense U-Net
Yang, X.-F., Li, X.-T., Ye, Y.-M., Zhang, X.-F., Zhang, H.-J., Huang, X., & Zhang, B. (2019) · IEEE International Joint Conference on Neural Network · doi:10.1109/ijcnn.2019.8851728 · Cited by 25
Pannu, R., Zubair, M., Owais, M., Hassan, S., Umair, M., Usman, S. M., Albashrawi, M., & Hussain, I. (2025) · Comput. Medical Imaging Graph. · doi:10.1016/j.compmedimag.2025.102559 · Cited by 24
Federated learning system on autonomous vehicles for lane segmentation
Kishawy, M., El-Hafez, M. T. A., Yousri, R., & Darweesh, M. (2024) · Scientific Reports · doi:10.1038/s41598-024-71187-8 · Cited by 24
“ResUNet, on the other hand, is specifically designed for remotely sensed data, which makes it come after U-Net, as noted in the literature 9,34 .”
BackgroundEfficient Brain Tumor Segmentation with Lightweight Separable Spatial Convolutional Network
Zhang, H., Liu, M., Qi, Y., Yang, N., Hu, S.-B., Nie, L.-Q., & Zhang, W. (2024) · ACM Trans. Multim. Comput. Commun. Appl. · doi:10.1145/3653715 · Cited by 24
“Emphasizing the role of skip connections, Zhang et al. [41] developed DeepResUNet, emphasizing skip connections and merging low-level and high-level semantic information for improved segmentation.”
BackgroundMethodZhang, L., Yuan, S., Dong, R.-M., Zheng, J.-P., Gan, B., Fang, D., Liu, Y., & Fu, H.-H. (2024) · International Journal of Applied Earth Observation and Geoinformation · doi:10.1016/j.jag.2024.103665 · Cited by 24
CT Liver Segmentation Via PVT-Based Encoding and Refined Decoding
Jha, D., Tomar, N. K., Biswas, K., Durak, G., Medetalibeyoğlu, A., Antalek, M., Velichko, Y., Ladner, D. P., Borhani, A. A., & Bagci, U. (2024) · IEEE International Symposium on Biomedical Imaging · doi:10.1109/isbi56570.2024.10635659 · Cited by 24
“Similarly, Rahman et al. [8] proposed a novel al-gorithm for automatically segmenting liver tumors from CT images using a hybrid ResUNet [9] model.”
MethodGAN Supervised Seismic Data Reconstruction: An Enhanced Learning for Improved Generalization
Goyes-Peñafiel, P., Suárez-Rodríguez, L., Correa, C. V., & Arguello, H. (2023) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2024.3434474 · Cited by 24
“…noting that although previous works have employed similar neural network architectures for data reconstruction, denoising, and segmentation [50], [51], [52], this work aims at providing a powerful guided learning approach for reconstruction tasks, rather than proposing new or sophisticated…”
ResultFusionU-Net: U-Net with Enhanced Skip Connection for Pathology Image Segmentation
Li, Z., Lyu, H., & Wang, J. (2023) · Asian Conference on Machine Learning · doi:10.48550/arxiv.2310.10951 · Cited by 24
“ResU-Net [12] uses residual units to make it easier to train deeper networks.”
BackgroundLGI Net: Enhancing local-global information interaction for medical image segmentation
Liu, L., Li, Y., Wu, Y., Ren, L., & Wang, G. (2023) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2023.107627 · Cited by 30
Sousa, J., Lin, J., Wang, Q., Liu, G., Fan, J.-H., Bai, S.-B., Zhao, H., Pan, H., Wei, W., Rittlinger, V., et al. (2023) · Geo-Spatial Information Science · doi:10.1080/10095020.2023.2234008 · Cited by 24
“Specifically, the U-Net architecture has been extensively employed in various remote sensing applications, including extracting urban roads (Zhang, Liu, and Wang 2018), identifying water bodies (Feng et al. 2018), and classifying crops (Wei et al. 2019), due to its efficient training time, minimal…”
Road object detection for HD map: Full-element survey, analysis and perspectives
Luo, Z., Gao, L., Xiang, H., & Li, J. (2023) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2023.01.009 · Cited by 33
Xie, L., Cai, W.-T., & Gao, Y. (2022) · IEEE journal of biomedical and health informatics · doi:10.1109/jbhi.2022.3192277 · Cited by 24
“…powerful segmentation methods, including medical image segmentation methods U-Net++ [10], U-Net3+[11], Attention U-Net [20], Residual U-Net [51], CE-Net [52], V-Net [18], TransUNet [23], Segformer [53], WAU [54] and semantic segmentation approaches such as FCN [6], DeepLab V3+ [55], PSPNet…”
MethodShao, S.-W., Xiao, L.-X., Lin, L.-P., Ren, C., & Tian, J. (2022) · Remote Sensing · doi:10.3390/rs14092061 · Cited by 24
“[27] combined the advantages of U-Net structure to extract scale information with the advantage of residual structure to connect different features maps.”
Toward accurate polyp segmentation with cascade boundary-guided attention
Lai, H., Luo, Y., Zhang, G.-K., Shen, X., Li, B., & Lu, J.-W. (2022) · The Visual Computer · doi:10.1007/s00371-022-02422-4 · Cited by 24
“UNet [32] and its variants [19,46,49] restored the resolution of the image through the upsampling operation, and utilized skip connections at different stages to integrate deep and shallow features.”
MethodInfluentialImproving across-dataset brain tissue segmentation for MRI imaging using transformer
Rao, V. M., Wan, Z., Arabshahi, S., Ma, D. J., Lee, P.-Y., Tian, Y., Zhang, X., Laine, A. F., & Guo, J. (2022) · Frontiers in Neuroimaging · doi:10.3389/fnimg.2022.1023481 · Cited by 27
“We chose Unet given its prior state of the art performance in 3D brain tissue segmentation (Kolařík et al., 2018), and we also compared to prior attempts at improving Unet including squeeze-excitation (SE) blocks (Hu et al., 2018) before each downsampling operation (Unet-SE) and residual connections (ResUnet) (Zhang e…”
InfluentialBae, J., Kapse, S., Singh, G., Gattu, R., Ali, S., Shah, N., Marshall, C., Pierce, J. D., Phatak, T., Gupta, A., et al. (2021) · Diagnostics · doi:10.3390/diagnostics11101812 · Cited by 24
“In order to segment lungs and artifacts from CXR images, two residual UNet DL models were employed [26,30].”
MethodSelf-supervised Remote Sensing Images Change Detection at Pixel-levelPreprint
Chen, Y.-X., & Bruzzone, L. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2105.08501 · Cited by 24
AG-CUResNeSt: A Novel Method for Colon Polyp SegmentationPreprint
Dinh, S., Tran, C. Q., Phan, L. N., Hang, D., Long, D. V., & Nguyen, T. (2021) · arXiv.org · doi:10.48550/arxiv.2105.00402 · Cited by 24
“The proposed AG-CUResNeSt-101 is compared with the aforementioned baseline models along with reported metrics from SFA [50], ResUNet-mod [51], UNet [17] and UNet++ [18].”
Recurrent residual U-Net with EfficientNet encoder for medical image segmentation
Siddique, N., Paheding, S., Alom, M., & Devabhaktuni, V. (2021) · Defense + Commercial Sensing · doi:10.1117/12.2591343 · Cited by 24
Dual Encoder Fusion U-Net (DEFU-Net) for Cross-manufacturer Chest X-ray Segmentation
Zhang, L., Liu, A., Xiao, J., & Taylor, P. M. (2021) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr48806.2021.9412718 · Cited by 30
“The U-Net [20], Residual U-Net (Res-U-Net) [26], Incept-Res-U-Net, BCDU-Net [2], R2U-Net and R2-Att-U-Net, DEFU-Net had all been trained”
Deep Residual U-Net Based Lung Image Segmentation for Lung Disease Detection
Mique, E., & Malicdem, A. (2020) · IOP Conference Series: Materials Science and Engineering · doi:10.1088/1757-899x/803/1/012004 · Cited by 24
Luo, Z.-Q., Zhou, K., Tan, Y.-M., Wang, X.-L., Zhu, R., & Zhang, L.-Q. (2023) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2023.3289583 · Cited by 24
“is preserved by residual blocks to detect very narrow roads, and compared to some previous research works in multiscale road feature extraction (see [17], [21], [35], [69]), this study intro-”
BackgroundResultInfluentialAn Res-Unet Method for Pulmonary Artery Segmentation of CT Images
Liu, Z., & Yuan, H. (2021) · Journal of Physics, Conference Series · doi:10.1088/1742-6596/1924/1/012018 · Cited by 24
“(d) represents the segmentation results of ResUnet in [6], the rightmost figure is the result of the prediction of the architectures proposed in this paper.”
BackgroundMethodResultInfluentialDeep Learning for Pulmonary Image Analysis: Classification, Detection, and Segmentation.
Kido, S., Hirano, Y., & Mabu, S. (2020) · Advances in Experimental Medicine and Biology · doi:10.1007/978-3-030-33128-3_3 · Cited by 24
A review of algorithms for surface defect detection in welds based on machine learning
Zhang, J., Li, P.-H., Zhang, M.-X., Shen, K.-H., & Xing, Y.-Z. (2025) · Expert systems with applications · doi:10.1016/j.eswa.2025.130188 · Cited by 23
Hassan, S. M., Laban, N., Khashaba, S. M. A., El-Shibiny, N. H., Bashir, B., Azer, M. K., Drüppel, K., & Keshk, H. M. (2024) · Remote Sensing · doi:10.3390/rs16132276 · Cited by 24
“Adding residual connections inside convolution blocks increases learning speed and overcomes the vanishing gradient problem [37].”
BackgroundSaad, A. I., Maghraby, F., & Badawy, O. M. (2023) · Neural computing & applications (Print) · doi:10.1007/s00521-023-09358-3 · Cited by 23
“The ResUNet architecture combines the U-Net architecture with residual learning, which relies on the idea of residual blocks [37].”
Alam, M. J., & Fattah, S. (2023) · Comput. Biol. Medicine · doi:10.1016/j.compbiomed.2023.106945 · Cited by 23
Deep-NFA: a Deep a contrario Framework for Small Object Detection
Ciocarlan, A., Hégarat-Mascle, S. L., Lefebvre, S., & Woiselle, A. (2023) · Pattern Recognition · doi:10.1016/j.patcog.2024.110312 · Cited by 23
“Indeed, the F1 score is almost 2% higher when using ResUnet+NFA than the baseline.”
MethodInfluentialSemi-Supervised Land Cover Classification of Remote Sensing Imagery Using CycleGAN and EfficientNet
Kwak, T., & Kim, Y. (2023) · KSCE Journal of Civil Engineering · doi:10.1007/s12205-023-2285-0 · Cited by 26
“…methods conducting pixel-level classification of remotely-sensed VHR images have been used in various applications, such as road extraction (Zhang et al., 2018; Zhou et al., 2018), building footprint extraction (Shi et al., 2018b; Bischke et al., 2019; Jung et al., 2021), change detection…”
MethodA Reproducible and Reusable Pipeline for Segmentation of Geoscientific Imagery
Buscombe, D., & Goldstein, E. B. (2022) · Earth and Space Science · doi:10.1029/2022ea002332 · Cited by 30
“In recent years, Deep Learning (LeCun et al., 2015) models based on the UNet (Ronneberger et al., 2015) and the Residual UNet (Zhang et al., 2018; Liu et al., 2019) have become the standard in state-44 of-the-art Earth science applications involving image segmentation (Kattenborn et al., 2019; Nalepa et al., 2019; Liu…”
BackgroundMethodInfluentialHybrid U-Net: Semantic segmentation of high-resolution satellite images to detect war destruction
Nabiee, S., Harding, M. L., Hersh, J., & Bagherzadeh, N. (2022) · Machine Learning with Applications · doi:10.1016/j.mlwa.2022.100381 · Cited by 23
DeepGPD: A Deep Learning Approach for Modeling Geospatio-Temporal Extreme Events
Wilson, T., Tan, P.-N., & Luo, L.-F. (2022) · AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v36i4.20344 · Cited by 23
“For example, CNN has been successfully used to model spatial relationships in geographic applications (M´attyus, Luo, and Urtasun 2017; Zhang, Liu, and Wang 2018; Sun et al. 2018; Lebedev et al. 2019; Vandal et al. 2017; Kaiser et al. 2017).”
MethodSemantic Labeling of High-Resolution Images Using EfficientUNets and Transformers
Al-Marzouqi, H., & Saoud, L. S. (2023) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2023.3268159 · Cited by 28
“A residual dense U-Net was proposed for pixelwise sea–land segmentation in complex and high-density remote sensing images [32].”
MethodInfluentialLuo, S., Zhang, J., Xiao, N., Qiang, Y., Li, K., Zhao, J., Meng, L., & Song, P. (2022) · Applied Intelligence · doi:10.1007/s10489-021-03038-2 · Cited by 22
“We use 3D U-Net as baseline and control variable method to keep all settings unchanged except for the contrast part.”
MethodInfluentialExploring multiple crowdsourced data to learn deep convolutional neural networks for road extraction
Li, P., He, X.-H., Qiao, M.-J., Miao, D., Cheng, X., Song, D., Chen, M., Li, J.-M., Zhou, T., Guo, X., et al. (2021) · International Journal of Applied Earth Observation and Geoinformation · doi:10.1016/j.jag.2021.102544 · Cited by 23
Li, J., Ou, X., Shen, N., Sun, J., Ding, J., Zhang, J., Yao, J., & Wang, Z. (2021) · Expert Systems with Applications · doi:10.1016/j.eswa.2021.115008 · Cited by 28
Rahaman, M., Hillas, M., Tuba, J., Ruma, J., Ahmed, N., & Rahman, R. M. (2021) · Cybernetics and systems · doi:10.1080/01969722.2021.1989171 · Cited by 23
A Modular U-Net for Automated Segmentation of X-Ray Tomography Images in Composite Materials
Bertoldo, J. P. C., Decencière, É., Ryckelynck, D., & Proudhon, H. (2021) · Frontiers in Materials · doi:10.3389/fmats.2021.761229 · Cited by 25
“[14] optimized a SegNet [15] to segment dendrites of different alloys, including a 4D XCT. [7] identified Alu-minides and Si phases in XCT using a U-Net, an architecture that, along with its many flavors [16–19], has shown success in a variety of applications [20–22].”
MethodWang, Y., Wang, Y., Guo, C., Zhang, S., & Yang, L. (2021) · Computational Intelligence and Neuroscience · doi:10.1155/2021/5520281 · Cited by 23
“These connections create a quick pathway for information between high-level and low-level feature maps which is facilitating the gradient backward propagation and compensating finer details into high-level semantic features [30].”
BackgroundSelf-citationChen, Y., Ying, C., Binkley, M. M., Juttukonda, M. R., Flores, S. E., Laforest, R. A., Benzinger, T. L. S., & An, H. (2021) · Magnetic Resonance in Medicine · doi:10.1002/mrm.28689 · Cited by 24
Zhao, S., Wu, N., & Wang, Q. (2020) · Advanced Engineering Informatics · doi:10.1016/j.aei.2020.101184 · Cited by 22
Neural Network Training for the Detection and Classification of Oceanic Mesoscale Eddies
Santana, O. J., Hernández-Sosa, D., Martz, J., & Smith, R. N. (2020) · Remote Sensing · doi:10.3390/rs12162625 · Cited by 23
“We tested several alternatives proposed in the literature for the design of our residual model [29,42,43] and subsequently concluded in the elaboration of our own mapping, shown in Figure 5.”
MethodSemantic–Spatial Feature Refinement Network for Road Extraction From Remote Sensing Images
Yang, Z.-G., Yao, H.-G., Li, Q., Ni, W., Wu, J.-Z., & Wang, Q. (2026) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2026.3665299 · Cited by 23
“For example, Zhang et al. [16] integrated residual networks into the UNet framework to deepen the encoder, which significantly improves the model feature extraction capability.”
Mass segmentation and classification from film mammograms using cascaded deep transfer learning
Tiryaki, V. M. (2023) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2023.104819 · Cited by 23
Reconstruction of Sparsely Sampled Seismic Data via Residual U-Net
Tang, S., Ding, Y.-S., Zhou, H.-W., & Zhou, H. (2022) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2020.3035835 · Cited by 23
“Zhang et al. [15] used ResU-Net in road extraction.”
MethodChicken Image Segmentation via Multi-Scale Attention-Based Deep Convolutional Neural Network
Li, W., Xiao, Y., Song, X.-B., Lv, N., Jiang, X.-B., Huang, Y., & Peng, J.-L. (2021) · IEEE Access · doi:10.1109/access.2021.3074297 · Cited by 23
“applied in other computer vision tasks as well [19], [32], [33].”
MethodKhaing, T., Okamoto, T., Ye, C., Mannan, M. A., Yokouchi, H., Nakano, K., Aimmanee, P., Makhanov, S., & Haneishi, H. (2021) · IEEE Access · doi:10.1109/access.2021.3124993 · Cited by 23
“[31] detected the choroid’s upper and lower boundaries in OCT images using the Residual U-Net model [32] and then performed binarization to detect the choroidal vessels using Niblack’s algorithm.”
MethodClassification and segmentation of kidney MRI images for chronic kidney disease detection
Islam, M. S. B., Sumon, M. S. I., Sarmun, R., Bhuiyan, E., & Chowdhury, M. E. H. (2024) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2024.109613 · Cited by 21
Transformers-based architectures for stroke segmentation: a review
Zafari-Ghadim, Y., Rashed, E. A., Mohamed, A. M. S., & Mabrok, M. A. (2024) · Artificial Intelligence Review · doi:10.1007/s10462-024-10900-5 · Cited by 25
“…proposed network demonstrated superior performance compared to other architectures, including U-Net, SegNet (Badrinarayanan et al. 2017), PSPNet (Zhao et al. 2017), ResUNet (Zhang et al. 2018b), 2D Dense-UNet (Li et al. 2018), and DeepLabv3+ (Chen et al. 2018), as evaluated on the ATLAS dataset.”
InfluentialOlsen, M., Zeitzer, J. M., Nakase‐Richardson, R., Musgrave, V. H., Sørensen, H. B. D., Mignot, E. J.-M., & Jennum, P. (2024) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2024.3378480 · Cited by 27
Filter pruning for convolutional neural networks in semantic image segmentation
López-González, C. I., Gascó, E., Barrientos-Espillco, F., Besada-Portas, E., & Pájares, G. (2023) · Neural Networks · doi:10.1016/j.neunet.2023.11.010 · Cited by 28
Xu, Z., Rittscher, J., & Ali, S. (2024) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2024.3411933 · Cited by 20
“Here, we have chosen Res-UNet [54] as the baseline network for both the supervised and the self-supervised learning approaches.”
Zhang, H., Yang, X., Li, D., Cui, Y., Zhao, J., & Qiu, S. (2023) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2023.104304 · Cited by 21
Wahbi, M., Bakali, I. E., Ez-zahouani, B., Azmi, R., Moujahid, A., Zouiten, M., Alaoui, O. Y., Boulaassal, H., Maâtouk, M., & Kharki, O. E. (2023) · Remote Sensing Applications Society and Environment · doi:10.1016/j.rsase.2022.100898 · Cited by 22
DGD-cGAN: A Dual Generator for Image Dewatering and Restoration
González-Sabbagh, S., Robles-Kelly, A., & Gao, S. (2022) · arXiv.org · doi:10.48550/arxiv.2211.10026 · Cited by 22
“Firstly, we include the skip connections as in [33, 53]; secondly, we add deep residual units between them as in [54, 55].”
MethodRBP-DIP: Residual back projection with deep image prior for ill-posed CT reconstruction
Shu, Z., & Entezari, A. (2022) · Neural Networks · doi:10.1016/j.neunet.2024.106740 · Cited by 22
PointScatter: Point Set Representation for Tubular Structure Extraction
Wang, D., Zhang, Z., Zhao, Z.-L., Liu, Y.-H., Chen, Y., & Wang, L. (2022) · European Conference on Computer Vision · doi:10.48550/arxiv.2209.05774 · Cited by 22
“We compare our PointScatter with two very competitive segmentation methods ( i.e . softDice [32] and clDice [43]) on various mainstream backbone networks [40,64,60,8,62].”
MethodSelf-citationContinual Hippocampus Segmentation with Transformers
Ranem, A., González, C., & Mukhopadhyay, A. (2022) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw56347.2022.00415 · Cited by 22
Cao, T., Wang, G., Ren, L., Li, Y., & Wang, H. (2022) · Physics in Medicine and Biology · doi:10.1088/1361-6560/ac5e5c · Cited by 25
Temporal Context Matters: Enhancing Single Image Prediction with Disease Progression Representations
Konwer, A., Xu, X., Bae, J., Chen, C., & Prasanna, P. (2022) · 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/cvpr52688.2022.01826 · Cited by 30
“For the COVID-19 chest radiograph datasets, lung region segmentation was first performed using a Residual U-Net model [76] so that features only from lung fields would be analyzed.”
MethodEncoder-Decoder Architectures for Clinically Relevant Coronary Artery Segmentation
Silva, J. L., Menezes, M. N., Rodrigues, T., Silva, B., Pinto, F. J., & Oliveira, A. L. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-17531-2_6 · Cited by 18
“…performance as a function of the number of FLOPS for the DeepLabV3+ [24], FPN [30], LinkNet [31], MANet [32], PAN [33], PSPNet [12], ResUNet [34], The dots represent the following models, in ascending order of FLOPS: EfficientNet - B0, B1, B2, B3, B4, B5, B6, B7; RegNet - Y2, Y4, Y6, Y8,…”
BackgroundRSNet: Rail semantic segmentation network for extracting aerial railroad images
Rampriya, R., Sabarinathan, & Suganya, R. (2021) · Journal of Intelligent & Fuzzy Systems · doi:10.3233/jifs-210349 · Cited by 22
“[68] To build network with residual block which has similar features of U-Net.”
Wang, J., Ji, J., Zhang, M., Lin, J., Zhang, G., Gong, W., Cen, L., Lu, Y., Huang, X., Huang, D., et al. (2021) · JAMA Network Open · doi:10.1001/jamanetworkopen.2021.8758 · Cited by 87
CoordConv-Unet: Investigating CoordConv for Organ Segmentation
Jurdi, R. E., Petitjean, C., Honeine, P., & Abdallah, F. (2021) · IRBM · doi:10.1016/j.irbm.2021.03.002 · Cited by 22
Roads in the Southwestern Amazon, State of Acre, between 2007 and 2019
Nascimento, E. D. S., da Silva, S. S., Bordignon, L., de Melo, A. F. D., Brandão, A., Souza, C., & Silva, C. (2021) · Land · doi:10.3390/land10020106 · Cited by 22
“Some recent studies have shown that Deep Learning techniques can automatically extract roads from high spatial resolution satellite images with high accuracy [14,25].”
BackgroundLuo, C.-C., Li, Y., Lin, K., Chen, G., Lee, S.-J., Choi, J., Yoo, Y., & Polley, M. O. (2020) · Computer Vision and Pattern Recognition · doi:10.1109/cvpr42600.2020.00248 · Cited by 22
“For this reason, UNet [21, 22, 23, 24] like architectures are widely used to feed forward low level feature maps through the skip branches.”
MethodDeep Learning in 5G Wireless Networks - Anomaly Detections
Doan, M., & Zhang, Z. (2020) · Wireless and Optical Communications Conference · doi:10.1109/wocc48579.2020.9114924 · Cited by 22
“In our research, residual unit is used for every two convolutional layers including batch normalization (BN) and ReLU activation function as in [7].”
BackgroundMethodSelf-citationPan, X., Zhao, J., & Xu, J. (2020) · Remote Sensing · doi:10.3390/rs12050852 · Cited by 22
“Based on U-Nets, FCNs, and transmitting structures that add additional spatial information, DSSNNs can improve road border and centerline recognition accuracy obtained from high-resolution remote sensing images [15].”
BackgroundResidual Unet for Urban Building Change Detection with Sentinel-1 SAR Data
Li, L., Wang, C., Zhang, H., & Zhang, B. (2019) · IEEE International Geoscience and Remote Sensing Symposium · doi:10.1109/igarss.2019.8898146 · Cited by 22
“Inspired by the effective result of the road extraction by Residual Unet [9] in the optical remote sensing images, we introduce it to our SAR images building change detection.”
MethodTowards Automatic Extraction and Updating of VGI-Based Road Networks Using Deep Learning
Manandhar, P., Marpu, P., Aung, Z., & Melgani, F. (2019) · Remote Sensing · doi:10.3390/rs11091012 · Cited by 26
“Lngkvist et al. [19] used CNNs along with spectral features of Simple Linear Iterative Clustering (SLIC) segmentation to improve the performance of CNNs. Zhang et al. [25] makes use of a semantic segmentation neural network approach which combines the strengths of residual learning and U-Net.”
Road Detection with EOSResUNet and Post Vectorizing Algorithm
Filin, O. A., Zapara, A., & Panchenko, S. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2018.00036 · Cited by 22
“Another interesting modification of the UNet architecture is Residual Unet [12], which includes Residual blocks [5].”
MethodZhao, B., Zhang, M., Wang, J., Song, X., Gui, Y., Zhang, Y., & Li, W. (2023) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2023.3272978 · Cited by 24
“In recent years, ResUNet was proposed to extract roads [29], and it has achieved good results by using U-Net as a backbone while using residual connections.”
MethodFusing Taxi Trajectories and RS Images to Build Road Map via DCNN
Li, Y., Xiang, L.-G., Zhang, C.-L., & Wu, H.-Y. (2019) · IEEE Access · doi:10.1109/access.2019.2951730 · Cited by 22
“[18] developed a network with few parameters by combining deep residual networks (ResNets) [12] and U-Net [19], and the results exhibited good performance.”
BackgroundMapping urban villages in China: Progress and challenges
Cao, R., Tu, W., Chen, D., & Zhang, W. (2025) · Computers Environment and Urban Systems · doi:10.1016/j.compenvurbsys.2025.102282 · Cited by 24
“Notably, Crivellari et al (2023) employs super-resolution generative adversarial networks (SR-GANs) to upscale Sentinel-2 imagery, subsequently addressing it as a semantic segmentation problem using ResUNet.”
Vanaja, C. B., & Prakasam, P. (2025) · BMC Medical Imaging · doi:10.1186/s12880-025-01625-0 · Cited by 21
“To provide impressive MA segmentation findings concerning specificity, sensitivity, and accuracy, the effective U-Net architecture [14, 15] for biomedical image segmentation has been altered in [16–19], and [20].”
LV-UNet: A Lightweight and Vanilla Model for Medical Image Segmentation
Jiang, J., Wang, M., Tian, H., Cheng, L., & Liu, Y. (2024) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm62325.2024.10822465 · Cited by 21
“Due to the impressive performance of Transformers in visual tasks in recent years, Transformer-based U-Net variants like Trans-UNet [9], Swin-UNet [10], MT-UNet [11] and Unetr [12] and so on have gained wider recognition and have shown remarkable effectiveness.”
CResU-Net: a method for landslide mapping using deep learning
Phạm, T. M., Do, N., Pham, H. T. T., Bui, H., Do, T., & Hoang, M. V. (2024) · Machine Learning: Science and Technology · doi:10.1088/2632-2153/ad5f17 · Cited by 21
“This section compares landslide mapping performance between our proposed CResU-Net model and four other widely used semantic segmentation models, including DeepLabv3 + [53], LinkNet [62], TransUNet [63], and ResU-Net [51].”
Unsupervised Segmentation of 3D Microvascular Photoacoustic Images Using Deep Generative Learning
Sweeney, P. W., Hacker, L., Lefebvre, T. L., Brown, E. L., Gröhl, J., & Bohndiek, S. (2024) · bioRxiv · doi:10.1002/advs.202402195 · Cited by 21
“PAI has demonstrated promise in early-stage clinical trials for various pathologies, [52,53] particularly in oncology, where the FDA has approved the use of PAI in the breast cancer diagnostic pathway.”
Multi-Scale Feature Fusion Attention Network for Building Extraction in Remote Sensing Images
Liu, J., Gu, H., Li, Z.-H., Chen, H.-Y., & Chen, H. (2024) · Electronics · doi:10.3390/electronics13050923 · Cited by 21
Timmins, K., van der Schaaf, I. C., Vos, I., Ruigrok, Y., Velthuis, B., & Kuijf, H. (2023) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2023.3288746 · Cited by 21
“1) Model Architecture: For our method, we use a ResU-net style architecture [36], [37] with MeshCNN [18] convolution and pooling layers.”
MethodBiomedical Image Segmentation with Modified U-Net
Tatli, U., & Budak, C. (2023) · Traitement du signal · doi:10.18280/ts.400211 · Cited by 21
“Classic U-Net 0.9473 0.9034 U-Net11(Proposed) 0.9502 0.9154 ResBCDU-Net [43] 0.9715 RU-Net [22] 0.9493”
InfluentialThe nnU-Net based method for automatic segmenting fetal brain tissues
Peng, Y.-J., Xu, Y.-D., Wang, M.-Z., Zhang, H., & Xie, J.-Y. (2023) · Health Information Science and Systems · doi:10.1007/s13755-023-00220-3 · Cited by 21
Qiao, S., Pang, S., Luo, G., Sun, Y., Yin, W., Pan, S., & Lv, Z. (2023) · Complex & Intelligent Systems · doi:10.1007/s40747-023-00968-x · Cited by 24
“To make a fair performance comparison, we choose several SOTA methods based on CNN and transformer, which include U-Net [16], U-Net ++ [17], Attention U-Net [18], Res-UNet [19], AxialAttention U-Net [37], Gated-Axial-Attention U-Net [33], and MedT [33], respectively.”
BackgroundMethodInfluentialAryal, J., & Neupane, B. (2023) · Remote Sensing · doi:10.3390/rs15020488 · Cited by 18
Küçükdemirci, M., Landeschi, G., Ohlsson, M., & Dell'Unto, N. (2022) · Archaeological Prospection · doi:10.1002/arp.1886 · Cited by 21
Menten, M., Paetzold, J., Dima, A. F., Menze, B. H., Knier, B., & Rueckert, D. (2022) · International Conference on Medical Image Computing and Computer-Assisted Intervention · doi:10.48550/arxiv.2207.11102 · Cited by 21
He, Y. M., Jin, Z., Zhang, J., Teng, S., Chen, G., Sun, X., & Cui, F. (2022) · Applied Sciences · doi:10.3390/app12157364 · Cited by 21
DTU-Net: Learning Topological Similarity for Curvilinear Structure Segmentation
Lin, M., Zepf, K., Christensen, A., Bashir, Z., Svendsen, M. B., Tolsgaard, M., & Feragen, A. (2022) · Information Processing in Medical Imaging · doi:10.48550/arxiv.2205.11115 · Cited by 21
Road extraction from satellite and aerial image using SE-Unet
Sofla, R. A. D., Alipour-Fard, T., & Arefi, H. (2021) · Journal of Applied Remote Sensing · doi:10.1117/1.jrs.15.014512 · Cited by 21
Semantic segmentation and colorization of grayscale aerial imagery with W‐Net models
Dias, M., Monteiro, J., Estima, J., Silva, J., & Martins, B. (2020) · Expert Syst. J. Knowl. Eng. · doi:10.1111/exsy.12622 · Cited by 21
“related to the use of residuals (Zhang et al., 2018b) or other intermediate supervisions.”
BackgroundAbdominal artery segmentation method from CT volumes using fully convolutional neural network
Oda, M., Roth, H. R., Kitasaka, T., Misawa, K., Fujiwara, M., & Mori, K. (2019) · International Journal of Computer Assisted Radiology and Surgery · doi:10.1007/s11548-019-02062-5 · Cited by 21
“The U-Net with residual unit [40] has slightly higher accuracies among the FCN structures.”
BackgroundMethodInfluential
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
