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 401–500 of 1,001
Zhang, Q., Sampani, K., Xu, M., Cai, S., Deng, Y., Li, H., Sun, J. K., & Karniadakis, G. E. (2022) · Translational Vision Science & Technology · doi:10.1167/tvst.11.8.7 · Cited by 31
“In addition to nnUNet, as shown in Fig.4 in SI, we specifically compare the performance of AOSLO-net with other popular CNN-based models, i.e., Deformable UNet [36], ResUNet [42, 43] and Deformable ResUNet [42–44], using the normal mask dataset.”
MethodZhang, H., Wang, M.-C., Wang, F.-Y., Yang, G., Zhang, Y., Jia, J., & Wang, S. (2021) · Remote Sensing · doi:10.3390/rs13030440 · Cited by 38
“For example, the authors in [47] used a region-based FCN (R-FCN), which was combined with the ResNet-101 network to try to determine the center pixel of the object before segmenting the image.”
BackgroundMethodDeep Learning: A Breakthrough in Medical Imaging
Ahmad, H. M., Khan, M. J., Yousaf, A., Ghuffar, S., & Khurshid, K. (2019) · Current Medical Imaging Formerly Current Medical Imaging Reviews · doi:10.2174/1573405615666191219100824 · Cited by 46
Multiscale Road Extraction in Remote Sensing Images
Wulamu, A., Shi, Z., Zhang, D., & He, Z. (2019) · Computational Intelligence and Neuroscience · doi:10.1155/2019/2373798 · Cited by 44
“,e use of deep learning technology for remote sensing image interpretation is mainly divided into two categories, semantic segmentation [23] and edge detection [24].”
Automated Pixel-Level Surface Crack Detection Using U-Net
Ji, J., Wu, L.-J., Chen, Z.-C., Yu, J., Lin, P., & Cheng, S. (2018) · International Workshop on Multi-disciplinary Trends in Artificial Intelligence · doi:10.1007/978-3-030-03014-8_6 · Cited by 38
seUNet-Trans: A Simple Yet Effective UNet-Transformer Model for Medical Image Segmentation
Pham, T.-H., Li, X., & Nguyen, K. (2024) · IEEE Access · doi:10.1109/access.2024.3451304 · Cited by 51
“SFA [43] 0.700 0.607 - - ResUNet-mod [44] 0.779 0.455 0.668 0.888 UNet++ [16] 0.794 0.729 - - U-Net [5] 0.872 0.804 0.868 0.917 PraNet [20] 0.899 0.849 - - DoubleU-Net [22] 0.924 0.861 0.846 0.959 FANet [23] 0.936 0.894 0.934 0.940 DS-TransUNet-L [28] 0 outperforms most of the other models but also…”
InfluentialThe ability of Segmenting Anything Model (SAM) to segment ultrasound images
Chen, F., Chen, L., Han, H., Zhang, S., Zhang, D., & Liao, H. (2023) · BioScience Trends · doi:10.5582/bst.2023.01128 · Cited by 38
“In other words, SAM is not as accurate as dataset specific deep-learning algorithms (19-27) for medical US segmentation tasks.”
BackgroundChen, F., Han, H.-J., Wan, P., Liao, H., Liu, C.-R., & Zhang, D. (2023) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2023.3262842 · Cited by 37
“1)Experimental findings comparing input data in 2D, 3D, and 2D+T for the Unet, ResUnet, and Swinunet models revealed that the latter three models performed best when fed 2D+T data for segmentation purposes in real-time CEUS.”
MethodAzam, M. A., Sampieri, C., Ioppi, A., Benzi, P., Giordano, G., Vecchi, M. D., Campagnari, V., Li, S., Guastini, L., Paderno, A., et al. (2022) · Frontiers in Oncology · doi:10.3389/fonc.2022.900451 · Cited by 41
“ResUNet (36) is a segmentation model based on the UNet architecture that implements residual units instead of plain neural units, in order to obtain good performance with fewer parameters.”
MethodLiu, J., Yuan, C., Sun, X., Sun, L., Dong, H., & Peng, Y. (2021) · Physical and Engineering Sciences in Medicine · doi:10.1007/s13246-021-01032-z · Cited by 37
Biomedical Image Segmentation: A Survey
Alzahrani, Y., & Boufama, B. (2021) · SN Computer Science · doi:10.1007/s42979-021-00704-7 · Cited by 47
“However, encoder–decoder architectures[101] and their variants, like ResUnet [149], SegNet [17], Unet++ [151], R2U-Net [6], and Residual Dilated UNet (RD-UNet)[43], are more suitable for pixel-level segmentation.”
MethodPancreas segmentation using a dual-input v-mesh network
Wang, Y., Gong, G., Kong, D., Li, Q., Dai, J.-P., Zhang, H.-Y., Qu, J., Liu, X.-Y., & Xue, J. (2021) · Medical Image Anal. · doi:10.1016/j.media.2021.101958 · Cited by 37
Self-citationRetinal blood vessel segmentation based on Densely Connected U-Net.
Cheng, Y., Ma, M., Zhang, L., Jin, C., Ma, L., & Zhou, Y. (2020) · Mathematical biosciences and engineering : MBE · doi:10.3934/mbe.2020175 · Cited by 37
“Therefore, we introduce the dense block [46] based on Residual U-Net [47], by connecting the features learned from different layers, implementing feature reuse, reducing redundancy in the network, leveraging the potential of the network and yielding condensed models that are easy to train and…”
CFU-Net: A Coarse–Fine U-Net With Multilevel Attention for Medical Image Segmentation
Yin, H., & Shao, Y. (2023) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2023.3293887 · Cited by 37
“3) Baselines: To demonstrate the efficiency of proposed CFU-Net, we compare it with six SOTA U-Net-based segmentation methods, including U-Net [24], U-Net ++ [41], Attention UNet (A-UNet) [35], Residual U-Net (ResU-Net) [30], ResU-Net ++ [53], and UNeXt [52].”
MethodModified UNet Model for Brain Stroke Lesion Segmentation on Computed Tomography Images
Omarov, B. S., Tursynova, A., Postolache, O. A., Gamry, K., Batyrbekov, A., Aldeshov, S., Azhibekova, Z., Nurtas, M., Aliyeva, A., & Shiyapov, K. (2022) · Computers, materials & continua/Computers, materials & continua (Print) · doi:10.32604/cmc.2022.020998 · Cited by 43
Using Adversarial Network for Multiple Change Detection in Bitemporal Remote Sensing Imagery
Zhao, W., Chen, X., Ge, X.-R., & Chen, J.-G. (2022) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2020.3035780 · Cited by 37
“The U-Net model combines encoding–decoding structure with the jumping network; it increases the robustness in spatial feature extraction through multilayer upsampling and downsampling processes [10].”
MethodZhang, X., Li, Q., Li, W., Guo, Y.-X., Zhang, J.-Y., Guo, C.-B., Chang, K.-I., & Lovell, N. H. (2024) · IEEE journal of biomedical and health informatics · doi:10.1109/jbhi.2024.3350245 · Cited by 36
CT-Net: Asymmetric compound branch Transformer for medical image segmentation
Zhang, N., Yu, L., Zhang, D.-Z., Wu, W., Tian, S.-W., Kang, X., & Li, M. (2023) · Neural Networks · doi:10.1016/j.neunet.2023.11.034 · Cited by 36
Chen, F., Chen, L.-Y., Kong, W.-T., Zhang, W.-J., Zheng, P.-F., Sun, L., Zhang, D., & Liao, H. (2023) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2023.3309249 · Cited by 36
“…on semi-supervised tasks, but also compares favorably with fully supervised frameworks, we choose seven remarkable full-supervised methods for comparison, including: 1) U-Net [13]; 2) Attention U-Net [62]; 3) ResU-Net [63]; 4) Deeplabv3 [64]; 5) U-Net ++ [65]; 6) TransUNet [66]; 7) BUSSeg [67].”
Yang, X., Xu, L., Yu, S., Xia, Q., Li, H., & Zhang, S.-T. (2023) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2024.3435714 · Cited by 36
A Few-Shot Attention Recurrent Residual U-Net for Crack Segmentation
Katsamenis, I., Protopapadakis, E., Bakalos, N., Doulamis, A., Doulamis, N., & Voulodimos, A. (2023) · International Symposium on Visual Computing · doi:10.48550/arxiv.2303.01582 · Cited by 36
“To enhance the performance of the original U-Net, numerous elements have been introduced, such as residual convolutional units [16, 17] and attention gates instead of the typical skip connection [18, 19].”
MethodA CT-based deep learning system for automatic assessment of aortic root morphology for TAVI planning
Saitta, S., Sturla, F., Gorla, R., Oliva, O., Votta, E., Bedogni, F., & Redaelli, A. (2023) · Comput. Biol. Medicine · doi:10.1016/j.compbiomed.2023.107147 · Cited by 36
“Both models were based on a fully convolutional 3D U-Net architecture proposed in [19], with encoding and decoding branches of 5 resolution levels each, defined using residual units as introduced by [20].”
MethodIB-TransUNet: Combining Information Bottleneck and Transformer for Medical Image Segmentation
Li, G.-J., Jin, D., Yu, Q., & Qi, M. (2023) · Journal of King Saud University: Computer and Information Sciences · doi:10.1016/j.jksuci.2023.02.012 · Cited by 36
Width Attention based Convolutional Neural Network for Retinal Vessel Segmentation
Alvarado-Carrillo, D. E., & Dalmau-Cedeño, O. S. (2022) · Expert systems with applications · doi:10.1016/j.eswa.2022.118313 · Cited by 36
Energy-Based Legged Robots Terrain Traversability Modeling via Deep Inverse Reinforcement Learning
Gan, L., Grizzle, J., Eustice, R. M., & Ghaffari, M. (2022) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2022.3188100 · Cited by 36
“We compare three different architectures used in literatures: ResNet [19], UNet [36], and ResUNet [30].”
MethodA deep learning segmentation-classification pipeline for X-ray-based COVID-19 diagnosis
Hertel, R., & Benlamri, R. (2022) · Biomedical Engineering Advances · doi:10.1016/j.bea.2022.100041 · Cited by 36
A Stacking Ensemble Deep Learning Model for Building Extraction from Remote Sensing Images
Cao, D.-G., Xing, H., Wong, M., Kwan, M.-P., Xing, H.-Q., & Meng, Y. (2021) · Remote Sensing · doi:10.3390/rs13193898 · Cited by 36
“Yi et al. [20] compared the building extraction performance of the proposed DeepResUNet with other semantic segmentation architectures: FCN-8s, SegNet, DeconvNet [21], U-Net, ResUNet [22], and DeepUNet [23].”
MethodZhao, F., Xiong, L., Wang, C., Wang, H.-R., Wei, H., & Tang, G.-A. (2021) · Trans. GIS · doi:10.1111/tgis.12824 · Cited by 36
Zheng, G., Jiang, Y., Shi, C., Miao, H., Yu, X.-L., Wang, Y.-Y., Chen, S.-S., Lin, Z., Wang, W., Lu, F., et al. (2020) · Journal of Innovative Optical Health Sciences · doi:10.1142/s1793545821400022 · Cited by 36
Self-citationD-Resunet: Resunet and Dilated Convolution for High Resolution Satellite Imagery Road Extraction
Liu, Z.-Q., Feng, R., Wang, L.-Z., Zhong, Y.-F., & Cao, L.-Q. (2019) · IEEE International Geoscience and Remote Sensing Symposium · doi:10.1109/igarss.2019.8898392 · Cited by 36
“[1] employed a U-Net with residual connections to extract road areas from one image through single forward pass.”
BackgroundMethodInfluentialWavelet-GAN: A GPR Noise and Clutter Removal Method Based on Small Real Datasets
Ge, J., Sun, H.-F., Shao, W., Liu, D., Liu, H., Zhao, F., Tian, B., & Liu, S.-B. (2024) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2024.3410277 · Cited by 36
“The deep-learning based declutter meth-ods for comparison include UNet [46], Trans-UNet [47], and Refine-Net [48].”
BackgroundMethodSafavi, F., & Rahnemoonfar, M. (2022) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2022.3219724 · Cited by 50
“Deep residual UNet [102] integrates the robustness of residual learning and”
BackgroundZhou, G.-D., Xu, J., Chen, W.-T., Li, X., Li, J., & Wang, L. (2023) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2023.3241331 · Cited by 36
“[69] combined the strengths of residual learning and U-Net to develop a model known as ResUNet.”
BackgroundXiong, L., Yi, C., Xiong, Q., & Jiang, S.-F. (2024) · BMC Medical Imaging · doi:10.1186/s12880-024-01194-8 · Cited by 35
“Zhang [6] replaced each sub-block of U-Net with a staggered block, and then applied it to retinal segmentation.”
MethodMeng, S.-W., Fu, Q., Tao, J.-P., Liang, L.-H., & Xu, J.-C. (2023) · Geoenergy Science and Engineering · doi:10.1016/j.geoen.2023.212467 · Cited by 35
TranSEFusionNet: Deep fusion network for colorectal polyp segmentation
Zhang, Y.-Y., Liu, L., Han, Z., Meng, F.-Y., Zhang, Y.-L., & Zhao, Y.-W. (2023) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2023.105133 · Cited by 35
DHUnet: Dual-branch hierarchical global–local fusion network for whole slide image segmentation
Lian, W., Pan, L., Wang, H., Liu, M., Feng, Z., Rong, P., Chen, Z., & Peng, S. (2023) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2023.104976 · Cited by 41
Kocur, V., Hegrová, V., Patočka, M., Neuman, J., & Herout, A. (2022) · Ultramicroscopy · doi:10.1016/j.ultramic.2022.113666 · Cited by 37
REU-Net: Region-enhanced nuclei segmentation network
Qin, J., He, Y., Zhou, Y., Zhao, J., & Ding, B. (2022) · Comput. Biol. Medicine · doi:10.1016/j.compbiomed.2022.105546 · Cited by 35
Scale-adaptive super-feature based MetricUNet for brain tumor segmentation
Liu, Y.-J., Du, J., Vong, C.-M., Yue, G., Yu, J., Wang, Y., Lei, B.-Y., & Wang, T.-F. (2022) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2021.103442 · Cited by 35
Self-citationStanislawski, L., Shavers, E., Wang, S.-W., Jiang, Z., Usery, E. L., Moak, E., Duffy, A., & Schott, J. (2021) · Remote Sensing · doi:10.3390/rs13122368 · Cited by 35
“The U-net deep learning model was originally applied to segmentation of electron microscopic images to track cells for biomedical research [27] but has since been applied to extraction of geospatial features, such as roads [28] and waterbodies [29].”
MethodAn improved framework for polyp image segmentation based on SegNet architecture
Afify, H., Mohammed, K. K., & Hassanien, A. (2021) · International journal of imaging systems and technology (Print) · doi:10.1002/ima.22568 · Cited by 35
“However, this Kvasir database has restrictions due to its use for classification only and missing ground truth.(14) Recently, the Kvasir-SEG dataset(20) was generated to support the polyp dataset with segmentation masks.”
MethodZhang, M., Jing, W., Lin, J., Fang, N., Wei, W., Woźniak, M., & Damaševičius, R. (2020) · Italian National Conference on Sensors · doi:10.3390/s20185292 · Cited by 35
“U-net employs a totally different feature fusion method where features are spliced together in channel dimension to form a thicker feature [19,20].”
MethodLi, J., He, J., Li, W., Chen, J., & Yu, J.-H. (2024) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2024.3380914 · Cited by 35
“Zhang et al. [11] proposed a Residual U-Net, which leverages the advantages of U-Net and residual blocks to simplify the training process in the segmentation network.”
BackgroundRethinking Brain Tumor Segmentation From the Frequency Domain Perspective
Shao, M.-Y., Wang, Z., Duan, H.-R., Huang, Y.-W., Zhai, B., Wang, S.-Z., Long, Y., & Zheng, Y.-F. (2025) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2025.3579213 · Cited by 34
“ResUNet 3D [42] and paired attention in UNETR ++ [43] push boundaries with detailed spatial focus.”
A hybrid feature fusion deep learning framework for multi-source medical image analysis
Cao, Q., & Cheng, X. S. (2024) · Information Processing & Management · doi:10.1016/j.ipm.2024.103934 · Cited by 39
Kaushal, A., Gupta, A. K., & Sehgal, V. K. (2024) · Scientific Reports · doi:10.1038/s41598-024-79266-6 · Cited by 34
Bougourzi, F., Dornaika, F., Distante, C., & Ahmed, A. T. (2024) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2024.108590 · Cited by 32
“Since Unet architecture Ronneberger et al. (2015) was proposed in 2017, great progress has been made and a lot of Unet variants have been proposed such as Attenion Unet (Att-Unet) Oktay, Schlemper and Folgoc (2018), Unet++ Zhou, Rahman Siddiquee, Tajbakhsh and Liang (2018), ResUnet Zhang, Liu and Wang (2018).”
BackgroundHe, X., Zhou, Y., Liu, B., Zhao, J.-Q., & Yao, R. (2024) · Expert systems with applications · doi:10.1016/j.eswa.2024.124019 · Cited by 34
Hussain, S. I., & Toscano, E. (2024) · Symmetry · doi:10.3390/sym16030366 · Cited by 34
Towards Clinically Applicable Automated Mandibular Canal Segmentation on CBCT.
Ni, F.-D., Xu, Z.-N., Liu, M.-Q., Zhang, M.-J., Li, S., Bai, H.-L., Ding, P., & Fu, K.-Y. (2024) · E -journal of dentistry · doi:10.1016/j.jdent.2024.104931 · Cited by 34
Bi, H., Feng, Y., Yan, Z., Mao, Y., Diao, W., Wang, H., & Sun, X. (2023) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2023.3326292 · Cited by 34
“It is currently applied in a wide variety of fields, including urban management [4], [5], land-use and land-cover mapping [6], [7], environmental monitoring [8], change detection [9], [10], and road extraction [11], [12].”
BackgroundCRCNet: Global-local context and multi-modality cross attention for polyp segmentation
Zhu, J.-B., Ge, M.-F., Chang, Z.-M., & Dong, W. (2023) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2023.104593 · Cited by 34
Usman, M., & Shin, Y.-G. (2023) · Italian National Conference on Sensors · doi:10.3390/s23041989 · Cited by 34
Madasamy, A., Gujrati, V., Ntziachristos, V., & Prakash, J. (2022) · Journal of Biomedical Optics · doi:10.1117/1.jbo.27.10.106004 · Cited by 34
Deep Sparse Representation Based Image Restoration With Denoising Prior
Xu, W., Zhu, Q., Qi, N., & Chen, D.-P. (2022) · IEEE transactions on circuits and systems for video technology (Print) · doi:10.1109/tcsvt.2022.3170689 · Cited by 34
“Inspired by [55], [58], we propose to 353 learn a CNN denoiser which integrates residual blocks [56] dataset can only slightly improve the performance.”
MethodJiao, C.-J., Heitzler, M., & Hurni, L. (2022) · International Journal of Applied Earth Observation and Geoinformation · doi:10.1016/j.jag.2022.102980 · Cited by 34
DuARE: Automatic Road Extraction with Aerial Images and Trajectory Data at Baidu Maps
Yang, J., Ye, X.-Q., Wu, B., Gu, Y., Wang, Z., Xia, D., & Huang, J. (2022) · Knowledge Discovery and Data Mining · doi:10.1145/3534678.3539029 · Cited by 34
“Segmentation-based methods formulate the task as a road segmentation problem from aerial images to predict the 𝑟𝑜𝑎𝑑𝑛𝑒𝑠𝑠 probability and even the fine-grained categories of each pixel [4, 11, 15, 31, 41, 43].”
BackgroundMethodAl‐Shaebi, Z., Ciloglu, F. U., Nasser, M., & Aydin, Ö. F. (2022) · ACS Omega · doi:10.1021/acsomega.2c03856 · Cited by 43
A deep neural network approach to QRS detection using autoencoders
Belkadi, M. A., Daamouche, A., & Melgani, F. (2021) · Expert Systems with Applications · doi:10.1016/j.eswa.2021.115528 · Cited by 40
Yang, R., Ahmed, Z., Schulthess, U., Kamal, M., & Rai, R. (2020) · Remote Sensing Applications Society and Environment · doi:10.1016/j.rsase.2020.100413 · Cited by 34
Deep Learning for Enrichment of Vector Spatial Databases
Touya, G., & Lokhat, I. (2020) · ACM Transactions on Spatial Algorithms and Systems · doi:10.1145/3382080 · Cited by 30
“First, it could be interesting to test residual U-Nets [33] as an improvement of the segmentation model: residual U-Net outperformed traditional U-Nets on different binary segmentation problems.”
BackgroundLearnable Gated Convolutional Neural Network for Semantic Segmentation in Remote-Sensing Images
Guo, S., Jin, Q., Wang, H., Wang, X., Wang, Y., & Xiang, S. (2019) · Remote Sensing · doi:10.3390/rs11161922 · Cited by 34
“…which has many important real-world applications [1–4], typically including plant-disease detection [5–10], land-cover planning [11], vegetation extraction [12], cloud detection [13,14], urban-change detection [15–17], vehicle detection [18], building extraction [19,20] and road extraction [21,22].”
Self-citationA Deep Learning Model for Green Algae Detection on SAR Images
Guo, Y., Gao, L., & Li, X. (2022) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2022.3215895 · Cited by 44
“The classic U-net framework has been widely used in pixelwise classification tasks due to better classification performance and fewer sample requirements [13], [44].”
MethodAn Enhanced GAN Model for Automatic Satellite-to-Map Image Conversion
Zhang, Y., Yin, Y., Zimmermann, R., Wang, G., Varadarajan, J., & Ng, S. (2020) · IEEE Access · doi:10.1109/access.2020.3025008 · Cited by 34
“this task such as the restricted Boltzmann machines [25], FCN with UNet [39] and D-LinkNet [32].”
MethodGlobal photovoltaic solar panel dataset from 2019 to 2022
Li, A., Liu, L., Li, S., Cui, X., Chen, X., & Cao, X. (2025) · Scientific Data · doi:10.1038/s41597-025-04985-y · Cited by 28
Detection of road extraction from satellite images with deep learning method
Aslan, E., & Özüpak, Y. (2024) · Cluster Computing · doi:10.1007/s10586-024-04880-y · Cited by 33
Huang, C., Xie, L., Chen, W., Lin, Y., Wu, Y., Li, P., Chen, W., Wu, Y., & Deng, J. (2024) · Applied Energy · doi:10.1016/j.apenergy.2024.123585 · Cited by 37
Ferreira, M. P., dos Santos, D. R., Ferrari, F., Filho, L. C. T. C., Martins, G. B., & Feitosa, R. Q. (2024) · Urban forestry & urban greening · doi:10.1016/j.ufug.2024.128240 · Cited by 32
Kent, O. W., Tan, W.-C., Choo, T. L., & Lai, W.-K. (2023) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2023.108192 · Cited by 33
Sravya, N., Priyanka, Lal, S., Nalini, J., Reddy, C. S., & Dell’Acqua, F. (2022) · IEEE Transactions on Emerging Topics in Computational Intelligence · doi:10.1109/tetci.2022.3182414 · Cited by 39
“Zhang et al. introduced the Residual U-Net [14] which replaces all the convolutions used in the U-Net on each level with the residual block.”
MethodDeep learning-based recognition and segmentation of intracranial aneurysms under small sample size
Zhu, G., Luo, X., Yang, T., Cai, L., Yeo, J. H., Yan, G., & Yang, J. (2022) · Frontiers in Physiology · doi:10.3389/fphys.2022.1084202 · Cited by 38
“Based on UNet, deep residual UNet (Res-UNet) simpli fi es the training process of deep neural networks with a residual mechanism, achieving higher accuracy in aerial image-based road extraction (Zhang et al., 2018).”
MethodPyo, J., Han, K.-J., Cho, Y., Kim, D., & Jin, D. (2022) · Forests · doi:10.3390/f13122170 · Cited by 33
BoxPolyp: Boost Generalized Polyp Segmentation Using Extra Coarse Bounding Box Annotations
Wei, J., Hu, Y., Li, G.-B., Cui, S., Zhou, S., & Li, Z. (2022) · International Conference on Medical Image Computing and Computer-Assisted Intervention · doi:10.1007/978-3-031-16437-8_7 · Cited by 33
“Thanks to the evolution of computer technology, massive polyp segmentation models [1,4,6,7,8,17,20,23,24,26,29] have been proposed and achieved remarkable performance.”
BackgroundMethodHigh-precision density mapping of marine debris and floating plastics via satellite imagery
Booth, H., Ma, W., & Karakuş, O. (2023) · Scientific Reports · doi:10.1038/s41598-023-33612-2 · Cited by 48
“F-mask takes raw Sentinel-2 data as an input and produces a mask with integer values of 0-5 representing (0) land, (1) water, (2) cloud shadow, (3) snow, (4) cloud, and (5) no observation, respectively.”
BackgroundMethodInfluentialLi, B., Liu, S.-K., Wu, F., Li, G.-H., Zhong, M.-L., & Guan, X.-H. (2022) · International Journal of Intelligent Systems · doi:10.1002/int.22956 · Cited by 33
Gao, L., Wang, C.-Y., Liu, K., Chen, S.-H., Dong, G.-N., & Su, H.-B. (2022) · IEEE International Geoscience and Remote Sensing Symposium · doi:10.1109/igarss46834.2022.9884549 · Cited by 33
“These models and their improved versions enable the pixel-level segmentation and have achieved significant successes in many RS image analysis tasks[17].”
MethodSAA-Net: U-shaped network with Scale-Axis-Attention for liver tumor segmentation
Zhang, C., Lu, J., Hua, Q., Li, C.-G., & Wang, P.-W. (2022) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2021.103460 · Cited by 33
Zhang, X., Cheng, B., Chen, J., & Liang, C. (2021) · Remote Sensing · doi:10.3390/rs13214237 · Cited by 38
“It is also clearly observed that ResUNet has a small number of parameters but still numerous FLOPs, which poses more requirements for hardware.”
ResultDutta, K., Roy, S. S., Whitehead, T., Luo, J. R., Jha, A. K., Li, S., Quirk, J. D., & Shoghi, K. I. (2021) · Cancers · doi:10.3390/cancers13153795 · Cited by 37
“U-Net [18], Res-Unet [19,21], and R2Unet [20] architectures were implemented to that end.”
MethodFuNet: A Novel Road Extraction Network with Fusion of Location Data and Remote Sensing Imagery
Zhou, K., Xie, Y., Gao, Z., Miao, F., & Zhang, L. (2021) · ISPRS International Journal of Geo-Information · doi:10.3390/ijgi10010039 · Cited by 29
“Road region segmentation based on remote sensing images [4] has its unique and difficult characteristics, which are manifested in Figure 1: (1) The road is long and narrow, although it occupies a small proportion of the whole image, and often covers the whole image; (2) the topological connectivity relationship is com…”
BackgroundPai, M.-C., Mehrotra, V., Verma, U., & Pai, R. (2020) · International Journal of Semantic Computing · doi:10.1142/s1793351x20400036 · Cited by 33
“A Deep Learning approach based on a modi¯ed U-Net architecture has been shown to work by Zhengxin Zhang et al. [15], for the extraction of the road using the Massachusetts roads dataset.”
MethodRoad Extraction from Unmanned Aerial Vehicle Remote Sensing Images Based on Improved Neural Networks
Li, Y.-X., Peng, B., He, L., Fan, K., Li, Z., & Tong, L. (2019) · Italian National Conference on Sensors · doi:10.3390/s19194115 · Cited by 33
“[6] proposed a new network for road extraction from remote sensing images, which combines ResNet and U-Net.”
MethodRoadCT: A Hybrid CNN-Transformer Network for Road Extraction From Satellite Imagery
Liu, W., Gao, S.-F., Zhang, C., & yang, B. (2024) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2024.3363128 · Cited by 33
“Zhang et al. [2] applied a U-Net [1] for road extraction, and showed that its skip connections can improve model performance by short-cutting the information propagation in neural networks.”
BackgroundLiu, Y.-Z., Mei, Y., Chen, Y., & Ding, B. (2024) · Composites Part B: Engineering · doi:10.1016/j.compositesb.2024.111353 · Cited by 32
CTH-Net: A CNN and Transformer hybrid network for skin lesion segmentation
Ding, Y., Yi, Z., Xiao, J., Hu, M., Guo, Y. F., Liao, Z., & Wang, Y. (2024) · iScience · doi:10.1016/j.isci.2024.109442 · Cited by 35
Self-citationMapping Industrial Influences on Earth's Ecology
Watson, J. E. M., Ellis, E. C., Pillay, R., Williams, B. A., & Venter, O. (2023) · Annual Review of Environment and Resources · doi:10.1146/annurev-environ-112420-013640 · Cited by 40
“For example, extensive road networks (53), power lines, water irrigation systems, fencing, grazing lands for livestock (54), low-density human settlements (55,56),emerging settlements,and small-scale agriculture can often transform ecosystems as much as industrial conversion and intensive use for…”
BackgroundAhamed, M. F., Syfullah, M. K., Sarkar, O., Islam, M. T., Nahiduzzaman, M., Islam, M. R., Khandakar, A. A., Ayari, M. A., & Chowdhury, M. E. H. (2023) · Sensors · doi:10.3390/s23187724 · Cited by 32
“Since there is minimal chance of injuring the surrounding tissues, the cold snare polypectomy is the most successful technique for removing tiny polyps [6].”
BackgroundRMMLP:Rolling MLP and matrix decomposition for skin lesion segmentation
Ji, C., Deng, Z.-H., Ding, Y., Zhou, F.-S., & Xiao, Z. (2023) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2023.104825 · Cited by 32
Deep learning universal crater detection using Segment Anything Model (SAM)
Giannakis, I., Bhardwaj, A., Sam, L., & Leontidis, G. (2023) · arXiv.org · doi:10.48550/arxiv.2304.07764 · Cited by 32
“In recent years, deep learning has been extensively used for image segmentation with impressive results compared to previous approaches [26, 27, 28, 29, 30, 31]; and has become the standard in remote sensing segmentation in geosciences [32, 33, 34, 35, 36], and for real time identification of objects in Martian terrai…”
ResultShojaiee, F., & Baleghi, Y. (2022) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2022.105627 · Cited by 34
APT-Net: Adaptive encoding and parallel decoding transformer for medical image segmentation
Zhang, N., Yu, L., Zhang, D.-Z., Wu, W., Tian, S., & Kang, X. (2022) · Comput. Biol. Medicine · doi:10.1016/j.compbiomed.2022.106292 · Cited by 32
DilatedSegNet: A Deep Dilated Segmentation Network for Polyp Segmentation
Tomar, N. K., Jha, D., & Bagci, U. (2022) · Conference on Multimedia Modeling · doi:10.48550/arxiv.2210.13595 · Cited by 32
“Train: Kvasir-SEG [8], Test: CVC-ClinicDB [1] U-Net [14] 0.6336 0.5433 0.6982 0.7891 0.6563 ResU-Net [20] 0.5970 0.4967 0.6210 0.8005 0.5991 U-Net++ [22] 0.6350 0.5475 0.6933 0.7967 0.6556 DeepLabV3+ [2] 0.8142 0.7388 0.8331 0.8735 0.8198 ResU-Net++ [9] 0.4642 0.3585 0.5880 0.5770 0.5084 DDANet…”
InfluentialSegmentation of Microaneurysms for Early Detection of Diabetic Retinopathy Using MResUNet
Qomariah, D. U. N., Tjandrasa, H., & Fatichah, C. (2021) · International Journal of Intelligent Engineering and Systems · doi:10.22266/ijies2021.0630.30 · Cited by 32
“[22,31].”
BackgroundRoad Extraction from High-Resolution Orthophoto Images Using Convolutional Neural Network
Abdollahi, A., Pradhan, B., & Shukla, N. (2020) · Journal of the Indian Society of Remote Sensing · doi:10.1007/s12524-020-01228-y · Cited by 32
“Extracting road networks from remote sensing imagery play a vital role in the improvement of transportation systems, such as traffic control, map updating, and automatic road navigation, for daily life, and industrial applications (Zhang et al. 2018).”
BackgroundMethodZhang, Z., Zhao, T.-Y., Gay, H., Zhang, W.-X., & Sun, B.-Z. (2020) · Medical Physics (Lancaster) · doi:10.1002/mp.14580 · Cited by 32
Self-citationAutomatic Segmentation of River and Land in SAR Images: A Deep Learning Approach
Pai, M. M. M., Mehrotra, V., Aiyar, S., Verma, U., & Pai, R. (2019) · International Conference on Artificial Intelligence and Knowledge Engineering · doi:10.1109/aike.2019.00011 · Cited by 32
“[10] for the extraction of the road using the Massachusetts roads data set.”
MethodHAFNet: Hierarchical Attention Fusion Network for Infrared Small Target Detection
Zhang, Y., Bao, W.-T., Yang, Y., Wan, W.-G., Xiao, Q., & Zou, X.-T. (2025) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2025.3607732 · Cited by 32
“ResUNet [44] integrated residual connections from ResNet [45] into both the encoder and decoder, enabling deeper network architectures while alleviating vanishing gradient issues and training di ffi culties.”
A Combination of Convolutional and Graph Neural Networks for Regularized Road Surface Extraction
Yan, J.-J., Ji, S., & Wei, Y. (2022) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2022.3151688 · Cited by 32
“Zhang et al. [13] proposed an architecture named ResUnet for road extraction, which combines the strengths of residual learning and the U-Net architecture to ease the training burden.”
BackgroundEnhancing satellite semantic maps with ground-level imagery
Balaska, V. E., Bampis, L., Kansizoglou, I., & Gasteratos, A. C. (2021) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2021.103760 · Cited by 34
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
