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
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 901–1,000 of 1,001
TOWARDS FINE-GRAINED ROAD MAPS EXTRACTION USING SENTINEL-2 IMAGERY
Ayala, C., Aranda, C., & Galar, M. (2021) · ISPRS annals of the photogrammetry, remote sensing and spatial information sciences · doi:10.5194/isprs-annals-v-3-2021-9-2021 · Cited by 15
“IoU(y, ŷ) = y ∩ ŷ y ∪ ŷ F1(y, ŷ) = 2yŷ y + ŷ (2) Like other works (Mnih and Hinton, 2010, Zhang et al., 2018) we have performed precision relaxation aiming at reducing the impact of the low spatial resolution on the metrics.”
BackgroundInfluentialKarabağ, B., Ayturan, K., & Hardalaç, F. (2026) · Diagnostics · doi:10.3390/diagnostics16050649 · Cited by 14
Extraction of Levees from Paddy Fields Based on the SE-CBAM UNet Model and Remote Sensing Images
Ai, H.-F., Zhu, X.-M., Han, Y.-Q., Ma, S., Wang, Y., Ma, Y.-H., Qin, C., Han, X.-Y., Yang, Y.-X., & Zhang, X.-L. (2025) · Remote Sensing · doi:10.3390/rs17111871 · Cited by 14
Self-citationLiterature review on deep learning for the segmentation of seismic images
Monteiro, B. A. A., Canguçu, G. L., Jorge, L. M. S., Vareto, R. H., Oliveira, B. S., Silva, T. H., Lima, L. A., Machado, A. M. C., Schwartz, W. R., & de Melo, P. O. S. V. (2024) · Earth-Science Reviews · doi:10.1016/j.earscirev.2024.104955 · Cited by 17
Sim, W., Yim, J.-S., & Lee, J. (2024) · Remote Sensing · doi:10.3390/rs16142623 · Cited by 16
Xu, C., Wu, X., Wang, B., Chen, J., Gao, Z.-F., Liu, X., & Zhang, H.-Y. (2024) · Comput. Medical Imaging Graph. · doi:10.1016/j.compmedimag.2024.102414 · Cited by 14
MADR-Net: multi-level attention dilated residual neural network for segmentation of medical images
Keerthiveena, B., Ramteke, M., Mittal, S., Bhargava, R., & Rathore, A. S. (2024) · Scientific Reports · doi:10.1038/s41598-024-63538-2 · Cited by 14
Detailed preform design procedure considering the effect of heat treatment in IN718 disk forging
Kim, K., Han, B., Kim, Y., & Kim, N. (2024) · Journal of Materials Research and Technology · doi:10.1016/j.jmrt.2024.04.181 · Cited by 14
Wan, C., Fang, J., Li, K., Zhang, Q., Zhang, S., & Yang, W. (2024) · Comput. Biol. Medicine · doi:10.1016/j.compbiomed.2024.108281 · Cited by 14
Uncertainty-aware prototypical learning for anomaly detection in medical images
Huang, C., Shi, Y., Zhang, B., & Lyu, K. (2024) · Neural Networks · doi:10.1016/j.neunet.2024.106284 · Cited by 14
MPFC-Net: A multi-perspective feature compensation network for medical image segmentation
Wu, X.-H., Huang, S., Shu, X., Hu, C.-L., & Wu, X.-J. (2024) · Expert systems with applications · doi:10.1016/j.eswa.2024.123430 · Cited by 14
Yuan, L., Song, J., & Fan, Y. (2024) · PeerJ Computer Science · doi:10.7717/peerj-cs.1798 · Cited by 14
“Based on the inspiration from deep residual learning (ResNet), Zhang, Liu & Wang (2018) proposed ResUnet.”
BackgroundLiu, Y., Han, L., Yao, B., & Li, Q. (2023) · Signal Image and Video Processing · doi:10.1007/s11760-023-02893-5 · Cited by 15
Luo, W.-R., Zhang, C.-C., Li, Y., & Yan, Y. (2023) · Remote Sensing · doi:10.3390/rs15163934 · Cited by 14
Yan, G., Jing, H.-T., Li, H., Guo, H., & He, S. (2023) · Remote Sensing · doi:10.3390/rs15153766 · Cited by 14
Prototype-Driven and Multiexpert Integrated Multimodal MR Brain Tumor Image Segmentation
Zhang, Y., Li, Z.-Y., Li, H.-F., & Tao, D.-P. (2023) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2024.3500067 · Cited by 14
Yuan, H., Wang, S., Bao, Z., & Wang, S. (2023) · Proceedings of the VLDB Endowment · doi:10.14778/3611479.3611504 · Cited by 9
DRI-UNet: dense residual-inception UNet for nuclei identification in microscopy cell images
Sharma, A., & Mishra, P. K. (2023) · Neural computing & applications (Print) · doi:10.1007/s00521-023-08729-0 · Cited by 14
“[ 20 ], R2-UNet [21], ResUNet [22], Multi-ResUNet [15], DC-UNet [23], Inception-UNet [9], MSRF-Net [24], FANet [25], and CFPNet-M [26], confirm the effectiveness of the proposed model.”
MethodResultNeighborhood Attention Makes the Encoder of ResUNet Stronger for Accurate Road Extraction
Jamali, A., Roy, S. K., Li, J., & Ghamisi, P. (2023) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2024.3354560 · Cited by 14
“In this work, we adopted the seven-layer ResUNet architecture initially developed by Zhang et al. [1] to address the accurate road extraction task as the backbone, illustrated in Fig.”
BackgroundMethodInfluentialÖztürk, O., Ișık, M. S., Kada, M., & Şeker, D. Z. (2023) · Applied Sciences · doi:10.3390/app13106161 · Cited by 16
Mapping stone walls in Northeastern USA using deep learning and LiDAR data
Suh, J. W., & Ouimet, W. B. (2023) · GIScience & Remote Sensing · doi:10.1080/15481603.2023.2196117 · Cited by 19
“…Drolet, and Brown 2019; Srivastava, Vargas-Muñoz, and Tuia 2019; Li et al. 2020; Zhang et al. 2020; Rodríguez, Vitrià, and Mora 2020; Kim et al. 2018) and urban structures mapping (Zhang, Liu, and Wang 2018; Wang and Li 2019; Tan, Xiong, and Li 2018; Abdollahi et al. 2020; Zhang et al. 2018).”
BackgroundMethodWeakly Supervised Caveline Detection for AUV Navigation Inside Underwater Caves
Yu, B.-X., Tibbetts, R., Барна, Т. Б., Morales, A., Rekleitis, I. M., & Islam, M. (2023) · IEEE/RJS International Conference on Intelligent RObots and Systems · doi:10.1109/iros55552.2023.10342435 · Cited by 14
“• UNet [43]: While originally proposed for medical image segmentation, many UNet variants [52, 50, 15] have been proposed for different application domains over the years.”
BackgroundDynamic Loss Weighting for Multiorgan Segmentation in Medical Images
Song, Y.-Y., Teoh, J. Y.-C., Choi, K., & Qin, J. (2023) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2023.3243241 · Cited by 14
“In detail, we chose three commonly used segmentation networks: UNet [51], ResUNet [52], and Inception [53], as the backbone network, and used two typical loss functions: Dice loss and CE loss [17], for training.”
MethodMunafò, R., Saitta, S., Ingallina, G., Denti, P., Maisano, F., Agricola, E., Redaelli, A. C. L., & Votta, E. (2024) · IEEE Access · doi:10.1109/access.2024.3349698 · Cited by 22
“The trained CNN was based on a modified 3D U-Net [28] with encoding and decoding branches of 5 resolution levels each, defined using residual units as shown in [29].”
Using Machine Learning to Predict Multiphase Flow through Complex Fractures
Ting, A., Santos, J. E., & Guiltinan, E. J. (2022) · Energies · doi:10.3390/en15238871 · Cited by 14
RING-Net: road inference from GPS trajectories using a deep segmentation network
Eftelioglu, E., Garg, R., Kango, V., Gohil, C., & Chowdhury, A. R. (2022) · BigSpatial@SIGSPATIAL · doi:10.1145/3557917.3567617 · Cited by 14
“Therefore, instead of re-discovering the whole road network, a conflation step [13, 45], which extracts the missing road segments with respect to a given map, can be used.”
BackgroundDental Lesion Segmentation Using an Improved ICNet Network with Attention
Ma, T., Zhou, X., Yang, J., Meng, B., Qian, J., Zhang, J., & Ge, G. (2022) · Micromachines · doi:10.3390/mi13111920 · Cited by 15
Semisupervised white matter hyperintensities segmentation on MRI
Huang, F., Xia, P., Vardhanabhuti, V., Hui, S. K., Lau, K. K., Mak, H. K., & Cao, P. (2022) · Human Brain Mapping · doi:10.1002/hbm.26109 · Cited by 18
Mutual gain adaptive network for segmenting brain stroke lesions
Huang, B., Tan, G., Dou, H., Cui, Z., Song, Y., & Zhou, T. (2022) · Applied Soft Computing · doi:10.1016/j.asoc.2022.109568 · Cited by 14
Seemann, F., Javed, A., Chae, R., Ramasawmy, R., O’Brien, K., Baute, S., Xue, H., Lederman, R., & Campbell-Washburn, A. (2022) · Journal of Cardiovascular Magnetic Resonance · doi:10.1186/s12968-022-00862-4 · Cited by 14
Cros, S., Bouttier, H., Nguyen-Tan, P., Vorontsov, E., & Kadoury, S. (2022) · Journal of Applied Clinical Medical Physics · doi:10.1002/acm2.13655 · Cited by 14
“Several alternatives have allowed to improve the U-net training capabilities with the development of residual networks[18,19] and dense CNNs,[20,21] both aiming for efficient deep networks that would achieve higher performance.”
BackgroundGapLoss: A Loss Function for Semantic Segmentation of Roads in Remote Sensing Images
Yuan, W. M., & Xu, W. (2022) · Remote Sensing · doi:10.3390/rs14102422 · Cited by 13
“Gao et al. [27] proposed a multiple-feature pyramid network, which was similar to the RSRCNN. Zhang et al. [28] proposed a deep residual UNet to perform road extraction.”
ResultZuo, B., Lee, F.-F., & Chen, Q. (2022) · Medical and Biological Engineering and Computing · doi:10.1007/s11517-022-02581-5 · Cited by 14
Habijan, M., Galić, I., Romić, K., & Leventić, H. (2022) · Applied Sciences · doi:10.3390/app12063024 · Cited by 14
“However, this has been shown to hinder the training process and ultimately contribute to accuracy degradation [32].”
BackgroundMulti-Path U-Net Architecture for Cell and Colony-Forming Unit Image Segmentation
Jumutc, V., Bļizņuks, D., & Lihachev, A. (2022) · Italian National Conference on Sensors · doi:10.3390/s22030990 · Cited by 14
“This “plain” approach does not make use of any residual or dense connections [16], it builds upon improving a standard U-Net layer with instance normalization [17], leaky ReLU activations [18], and replicated convolutional layers.”
BackgroundGao, L.-P., Shi, W.-Z., Zhu, J., Shao, P., Sun, S., Li, Y., Wang, F., & Gao, F. (2021) · Remote Sensing · doi:10.3390/rs13234766 · Cited by 14
“proposed the residual U-Net, which combines the advantages of U-Net with residual blocks [14].”
BackgroundLiang, D., Wang, L., Han, D., Qiu, J., Yin, X., Yang, Z., Xing, J., Dong, J., & Ma, Z. (2021) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2021.102894 · Cited by 14
CLC+ Backbone: Set the Scene in Copernicus for the Coming Decade
Probeck, M., Ruíz, I., Ramminger, G., Fourie, C., Maier, P., Ickerott, M., Storch, C., Homolka, A., Muller, S. J., Tiwari, H., et al. (2021) · 2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS · doi:10.1109/igarss47720.2021.9553252 · Cited by 14
“In order to recognise roads on the satellite images, a semantic segmentation is performed using a Convolutional Neural Network (CNN) and a U-Net architecture [3], together with an auto-encoder for improved noise reduction of the segmentation.”
MethodSemi-Supervised Segmentation of Multi-vendor and Multi-center Cardiac MRI
Bolhassani, M., & Oksuz, I. (2021) · Signal Processing and Communications Applications Conference · doi:10.1109/siu53274.2021.9477818 · Cited by 14
“introduced residual U-net architecture for road area extraction [6].”
BackgroundHuang, H., Chen, H., Xu, H., Chen, Y., Yu, Q., Cai, Y., & Zhang, Q. (2021) · Journal of Medical and Biological Engineering · doi:10.1007/s40846-020-00585-w · Cited by 15
Local Adaptive U-net for Medical Image Segmentation
Liu, N., Liu, L.-L., & Wang, J. (2020) · IEEE International Conference on Bioinformatics and Biomedicine · doi:10.1109/bibm49941.2020.9313515 · Cited by 14
“[12] proposed a Bidirectional ConvLSTM U-Net with densely connected convolutions for medical image segmentation.”
Overview of Image Semantic Segmentation Technology
Wang, L., Chen, X., Hu, L., & Li, H. (2020) · IEEE Joint International Information Technology and Artificial Intelligence Conference · doi:10.1109/itaic49862.2020.9338770 · Cited by 14
“In order to extract roads from aerial images, Zhang et al. [25] proposed a new network structure combining the characteristics of the residual network and the structure of U-Net, which achieved a good segmentation of roads.”
BackgroundJiang, W., Lin, F., Zhang, J., Zhan, T., Cao, P., & Wang, S. (2020) · Interdisciplinary Sciences Computational Life Sciences · doi:10.1007/s12539-020-00398-0 · Cited by 13
LONG-SHORT SKIP CONNECTIONS IN DEEP NEURAL NETWORKS FOR DSM REFINEMENT
Bittner, K., Liebel, L., Körner, M., & Reinartz, P. (2020) · The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences · doi:10.5194/isprs-archives-xliii-b2-2020-383-2020 · Cited by 14
“(Drozdzal et al., 2016; Zhang et al., 2018) have already explored it for different semantic image segmentation tasks.”
BackgroundRoad Network Extraction from Satellite Images Using CNN Based Segmentation and Tracing
Yao, W., Zhang, K., & Ji, S. (2019) · IEEE International Geoscience and Remote Sensing Symposium (IGARSS) · doi:10.1109/igarss.2019.8898565 · Cited by 13
“Zhang et al. [4] combined residual learning and U-net model to achieve better results.”
City-scale Road Extraction from Satellite ImageryPreprint
Etten, A. V. (2019) · arXiv.org · doi:10.48550/arxiv.1904.09901 · Cited by 14
“Extracting road pixels in small image chips from aerial imagery has a rich history (e.g. [5], [6], [7]).”
BackgroundRoad Topology Refinement via a Multi-Conditional Generative Adversarial Network
Zhang, Y., Li, X., & Zhang, Q. (2019) · Italian National Conference on Sensors · doi:10.3390/s19051162 · Cited by 14
“With the development of the convolutional neural network (CNN) [39], recent learning-based road extraction approaches either develop based on CNNs or the derived networks, such as FCN [40], ResNet [41], etc.”
MethodMulti-Scale Contourlet Knowledge Guide Learning Segmentation
Liu, M., Jiao, L., Liu, X., Li, L., Liu, F., Yang, S., Wang, S., & Hou, B. (2023) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2023.3326949 · Cited by 16
P., L., Ullah, M., Vats, A., Cheikh, F. A., G., S., & Nair, M. S. (2024) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2024.106210 · Cited by 14
Xu, Y., Shi, Z., Xie, X., Chen, Z., & Xie, Z. (2024) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2024.3383596 · Cited by 18
“Zhang et al. [17] applied residual connectivity to U-Net to learn to get more fine-grained features for road segmentation.”
BackgroundPreedanan, W., Suzuki, K., Kondo, T., Kobayashi, M., Tanaka, H., Ishioka, J., Matsuoka, Y., Fujii, Y., & Kumazawa, I. (2023) · IEEE Access · doi:10.1109/access.2023.3257049 · Cited by 14
“The U-Net variants that we experimented included U-Net, ResUnet [32], Unet ++ [33], Attention Unet [34], MultiResUnet [35], and TransUnet models [36].”
MethodTERNformer: Topology-Enhanced Road Network Extraction by Exploring Local Connectivity
Wang, B., Liu, Q., Hu, Z., Wang, W., & Wang, Y. (2023) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2023.3296717 · Cited by 15
“Most of the segmentation methods [20], [21], [22], [23], [24], [25], [26] are applicable for road network extraction.”
MethodSelf-citationMultiscale Residual Convolution Neural Network and Sector Descriptor-Based Road Detection Method
Dai, J.-G., Du, Y., Zhu, T., Wang, Y., & Gao, L. (2019) · IEEE Access · doi:10.1109/access.2019.2956725 · Cited by 14
“[25] introduced residual units into the U-Net network, which reduced the computational complexity and improved the segmentation”
BackgroundSelf-citationKılıç, Ş. (2025) · PLoS ONE · doi:10.1371/journal.pone.0331896 · Cited by 13
“ResUNet [17] incorporated residual blocks to facilitate gradient flow in deeper networks, while U-Net++ [7] proposed nested and dense skip connections to reduce the semantic gap between encoder and decoder features.”
Dual-domain guided vision Mamba network for medical image segmentation
Liu, S., Zhao, M., & Lin, Y. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.128512 · Cited by 8
WHU-RuR+: A benchmark dataset for global high-resolution rural road extraction
Wang, N.-J., Wang, X.-Y., Pan, Y., Yao, W., & Zhong, Y.-F. (2025) · International Journal of Applied Earth Observation and Geoinformation · doi:10.1016/j.jag.2025.104518 · Cited by 13
Lung Segmentation with Lightweight Convolutional Attention Residual U-Net
Jannat, M., Birahim, S. A., Hasan, M. A., Roy, T., Sultana, L., Sarker, H., Fairuz, S., & Abdallah, H. A. (2025) · Diagnostics · doi:10.3390/diagnostics15070854 · Cited by 13
“Road image extraction using ResUNet [7], a U-Net architectural variation, has produced state-of-the-art (SOTA) results.”
Full-scale representation guided network for retinal vessel segmentation
Seo, S., Yoo, S., & Yoon, H. (2025) · BMC Medical Imaging · doi:10.1186/s12880-025-02021-4 · Cited by 13
“To select the optimized model during the training step, we used the highest F1 score [44], with an early stop of 400 epochs.”
Multi-UNet: An effective Multi-U convolutional networks for semantic segmentation
Zhao, Q., Cao, J.-J., Ge, J., Zhu, Q., Chen, X., & Liu, W.-X. (2024) · Knowledge-Based Systems · doi:10.1016/j.knosys.2024.112854 · Cited by 13
Paul, A., & Mallidi, S. (2024) · Photoacoustics · doi:10.1016/j.pacs.2024.100674 · Cited by 11
CRNet: Cascaded Refinement Network for polyp segmentation
Wen, X.-L., Zhang, A., Lin, C., & Pang, X. (2024) · Journal of King Saud University: Computer and Information Sciences · doi:10.1016/j.jksuci.2024.102250 · Cited by 13
Non-Serial Quantization-Aware Deep Optics for Snapshot Hyperspectral Imaging
Wang, L., Li, L.-G., Song, W.-T., Zhang, L., Xiong, Z., & Huang, H. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2024.3425512 · Cited by 13
“Concretely, we adopt the Res-UNet [68] as the data-driven module.”
MethodLi, G.-J., & Qi, M. (2024) · Expert systems with applications · doi:10.1016/j.eswa.2024.124284 · Cited by 13
Bougourzi, F., Dornaika, F., Taleb-Ahmed, A., & Hoang, V. T. (2024) · International Conference on Pattern Recognition · doi:10.48550/arxiv.2404.18199 · Cited by 13
“Since then, numerous variants such as Attention U-Net (Att-UNet) [12], U-Net++ [14], and ResU-Net [15] have emerged, each aiming to enhance segmentation performance.”
BackgroundRoad Extraction Method of Remote Sensing Image Based on Deformable Attention Transformer
Zhao, L., Zhang, J.-N., Meng, X.-J., Zhou, W., Zhang, Z.-S., & Peng, C.-L. (2024) · Symmetry · doi:10.3390/sym16040468 · Cited by 13
Self-citationAGF-Net: adaptive global feature fusion network for road extraction from remote-sensing images
Zhang, Y., Zhang, L., Wang, Y., & Xu, W. (2024) · Complex & Intelligent Systems · doi:10.1007/s40747-024-01364-9 · Cited by 13
Self-citationUz, M., Akyılmaz, O., Shum, C., Atman, K. G., Olgun, S., & Güneş, Ö. (2024) · Scientific Data · doi:10.1038/s41597-023-02887-5 · Cited by 13
“For this reason, CNNs have been widely used for problems such as filling the data gap in remote sensing 14 , land surface temperature reconstruction 15 , etc.”
Qu, G.-J., Wu, Y., Lv, Z.-H., Zhao, D., Lu, Y., Zhou, K.-F., Tang, J., Zhang, Q., & Zhang, A.-J. (2024) · Italian National Conference on Sensors · doi:10.3390/s24020531 · Cited by 13
“This approach typically transforms the road extraction problem into a semantic segmentation problem in computer vision and automatically acquires road in-Sensors formation [23,24].”
BackgroundWei, C., Wei, H., Crivellari, A., Liu, T., Wan, Y., Chen, W., & Lu, Y. (2023) · International Journal of Remote Sensing · doi:10.1080/01431161.2023.2288948 · Cited by 13
“ResUnet refers to the Deep Residual Unet developed by Zhengxin Zhang et al. for semantic segmentation (Zhang, Liu, and Wang 2018).”
MethodLi, Y., Zhang, L., Yu, H., Wang, J., Wang, S., Liu, J., & Zheng, Q. (2023) · European Radiology · doi:10.1007/s00330-023-10367-y · Cited by 12
“…strategy divided the CXR into six components, consisting of the left lung, right lung, mediastinum, diaphragm, ext-left lung, and ext-right lung, and the RA-UNet [15] adopted in our study was compared with other alternative deep learning models of TransUNet [18], ResUNet [19], and DC-UNet [20].”
InfluentialHybrid Approach to Colony-Forming Unit Counting Problem Using Multi-Loss U-Net Reformulation
Jumutc, V., Suponenkovs, A., Bondarenko, A., Bļizņuks, D., & Lihachev, A. (2023) · Italian National Conference on Sensors · doi:10.3390/s23198337 · Cited by 13
“The results are aggregated across single-loss, hybrid (ours), and multi-loss (ours) formulations for the U-Net++ [30], Plain U-Net [7], Residual U-Net [31], Dense U-Net [32], and MultiRes U-Net [33] architectures.”
BackgroundKey information-guided networks for medical image segmentation in medical systems
Liu, C., Cheng, Y.-S., & Tamura, S. (2023) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.121851 · Cited by 11
Zhao, L., Ye, L., Zhang, M., Jiang, H.-W., Yang, Z., & Yang, M. (2023) · Remote Sensing · doi:10.3390/rs15153741 · Cited by 13
P-TransUNet: an improved parallel network for medical image segmentation
Chong, Y., Xie, N., Liu, X., & Pan, S. (2023) · BMC Bioinformatics · doi:10.1186/s12859-023-05409-7 · Cited by 13
Development of lung segmentation method in x-ray images of children based on TransResUNet
Chen, L.-D., Yu, Z., Huang, J., Shu, L., Kuosmanen, P., Shen, C., Ma, X.-H., Li, J., Sun, C.-S., Li, Z.-M., et al. (2023) · Frontiers in Radiology · doi:10.3389/fradi.2023.1190745 · Cited by 13
“The TransUNet model showed satisfying performances in many medical image segmentation tasks (31, 32).”
MethodZhu, X.-L., Zhang, S.-M., Hao, H., & Zhao, Y. (2023) · Frontiers in Cardiovascular Medicine · doi:10.3389/fcvm.2023.1153053 · Cited by 13
“From left to right: the original image, the vessel segmentation results obtained by U-Net, ResU-Net, CS-Net, SwinU-Net, TransU-Net, and the proposed method, respectively.”
MethodInfluentialOne step surgical scene restoration for robot assisted minimally invasive surgery
Ali, S., Jonmohamadi, Y., Fontanarosa, D., Crawford, R., & Pandey, A. (2023) · Scientific Reports · doi:10.1038/s41598-022-26647-4 · Cited by 13
Attention Res-UNet: Attention Residual UNet With Focal Tversky Loss for Skin Lesion Segmentation
Rehman, A., Butt, M., & Zaman, M. (2023) · International Journal of Decision Support System Technology · doi:10.4018/ijdsst.315756 · Cited by 13
“Zhang et al (Zhang et al., 2018) designed a deeper residual U-Net network called ResUNet that combines the best features of both the deep residual learning framework and UNet (Ronneberger et al.”
BackgroundMethodInfluentialDetecting Hydronephrosis Through Ultrasound Images Using State-of-the-Art Deep Learning Models
Lien, W., Chang, Y.-C., Chou, H., Lin, L., Liu, Y.-P., Liu, L., Chan, Y.-T., & Kuan, F.-S. (2022) · Ultrasound in Medicine & Biology · doi:10.1016/j.ultrasmedbio.2022.10.001 · Cited by 18
Transfer Learning with Pretrained Remote Sensing Transformers
Fuller, A., Millard, K., & Green, J. R. (2022) · arXiv.org · doi:10.48550/arxiv.2209.14969 · Cited by 13
“Finally, to put SatViT-V2’s performance in context, we also fine-tune SatViT-V1 [18], four convolutional neural networks trained from scratch (UNet [63], UNet++ [64], ResUNet [65], and ResUNet++ [66]), and SatViT-V2 trained from scratch.”
MethodVideo-TransUNet: temporally blended vision transformer for CT VFSS instance segmentation
Zeng, C., Yang, X.-Y., Mirmehdi, M., Gambaruto, A., & Burghardt, T. (2022) · International Conference on Machine Vision · doi:10.1117/12.2679409 · Cited by 13
“However, as shown in rows 3 and 4, ResUNet and AttUNet also produce some noise compared to the ground truth resulting in lower sensitivity (see Tab.”
BackgroundECA-UNet for coronary artery segmentation and three-dimensional reconstruction
Duan, X.-J., Sun, Y., & Wang, J.-M. (2022) · Signal, Image and Video Processing · doi:10.1007/s11760-022-02288-y · Cited by 13
“The encoder structure in [15] uses a single BasicBlock for feature extraction.”
MethodEnd-to-end cell recognition by point annotation
Shui, Z.-Y., Zhang, S.-C., Zhu, C.-L., Wang, B.-C., Chen, P.-Y., Zheng, S.-Y., & Yang, L. (2022) · International Conference on Medical Image Computing and Computer-Assisted Intervention · doi:10.48550/arxiv.2207.00176 · Cited by 13
MSPNet: Multi-Scale Strip Pooling Network for Road Extraction from Remote Sensing Images
Qu, S., Zhou, H., Zhang, B., & Liang, S. (2022) · Applied Sciences · doi:10.3390/app12084068 · Cited by 14
“The D-LinkNet with additional dilated convolution layers outperforms ResUNet, obtaining an improvement of 1.5% on the IoU score and 0.67% on the F1-score.”
MethodInfluentialReal-time guidewire tracking and segmentation in intraoperative x-ray
Zhang, B., Bui, M., Wang, C., Bourier, F., Schunkert, H., & Navab, N. (2022) · Medical Imaging · doi:10.1117/12.2611097 · Cited by 13
“Method U-Net [13] R2UNet [14] ResUnet [15] FARNet [8] CSNet [11] HessianNet w/o Attention HessianNet w/o Enhance HessianNet”
MethodAutomatic Segmentation of Head and Neck Tumor: How Powerful Transformers Are?
Sobirov, I., Nazarov, O., Alasmawi, H., & Yaqub, M. (2022) · International Conference on Medical Imaging with Deep Learning · doi:10.48550/arxiv.2201.06251 · Cited by 13
“, 2016), residual blocks (Zhang et al., 2017), multi-scale patches (Jiayun et al.”
BackgroundOhno-Matsui, K., Takahashi, H., Mao, Z., & Nakao, N. (2021) · British Journal of Ophthalmology · doi:10.1136/bjophthalmol-2021-320131 · Cited by 13
Evolutionary NAS for aerial image segmentation with gene expression programming of cellular encoding
Broni-Bediako, C., Murata, Y., Mormille, L. H., & Atsumi, M. (2021) · Neural Computing and Applications · doi:10.1007/s00521-021-06564-9 · Cited by 15
Dual-Path Morph-UNet for Road and Building Segmentation From Satellite Images
Dey, M., Chaudhuri, U., Banerjee, B., & Bhattacharya, A. (2021) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2021.3106772 · Cited by 13
“We also used LinkNet [18], Residual UNet [10], and Joint-Net [11], of which the last two have been used in RS.”
BackgroundMethodBibliometric and visualized analysis of deep learning in remote sensing
Bai, Y., Sun, X., Ji, Y., Huang, J., Fu, W., & Shi, H. (2021) · International Journal of Remote Sensing · doi:10.1080/01431161.2021.1949069 · Cited by 14
“…methods based on CNNs have been proposed to extract spatial (Liu and Shi et al. 2020; Kestur et al. 2018; Liao and Wang 2020; Zhang, Liu, and Wang 2018) or spectral-spatial features (Chen and Jiang et al. 2016 Xu and Zhang et al. 2020b Zhong and Jonathan et al. 2019 Kong, Wang, and Cheng…”
BackgroundMethodRoad Extraction from High Resolution Remote Sensing Images Based on Vector Field Learning
Liang, P., Shi, W.-Z., Ding, Y., Liu, Z., & Shang, H. (2021) · Italian National Conference on Sensors · doi:10.3390/s21093152 · Cited by 13
Holistic Grid Fusion Based Stop Line Estimation
Xu, R., Tafazzoli, F., Zhang, L., Rehfeld, T., Krehl, G., & Seal, A. (2020) · International Conference on Pattern Recognition · doi:10.1109/icpr48806.2021.9413070 · Cited by 13
“We have used UNet [20] as the backbone for the joint learning because of its capability to retain both low level details and high level semantic information [23].”
MethodExtracting road maps from high-resolution satellite imagery using refined DSE-LinkNet
Das, P., & Chand, S. (2020) · Connection Science · doi:10.1080/09540091.2020.1807466 · Cited by 12
“In literature (Buslaev et al., 2018; Yuan et al., 2019; Zhang et al., 2018; Zhou et al.,2018), the pre-trained weights of a single model are used in the encoder part of the standard architectures developed for road extraction from satellite imagery.”
MethodInfluentialLee, E.-J., Liao, W.-Y., Mu, D., Wang, W., & Chen, P. (2020) · doi:10.1785/0220190323 · Cited by 13
Segmentation of Cell Images Based on Improved Deep Learning Approach
Huang, C., Ding, H., & Liu, C. (2020) · IEEE Access · doi:10.1109/access.2020.3001571 · Cited by 23
“In this paper, inspired by the deep residual learning [39], [40], we utilize residual paths corresponding to different numbers of mixed convolution block II.”
MethodCoronary Wall Segmentation in CCTA Scans Via a Hybrid Net with Contours Regularization
Huang, K.-K., Tejero-de-Pablos, A., Yamane, H., Kurose, Y., Iho, J., Tokunaga, Y., Horie, M., Nishizawa, K., Hayashi, Y., Koyama, Y., et al. (2020) · IEEE International Symposium on Biomedical Imaging · doi:10.1109/isbi45749.2020.9098478 · Cited by 13
“[6] Zhengxin Zhang, Qingjie Liu, and Yunhong Wang, “Road extraction by deep residual U-Net,” IEEE Geoscience and Remote Sensing Letters, vol. 15, pp. 749– 753, 2018.”
BackgroundMethodInfluentialDeep Fusion of Local and Non-Local Features for Precision Landslide RecognitionPreprint
Zhu, Q., Chen, L., Hu, H., Xu, B.-Z., Zhang, Y.-T., & Li, H.-F. (2020) · arXiv.org · doi:10.48550/arxiv.2002.08547 · Cited by 13
Wang, G., Stappen, G. V., & Baets, B. D. (2020) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2019.105102 · Cited by 13
A Comparative Study of U-Nets with Various Convolution Components for Building Extraction
Zhang, W., Tang, P., Zhao, L.-J., & Huang, Q. (2019) · Joint Urban Remote Sensing Event · doi:10.1109/jurse.2019.8809055 · Cited by 13
“The method that combines the residual learning and U-Net was proposed to extract road and outperforms other compared methods [7].”
MethodA Two-Step Deep Convolution Neural Network for Road Extraction from Aerial Images
Singh, P., & Dash, R. (2019) · SPIN · doi:10.1109/spin.2019.8711639 · Cited by 13
“The Unet has proved to produce better results for road segmentation problem [12] because the skip connections provide a way to include the low-level features in the corresponding high-level features [1].”
BackgroundInfluential
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
