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 501–600 of 1,001
Wang, X., Jin, X.-Z., Dai, Z., Wu, Y., & Chehri, A. (2025) · IEEE Geoscience and Remote Sensing Magazine · doi:10.1109/mgrs.2024.3491014 · Cited by 31
“Combining the advantages of residual networks and U-Net, Zhang et al. [69] constructed a deep residual U-Net (ResUNet) model with residual units as the basic neural units.”
PRCNet: A parallel reverse convolutional attention network for colorectal polyp segmentation
Li, J., Wang, J.-W., Lin, F.-W., Heidari, A., Chen, Y., Chen, H.-L., & Wu, W. (2024) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2024.106336 · Cited by 31
DSEUNet: A lightweight UNet for dynamic space grouping enhancement for skin lesion segmentation
Li, J., Wang, J., Lin, F., Wu, W., Chen, Z., Heidari, A. A., & Chen, H. (2024) · Expert Systems with Applications · doi:10.1016/j.eswa.2024.124544 · Cited by 23
Integrated photonic encoder for low power and high-speed image processing
Wang, X., Redding, B., Karl, N., Long, C., Zhu, Z., Skowronek, J., Pang, S. S., Brady, D., & Sarma, R. (2024) · Nature Communications · doi:10.1038/s41467-024-48099-2 · Cited by 31
“I especially think it is important for them to appropriately reframe their claims in the title, introduction and abstract to accurately reflect the experimentally demonstrated evidence.”
Behera, T. K., Bakshi, S., Khan, M. A., & Albarakati, H. M. (2024) · IEEE Transactions on Consumer Electronics · doi:10.1109/tce.2024.3367531 · Cited by 32
“Some of the frequently used tasks in this domain include building footprint detection [39], [40], road extraction [41], [42], vegetation extraction [43].”
MethodColorectal Polyp Segmentation in the Deep Learning Era: A Comprehensive Survey
Wu, Z.-Y., Lv, F., Chen, C., Hao, A.-M., & Li, S. (2024) · arXiv.org · doi:10.48550/arxiv.2401.11734 · Cited by 31
Fetal ECG extraction from maternal ECG using deeply supervised LinkNet++ model
Rahman, A., Mahmud, S., Chowdhury, M., Yalcin, H., Khandakar, A., Mutlu, O., Mahbub, Z. B., Kamal, R., & Pedersen, S. (2023) · Engineering applications of artificial intelligence · doi:10.1016/j.engappai.2023.106414 · Cited by 31
Rahman, M. H., Chowdhury, M. Z., Utama, I. B. K. Y., & Jang, Y. (2023) · IEEE Transactions on Cognitive Communications and Networking · doi:10.1109/tccn.2023.3239739 · Cited by 31
“Restrictions apply. connection between low levels to high levels [33].”
BackgroundChang, D., Wang, Q.-J., Yang, J., & Xu, W. (2022) · Remote Sensing · doi:10.3390/rs14236015 · Cited by 31
Kittipongdaja, P., & Siriborvornratanakul, T. (2022) · EURASIP Journal on Image and Video Processing · doi:10.1186/s13640-022-00581-x · Cited by 39
“[23] propose a deep ResUNet network for road segmentation, where ResUNet refers to a semantic segmentation neural network that combines the strengths of U-Net and residual neural network.”
BackgroundImproved U-Net3+ with stage residual for brain tumor segmentation
Qin, C.-B., Wu, Y., Liao, W.-Z., Zeng, J.-Y., Liang, S.-F., & Zhang, X.-Z. (2021) · BMC Medical Imaging · doi:10.1186/s12880-022-00738-0 · Cited by 31
“Zhang et al.[9] used the residual structure for encoder and decoder.”
BackgroundCloudU-Netv2: A Cloud Segmentation Method for Ground-Based Cloud Images Based on Deep Learning
Shi, C., Zhou, Y.-T., & Qiu, B. (2021) · Neural Processing Letters · doi:10.1007/s11063-021-10457-2 · Cited by 31
“Recently, deep learning [21–38] has been widely used in various fields with good results.”
BackgroundVision-based UAVs Aerial Image Localization
Xu, Y., Pan, L., Du, C., Li, J., Jing, N., & Wu, J. (2018) · ACM SIGSPATIAL International Workshop on AI for Geographic Knowledge Discovery (GeoAI) · doi:10.1145/3281548.3281556 · Cited by 28
“A team from Beihang University proposed a Residual U-Net[78] with encoding-bridge-decoding structure to extract roads from aerial images.”
BackgroundLiu, H., Huang, B., & Cai, J. (2023) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2023.3236106 · Cited by 27
“They are a popular end-to-end segmentation network, ResUnet [47], two temporal-based CRNs, CRN [44] and STS-CNN [46], and one multisource-based CRN, DSen2-CR [35].”
BackgroundMethodMultimodal Magnetic Resonance Image Brain Tumor Segmentation Based on ACU-Net Network
Tan, L., Ma, W.-J., Xia, J.-M., & Sarker, S. (2021) · IEEE Access · doi:10.1109/access.2021.3052514 · Cited by 31
“The improved U-Net algorithms [10], [33], [34] are included.”
BackgroundYang, C. F., & Wang, Z. (2020) · IEEE Access · doi:10.1109/access.2020.3026084 · Cited by 38
Not All Diffusion Model Activations Have Been Evaluated as Discriminative Features
Meng, B.-Y., Xu, Q.-Q., Wang, Z.-T., Cao, X.-C., & Huang, Q.-M. (2024) · Neural Information Processing Systems · doi:10.48550/arxiv.2410.03558 · Cited by 30
“Furthermore, as shown in Appendix A, such an asymmetric pattern is consistent across activations in different diffusion models.”
BackgroundKariminejad, N., Shahabi, H., Ghorbanzadeh, O., Shafaie, V., Hosseinalizadeh, M., Homayouni, S., & Pourghasemi, H. (2024) · Earth Systems and Environment · doi:10.1007/s41748-024-00419-8 · Cited by 30
“This enhanced model, rather than adhering to the conventional U-Net framework, introduces structures grounded in residual learning blocks, marking a departure from the plain convolution layers (Zhang et al. 2018).”
Boundary-Aware Gradient Operator Network for Medical Image Segmentation
Yu, L., Min, W.-W., & Wang, S.-F. (2024) · IEEE journal of biomedical and health informatics · doi:10.1109/jbhi.2024.3404273 · Cited by 30
“For example, U-Net achieves excellent medical image segmentation performance in a variety of different imaging modes and is frequently cited in various computer vision subfields, including ResU-Net [20], U-Net++ [21], MS-UNet [22], etc.”
BackgroundNeural deformation fields for template-based reconstruction of cortical surfaces from MRI
Bongratz, F., Rickmann, A.-M., & Wachinger, C. (2024) · Medical Image Anal. · doi:10.1016/j.media.2024.103093 · Cited by 30
Yang, S.-K., Zhang, X., Chen, Y.-F., Jiang, Y., Feng, Q., Pu, L., & Sun, F. (2023) · Knowledge-Based Systems · doi:10.1016/j.knosys.2023.110868 · Cited by 30
Vegetation Extraction from UAV-based Aerial Images through Deep Learning
Behera, T., Bakshi, S., & Sa, P. K. (2022) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2022.107094 · Cited by 30
Huang, Z., Tang, S., Chen, Z., Wang, G.-S., Shen, H., Zhou, Y., Wang, H.-N., Fan, W., Liang, D., Hu, Y.-Y., et al. (2022) · Comput. Biol. Medicine · doi:10.1016/j.compbiomed.2022.105869 · Cited by 30
Wang, Z., Xu, N., Wang, B.-H., Liu, Y., & Zhang, S. (2022) · GIScience & Remote Sensing · doi:10.1080/15481603.2022.2076382 · Cited by 30
“Zhang, Liu, and Wang (2015) combined residual learning and U-Net proposed a lightweight neural network model for building extraction, which uses residual learning to accelerate the model training process, and uses skip connection for information interaction between different features.”
BackgroundRatUNet: residual U-Net based on attention mechanism for image denoising
Zhang, H., Lian, Q.-S., Zhao, J.-M., Wang, Y.-N., Yang, Y., & Feng, S.-Q. (2022) · PeerJ Computer Science · doi:10.7717/peerj-cs.970 · Cited by 30
“Zhang, Zuo & Zhang (2018) presented a fast and flexible network (FFDNet) which has the ability to remove spatially variant noise.”
BackgroundMethodSelf-citationDilated transformer: residual axial attention for breast ultrasound image segmentation
Shen, X., Wang, L., Zhao, Y. Q., Liu, R., Qian, W., & Ma, H. (2022) · Quantitative Imaging in Medicine and Surgery · doi:10.21037/qims-22-33 · Cited by 32
Deep Residual Autoencoder with Multiscaling for Semantic Segmentation of Land-Use Images
Li, L. (2019) · Remote Sensing · doi:10.3390/rs11182142 · Cited by 30
“CNN was used to extract the roads based on aerial images [29,30].”
BackgroundMethodInfluentialReducing the U-Net size for practical scenarios: Virus recognition in electron microscopy images
Matuszewski, D. J., & Sintorn, I. (2019) · Comput. Methods Programs Biomed. · doi:10.1016/j.cmpb.2019.05.026 · Cited by 30
Frequency-Enhanced Lightweight Vision Mamba Network for Medical Image Segmentation
Liu, S.-W., Lin, Y., Liu, D., Wang, P., Zhou, B., & Si, F. (2025) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2025.3527526 · Cited by 30
“Subsequently, numerous improved variants of UNets have emerged, such as AttUNet [10], UNet ++ [11], ResUNet [12], MADRU-Net [13], UNext [14], CMUNeXt [15], RollingUNet [16], and CANet [17].”
AMD-SD: An Optical Coherence Tomography Image Dataset for wet AMD Lesions Segmentation
Hu, Y., Gao, Y.-D., Gao, W.-H., Luo, W.-B., Yang, Z., Xiong, F., Chen, Z., Lin, Y., Xia, X., Yin, X., et al. (2024) · Scientific Data · doi:10.1038/s41597-024-03844-6 · Cited by 29
Rs-net: Residual Sharp U-Net architecture for pavement crack segmentation and severity assessment
Ali, L., Aljassmi, H., Swavaf, M., Khan, W., & Alnajjar, F. (2024) · Journal of Big Data · doi:10.1186/s40537-024-00981-y · Cited by 29
“Residual U-Net is an enhanced version of the U-Net architecture that integrates Residual Neural Networks and U-Net model strengths, resulting in better performance in image segmentation tasks [75].”
BackgroundDGD-cGAN: A dual generator for image dewatering and restoration
González-Sabbagh, S., Robles‐Kelly, A., & Gao, S. (2023) · Pattern Recognition · doi:10.1016/j.patcog.2023.110159 · Cited by 51
Feng, D.-J., Chen, H., Xie, Y.-K., Liu, Z., Liao, Z., Zhu, J., & Zhang, H. (2022) · International Journal of Applied Earth Observation and Geoinformation · doi:10.1016/j.jag.2022.103046 · Cited by 29
Single-Shot End-to-end Road Graph Extraction
Bahl, G., Bahri, M., & Lafarge, F. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw56347.2022.00146 · Cited by 29
“The first kind [5,26,44,45] relies on a pixel-based segmentation which is then converted to a graph using compute-intensive handcrafted algorithms that require a lot of manual tuning and can often yield partial graphs.”
BackgroundMethodGDCSeg-Net: general optic disc and cup segmentation network for multi-device fundus images.
Zhu, Q.-L., Chen, X.-J., Meng, Q., Song, J., Luo, G., Wang, M., Shi, F., Chen, Z., Xiang, D.-H., Pan, L., et al. (2021) · Biomedical Optics Express · doi:10.1364/boe.434841 · Cited by 29
“(1) Comparison experiments With the same data split strategy, we compare our method with other excellent CNN based methods, including FCN, U-Net, CE-Net, CPFNet, Attention U-Net, U-Net++, Deep ResU-Net, ResU-Net++, CS2Net and SegNet.”
MethodInfluentialCT-UNet: Context-Transfer-UNet for Building Segmentation in Remote Sensing Images
Liu, S., Ye, H.-R., Jin, K., & Cheng, H. (2021) · Neural Processing Letters · doi:10.1007/s11063-021-10592-w · Cited by 29
Cira, C.-I., Alcarria, R., Manso-Callejo, M.-Á., & Serradilla, F. (2020) · Applied Sciences · doi:10.3390/app10207272 · Cited by 29
“[28] purpose ResUnet for road extraction by semantic segmentation on the Massachusetts roads dataset, replacing the convolutional blocks with residual modules.”
MethodSoftware Engineering Practice in the Development of Deep Learning ApplicationsPreprint
Zhang, X., Yang, Y., Feng, Y., & Chen, Z. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1910.03156 · Cited by 27
Mohajerani, S., & Saeedi, P. (2019) · IEEE Transactions on Image Processing · doi:10.1109/tip.2019.2904267 · Cited by 29
“Many researches have shown that skip connections have a significant impact on the convergence time of networks and therefore they improve the overall performance [34], [36], [37].”
BackgroundRWKV-UNet: Improving UNet with Long-Range Cooperation for Effective Medical Image Segmentation
Jiang, J.-T., Zhang, J.-N., Liu, W.-X., Gao, M., Hu, X.-B., Xue, Z.-C., Liu, Y., & Yan, S.-C. (2025) · arXiv.org · doi:10.48550/arxiv.2501.08458 · Cited by 28
“Variations based on U-Net improve its performance through various means, which include using developed encoders [13], [14], gating mechanisms to focus on important features [15], improving skip connection formats [16], [17], [18] to recover more spatial details, as well as adaptations for 3D images…”
Li, Y., Fu, B., Yin, Y., Hu, X., Wang, W., Wang, W., Li, X. S., & Long, G. (2024) · Intelligent geoengineering. · doi:10.1016/j.ige.2024.10.003 · Cited by 40
BD-SKUNet: Selective-Kernel UNets for Building Damage Assessment in High-Resolution Satellite Images
Ahmadi, S. A., Mohammadzadeh, A., Yokoya, N., & Ghorbanian, A. (2023) · Remote Sensing · doi:10.3390/rs16010182 · Cited by 34
DBU-Net: Dual branch U-Net for tumor segmentation in breast ultrasound images
Pramanik, P., Pramanik, R., Schwenker, F., & Sarkar, R. (2023) · PLoS ONE · doi:10.1371/journal.pone.0293615 · Cited by 27
“For example, Deep Residual U-Net [24] integrates residual blocks into the encoder and decoder layers, which deepens the network and enhances its performance.”
BackgroundPark, B., Shin, T.-S., Kang, R., Fong, A. Y., McDonogh, B., & Yoon, S.-C. (2023) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2023.107802 · Cited by 31
SU-Net: pose estimation network for non-cooperative spacecraft on-orbit
Gao, H., Li, Z., Wang, N., Yang, J., & Dang, D. (2023) · Scientific Reports · doi:10.1038/s41598-023-38974-1 · Cited by 25
“To enhance its effectiveness, subsequent researchers have improved the model, such as 38–41 .”
BackgroundSwinv2-Imagen: hierarchical vision transformer diffusion models for text-to-image generation
Li, R., Li, W., Yang, Y., Wei, H., Jiang, J., & Bai, Q. (2023) · Neural Computing and Applications · doi:10.1007/s00521-023-09021-x · Cited by 37
“In the following subsections, we describe the main components of Swinv2-Imagen in detail.”
Deep Neural Network for Lung Image Segmentation on Chest X-ray
Chavan, M., Varadarajan, V., Gite, S., & Kotecha, K. (2022) · Technologies · doi:10.3390/technologies10050105 · Cited by 28
Diabetic foot thermal image segmentation using Double Encoder-ResUnet (DE-ResUnet)
Bouallal, D., Douzi, H., & Harba, R. (2022) · Journal of Medical Engineering & Technology · doi:10.1080/03091902.2022.2077997 · Cited by 29
“studies [26, 27] and the second one is to take advan-”
BackgroundResearch on epileptic EEG recognition based on improved residual networks of 1-D CNN and indRNN
Ma, M., Cheng, Y., Wei, X.-H., Chen, Z., & Zhou, Y. (2021) · BMC Medical Informatics and Decision Making · doi:10.1186/s12911-021-01438-5 · Cited by 28
“The residual architecture [35] used in this experiment is a convolutional network of three residual blocks, as shown in the Fig.”
MethodRaj, R., Londhe, N. D., & Sonawane, R. S. (2021) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2021.106123 · Cited by 33
Alvarado-Carrillo, D. E., Ovalle-Magallanes, E., & Dalmau-Cedeño, O. S. (2021) · International Symposium on Geometry and Vision · doi:10.1007/978-3-030-72073-5_29 · Cited by 28
“Besides, the conventional convolutional blocks of each level have been replaced with residual convolutional blocks, similarly to previous works presented for segmentation of curvilinear objects in [17,39].”
MethodAn automated estimator for Cobb angle measurement using multi-task networks
Fu, X., Yang, G., Zhang, K., Xu, N., & Wu, J. (2020) · Neural computing & applications (Print) · doi:10.1007/s00521-020-05533-y · Cited by 28
Wang, H., Zhang, H., Hu, J., Song, Y., Bai, S., & Zhang, Y. (2020) · International Journal of Intelligent Systems · doi:10.1002/int.22280 · Cited by 29
Brandt, J., & Stolle, F. (2020) · International Journal of Remote Sensing · doi:10.1080/01431161.2020.1841324 · Cited by 42
“Many studies have concluded that the U-net significantly outperforms other machine learning classifiers for remote-sensing tasks with high-resolution imagery (Diakogiannis et al. 2019; Li et al. 2017; Feng et al. 2019; Xu et al. 2018; Zhang, Liu, and Wang 2018).”
BackgroundMethodInfluentialA Cross Entropy Based Deep Neural Network Model for Road Extraction from Satellite Images
Shan, B., & Fang, Y. (2020) · Entropy · doi:10.3390/e22050535 · Cited by 28
“Zhang et al. [9] proposed a Deep Residual U-Net (DRUnet), which combines the deep residual learning and U-Net architecture for road extraction.”
BackgroundInfluentialConductive particle detection via deep learning for ACF bonding in TFT-LCD manufacturing
Liu, E., Chen, K., Xiang, Z., & Zhang, J. (2019) · Journal of Intelligent Manufacturing · doi:10.1007/s10845-019-01494-9 · Cited by 31
“In Zhang et al. (2018), there are three residual blocks in down and up streams, and one additional convolution layer in up stream, with each residual block including two convolution layers.”
BackgroundMethodPeng, F., Zheng, X., & Miao, Q. (2023) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2023.3308239 · Cited by 28
“Next, a ResUNet-based deep learning network is trained using the simulated dataset to establish a mapping relationship between the wrapped phase (affected by multiple noise in ϕ-OTDR) and real phase [19], [20], [21].”
InfluentialSaputra, M. R. U., Bhaswara, I. D., Nasution, B. I., Ang, M. L. E., Husna, N. L. R., Witra, T., Feliren, V., Owen, J. R., Kemp, D., & Lechner, A. M. (2024) · Remote Sensing of Environment · doi:10.1016/j.rse.2024.114584 · Cited by 35
Reasoning cartographic knowledge in deep learning-based map generalization with explainable AI
Fu, C., Zhou, Z., Xin, Y., & Weibel, R. (2024) · International Journal of Geographical Information Systems · doi:10.1080/13658816.2024.2369535 · Cited by 30
“The pre-trained DNN we try to explore is a ResU-Net (Zhang et al .”
MethodInfluentialProMamba: Prompt-Mamba for polyp segmentation
Xie, J., Liao, R.-F., Zhang, Z., Yi, S., Zhu, Y.-S., & Luo, G.-B. (2024) · arXiv.org · doi:10.48550/arxiv.2403.13660 · Cited by 27
“Subsequent models like ResUNet [3] and ResUNet++ [4] incorporate residual connections into the U-Net structure, mitigating gradient vanishing issues and improving segmentation effectiveness.”
MethodSelf-citationA self-supervised network for image denoising and watermark removal
Tian, C., Xiao, J., Zhang, B., Zuo, W., Zhang, Y., & Lin, C. (2024) · Neural Networks · doi:10.1016/j.neunet.2024.106218 · Cited by 27
Yang, Y., Zhou, W., Jiskani, I. M., & Wang, Z. (2024) · Expert Systems with Applications · doi:10.1016/j.eswa.2024.123628 · Cited by 30
A comparison of art style transfer in Cycle-GAN based on different generators
Ma, X. (2024) · Journal of Physics, Conference Series · doi:10.1088/1742-6596/2711/1/012006 · Cited by 27
“In the case of two-lane roads, U-Net demonstrated high confidence in segmenting each lane [3].”
BackgroundUnfolded deep kernel estimation-attention UNet-based retinal image segmentation
Radha, K., Yepuganti, K., Saritha, S., Kamireddy, C., & Bavirisetti, D. P. (2023) · Scientific Reports · doi:10.1038/s41598-023-48039-y · Cited by 27
“Specifically, UNet 9, 16–18, 32 , filters or layers 19, 20 , wavelet”
Traffic Analysis Through Deep-Learning-Based Image Segmentation From UAV Streaming
Bisio, I., Garibotto, C., Haleem, H., Lavagetto, F., & Sciarrone, A. (2022) · IEEE Internet of Things Journal · doi:10.1109/jiot.2022.3223283 · Cited by 32
“However, rather than using standard CNN layers, the ResUNet model [30] utilized residual layers to achieve high performance while retaining a low level of complexity.”
MethodInfluentialSemantic Segmentation of Hyperspectral Remote Sensing Images Based on PSE-UNet Model
Li, J., Wang, H., Zhang, A., & Liu, Y. (2022) · Sensors · doi:10.3390/s22249678 · Cited by 32
Are 3D better than 2D Convolutional Neural Networks for Medical Imaging Semantic Segmentation?
Crespi, L., Loiacono, D., & Sartori, P. (2022) · IEEE International Joint Conference on Neural Network · doi:10.1109/ijcnn55064.2022.9892850 · Cited by 27
“To answer this question, in this work we compared 2D CNN and 3D CNN based on the ResUnet architecture [4] on three different segmentation task: (i) identifying tumoral lesions in brain MRI, (ii) segmenting trachea, and (iii) spinal cord in thoracic CT scans.”
MethodRed Tide Detection Method for HY−1D Coastal Zone Imager Based on U−Net Convolutional Neural Network
Zhao, X., Liu, R., Ma, Y., Xiao, Y., Ding, J., Liu, J., & Wang, Q. (2021) · Remote Sensing · doi:10.3390/rs14010088 · Cited by 31
“U−Net has been widely used in medical diagnosis [46,47], remote sensing [48], and other fields [49,50] as a pixel−wise prediction model that can be trained in an end−to−end manner.”
MethodWilson, R. J., de Siqueira, A. F., Brooks, S. J., Price, B. W., Simon, L., van der Walt, S., & Fenberg, P. B. (2022) · Methods in Ecology and Evolution · doi:10.1111/2041-210x.13844 · Cited by 36
“To recognize image elements (specimen, scale, and labels), we use a U-Net convolutional neural network (Ronneberger et al. 2015) with ResNet-34 (He et al. 2016) in the analysis path (Zhang et al. 2018; Paszke et al. 2019; Howard & Gugger 2020).”
MethodWu, X., Liu, X., & Duan, J. (2021) · Powder Technology · doi:10.1016/j.powtec.2021.04.045 · Cited by 27
Robust Deep Neural Networks for Road Extraction From Remote Sensing Images
Li, P., He, X.-H., Qiao, M.-J., Cheng, X., Li, Z., Luo, H., Song, D., Li, D., Hu, S., Li, R., et al. (2020) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2020.3023112 · Cited by 27
“With the advent of deep residual learning and u-net, Zhang et al. [33] proposed ResUnet that combined the strengths of the residual unit and u-net.”
BackgroundMethodInfluentialDeep learning based automated analysis of archaeo‐geophysical images
Küçükdemirci, M., & Sarris, A. (2020) · Archaeological Prospection · doi:10.1002/arp.1763 · Cited by 41
“Considering the promising results of U-Net for biomedical images (Mittal et al., 2019; Ronneberger et al., 2015), road extraction (Zhang, Liu, & Wang, 2018) and building extraction (Xu, Wu, Xie, & Chen, 2018) from aerial images, we considered the adaptation of this approach for analysis of features…”
BackgroundKarabağ, C., Verhoeven, J., Miller, N., & Reyes-Aldasoro, C. (2019) · Applied Sciences · doi:10.3390/app9183900 · Cited by 27
“U-Nets have been used widely, for instance, for road extraction [47], singing voice”
MethodCFRNet: Road Extraction in Remote Sensing Images Based on Cascade Fusion Network
Xiong, Y., Li, L., Yuan, D., Wang, H., Ma, T., Wang, Z., & Yang, Y. (2024) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2024.3409758 · Cited by 27
“Combining the strengths of residual learning and U-Net, Zhang et al. [9] designed a network which was built with residual units and it had a similar architecture to that of U-Net.”
BackgroundResultFeng, W.-Q., Guan, F.-L., Sun, C., & Xu, W. (2024) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2024.3430900 · Cited by 27
“Furthermore, the existing research primarily focuses on models trained on specific small-scale road datasets, restricting their generalizability across different datasets and their robustness for practical use [8], [9].”
BackgroundMethodImproving Semantic Segmentation in Aerial Imagery via Graph Reasoning and Disentangled Learning
Niu, R., Sun, X., Tian, Y., Diao, W., Feng, Y., & Fu, K. (2021) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2021.3121471 · Cited by 37
“A S ONE of the most fundamental tasks in remote-sensing image interpretation, semantic segmentation has been widely applied to road extraction [1], infrastructure planning [2], urban change detection [3], and so on.”
BackgroundGuo, Q., & Wang, Z.-P. (2020) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2020.3014242 · Cited by 27
Guo, P.-W., Meng, X., Meng, W.-N., & Bao, Y. (2024) · Automation in Construction · doi:10.1016/j.autcon.2024.105787 · Cited by 26
Lensless Efficient Snapshot Hyperspectral Imaging using Dynamic Phase Modulation
Zhang, C., Liu, X., Wang, L., Ma, S.-N., Zheng, Y., Liu, Y., Huang, H., Wang, Y.-T., & Song, W.-T. (2024) · Photonics Research · doi:10.1364/prj.543621 · Cited by 26
“The deep-learning-based methods include U-net [47] and its variants [48], RNN [49], Transformer [50], LSTM [17], and Mamba [51].”
Self-citationKhankeshizadeh, E., Tahermanesh, S., Mohsenifar, A., Moghimi, A., & Mohammadzadeh, A. (2024) · Ecological Indicators · doi:10.1016/j.ecolind.2024.112589 · Cited by 26
Mapping Remote Roads Using Artificial Intelligence and Satellite Imagery
Sloan, S., Talkhani, R. R., Huang, T., Engert, J. E., & Laurance, W. F. (2024) · Remote Sensing · doi:10.3390/rs16050839 · Cited by 29
Tan, D.-Y., Yao, Z., Peng, X., Ma, H.-P., Dai, Y.-K., Su, Y., & Zhong, W.-M. (2024) · IEEE Transactions on Emerging Topics in Computational Intelligence · doi:10.1109/tetci.2023.3306250 · Cited by 26
“Subsequent variant networks have enhanced the encoder feature extraction capability by introducing residual connection [13], dense connection [32], and other ideas in the feature extraction block.”
BackgroundMRA-UNet: balancing speed and accuracy in road crack segmentation network
Gao, X.-W., & Tong, B.-R. (2022) · Signal, Image and Video Processing · doi:10.1007/s11760-022-02423-9 · Cited by 26
“Zhang et al. proposed ResUNet [9], which combines UNet and ResNet after forming a new network structure.”
MethodInfluentialHuang, Y., Liu, Z., Zheng, G., & Zhao, C. (2022) · Ecological Indicators · doi:10.1016/j.ecolind.2022.109704 · Cited by 26
Fan, L., Yuan, J.-B., Zha, K.-L., & Wang, X. (2022) · Remote Sensing · doi:10.3390/rs14205225 · Cited by 26
“This method identified 65–75% of craters in common with a human-annotated dataset, and [39] used the ResUNET [30] model to detect craters with the global maps and infra-red imagery for Mars.”
MethodShi, J., Sun, B., Ye, X., Wang, Z., Luo, X., Liu, J., Gao, H., & Li, H. (2022) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2022.3221529 · Cited by 28
Automatic Pancreatic Cyst Lesion Segmentation on EUS Images Using a Deep-Learning Approach
Oh, S. H., Kim, Y. J., Park, Y., & Kim, K. G. (2021) · Sensors · doi:10.3390/s22010245 · Cited by 31
“We also employed the Residual U-Net [21], U-Net++ [22], and Basic U-Net for comparison with the Attention U-Net.”
MethodHillsley, A. V., Santos, J. E., & Rosales, A. M. (2021) · Scientific Reports · doi:10.1038/s41598-021-01304-4 · Cited by 27
“This type of model was first utilized by Ronnenberger et al. in their UNet 39 and has since been built upon, including but not limited to ResUNet 40 , ENet 41 , FRRN 42 , and ERFNet 43 .”
Generating 3D digital material twins for woven ceramic‐matrix composites from μCT images
Chen, Y.-H., Chen, Y., Wang, D., & Ai, S.-G. (2021) · Journal of The American Ceramic Society · doi:10.1111/jace.18044 · Cited by 26
Orthogonal Ensemble Networks for Biomedical Image Segmentation
Larrazabal, A. J., Mart'inez, C., Dolz, J., & Ferrante, E. (2021) · International Conference on Medical Image Computing and Computer-Assisted Intervention · doi:10.1007/978-3-030-87199-4_56 · Cited by 26
“For all the experiments, the backbone segmentation network was a state-of-the-art ResUNet architecture [23] implemented in Keras 2.”
MethodPrieto, J., Shah, H., Rosenbaum, A. J., Jiang, X.-N., Musonda, P., Price, J., Stringer, E., Vwalika, B., Stamilio, D., & Stringer, J. (2021) · Medical Imaging · doi:10.1117/12.2582243 · Cited by 26
MIGN: Multiscale Image Generation Network for Remote Sensing Image Semantic Segmentation
Nie, J., Wang, C., Yu, S., Shi, J., Lv, X., & Wei, Z. (2022) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2022.3197369 · Cited by 31
GAN-Based Satellite Imaging: A Survey on Techniques and Applications
Mansourifar, H., Moskovitz, A., Klingensmith, B., Mintas, D., & Simske, S. (2022) · IEEE Access · doi:10.1109/access.2022.3221123 · Cited by 43
“U-Net [74], [75] is one of the well-known deep neural network architectures with a symmetrical structure that looks like a U letter.”
BackgroundA Parcel-Based Deep-Learning Classification to Map Local Climate Zones From Sentinel-2 Images
Zhou, Y., Wei, T., Zhu, X., & Collin, M. (2021) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2021.3071577 · Cited by 32
Machine/deep learning‐assisted hemoglobin level prediction using palpebral conjunctival images
Kato, S., Chagi, K., Takagi, Y., Hidaka, M., Inoue, S., Sekiguchi, M., Adachi, N., Sato, K., Kawai, H., & Kato, M. (2024) · British Journal of Haematology · doi:10.1111/bjh.19621 · Cited by 21
Song, Y., Wang, J., Ge, Y., Li, L., Guo, J., Dong, Q., & Liao, Z. (2024) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2024.104212 · Cited by 24
Huang, Z.-Y., Zhao, Y., Yu, Z., Qin, P., Han, X., Wang, M., Liu, M., & Gregersen, H. (2024) · Comput. Methods Programs Biomed. · doi:10.1016/j.cmpb.2024.108235 · Cited by 25
GAN inversion-based semi-supervised learning for medical image segmentation
Feng, X., Lin, J.-Y., Feng, C.-M., & Lu, G.-M. (2024) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2023.105536 · Cited by 25
Noor, M. N., Nazir, M., Khan, S. S., Ashraf, I., & Song, O.-Y. (2023) · Applied Sciences · doi:10.3390/app13159031 · Cited by 25
ICUnet++: an Inception-CBAM network based on Unet++ for MR spine image segmentation
Li, L., Qin, J., Lv, L., Cheng, M., Wang, B., Xia, D., & Wang, S. (2023) · International Journal of Machine Learning and Cybernetics · doi:10.1007/s13042-023-01857-y · Cited by 25
“8d makes Unet [14] 0.8142 0.8920 0.8925 0.8916 25 s Unet++ [15] 0.8170 0.8925 0.8913 0.8927 40 s ResUnet [38] 0.8169 0.8930 0.8956 0.8926 32 s DenseUnet [39] 0.8137 0.8909 0.8913 0.8928 37 s RARUnet [40] 0.8215 0.8950 0.8972 0.8946 43 s mRRUnet [41] 0.8212 0.8945 0.8977 0.8950 50 s ICUnet++ (Ours)…”
Influential
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
