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 801–900 of 1,001
Richer U-Net: Learning More Details for Road Detection in Remote Sensing Images
Zao, Y., & Shi, Z.-W. (2022) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2021.3081774 · Cited by 18
“Zhang et al. [8] designed a road extraction network, which combines the strengths of residual learning and U-Net.”
BackgroundImprovement of Urinary Stone Segmentation Using GAN-Based Urinary Stones Inpainting Augmentation
Preedanan, W., Suzuki, K., Kondo, T., Kobayashi, M., Tanaka, H., Ishioka, J., Matsuoka, Y., Fujii, Y., & Kumazawa, I. (2022) · IEEE Access · doi:10.1109/access.2022.3218444 · Cited by 18
“The Unet-based models used in this experiment are the original U-Net [37], ResUnet [38], Unet ++ [39], Attention Unet [40], MultiResUnet [33], TransUnet [41], and UTNet [42].”
MethodResD-Unet Research and Application for Pulmonary Artery Segmentation
Yuan, H., Liu, Z., Shao, Y., & Liu, M. (2021) · IEEE Access · doi:10.1109/access.2021.3073051 · Cited by 23
“To fully extract high-level intra-slice features, we designed an efficient deep network called ResD-Unet, which combines the advantages of residual connections [12], dense connections [13] and U-Net [6].”
MethodHuman Face Sketch to RGB Image with Edge Optimization and Generative Adversarial Networks
Zhang, F., Zhao, H., Ying, W., Liu, Q., Raj, A., & Fu, B. (2020) · Intelligent Automation and Soft Computing · doi:10.32604/iasc.2020.011750 · Cited by 18
“The generator architecture uses U-Net to skip connections to break through the bottleneck reached by sampling.”
MethodInfluentialSelf-citationAn improved EnlightenGAN shadow removal framework for images of cracked concrete
Sun, R., Li, X., Law, S., Zhang, L., Hu, L.-Z., & Liu, G. (2024) · Mechanical systems and signal processing · doi:10.1016/j.ymssp.2024.111943 · Cited by 18
Optimisation of city structures with respect to high wind speeds using U-Net models
Nowak, D., Werner, J., Parsons, Q., Johnson, T., Mark, A., & Edelvik, F. (2024) · Engineering applications of artificial intelligence · doi:10.1016/j.engappai.2024.108812 · Cited by 17
Shape-intensity-guided U-net for medical image segmentation
Dong, W., Du, B., & Xu, Y. (2024) · Neurocomputing · doi:10.1016/j.neucom.2024.128534 · Cited by 19
Depth estimation from monocular endoscopy using simulation and image transfer approach
Jeong, B. H., Kim, H. K., & Son, Y. (2024) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2024.109038 · Cited by 24
He, Q., Yao, X.-J., Wu, J., Yi, Z., & He, T. (2024) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2024/91 · Cited by 17
“For example, ResUNet [Zhang et al. , 2018] combines the UNet architecture with residual connections inspired by ResNet [He et al. , 2015].”
MethodDong, C., Dai, D.-W., Li, Z., & Xu, S.-Y. (2024) · Information Fusion · doi:10.1016/j.inffus.2024.102561 · Cited by 17
TV-Net: A Structure-Level Feature Fusion Network Based on Tensor Voting for Road Crack Segmentation
Zheng, W., Jiang, X.-Y., Fang, Z.-J., & Gao, Y.-B. (2024) · IEEE transactions on intelligent transportation systems (Print) · doi:10.1109/tits.2023.3334266 · Cited by 17
Kaur, A., Singh, Y., & Chinagundi, B. (2024) · Evolutionary Systematics · doi:10.1007/s12530-024-09579-4 · Cited by 17
Shape-margin knowledge augmented network for thyroid nodule segmentation and diagnosis
Liu, W., Lin, C., Chen, D.-D., Niu, L.-J., Zhang, R., & Pi, Z. (2024) · Comput. Methods Programs Biomed. · doi:10.1016/j.cmpb.2023.107999 · Cited by 17
Erep, T. R. B. A., & Chaâri, L. (2023) · Italian National Conference on Sensors · doi:10.3390/s24010209 · Cited by 17
“We compared the performance of the mid-DeepLabv3+ model with some popular CNN semantic image segmentation models, including GourmetNet [37], DeepLabv3+ [9], FCN [56], ResUnet [57], and U-Net [58].”
MethodRoad Extraction from High-Resolution Remote Sensing Images via Local and Global Context Reasoning
Chen, J., Yang, L., Wang, H., Zhu, J., Sun, G., Dai, X., Deng, M., & Shi, Y. (2023) · Remote Sensing · doi:10.3390/rs15174177 · Cited by 23
Lin, J., Miao, Q., Surawech, C., Raman, S. S., Zhao, K., Wu, H. H., & Sung, K. (2023) · IEEE Access · doi:10.1109/access.2023.3307577 · Cited by 17
“1) NETWORK ARCHITECTURES—Our proposed deep generative networks are compared against three other popular deep-learning networks structures, such as U-Net [50], ResUNet [51], and SRGAN [38], to demonstrate the compatibility of the SPTSR framework with other deep learning networks architecture.”
InfluentialZhu, T., Zhu, S., Zheng, T., Ding, H., Song, W., & Li, C.-J. (2023) · The Visual Computer · doi:10.1007/s00371-023-02846-6 · Cited by 17
“To further evaluate the performance of the proposed model for pixel-level segmentation, HEU-Net is compared with state-of-the-art methods, including FCN-8S [27], PSPNet [57], U -Net [28], Res-U-Net [29], SE-U-Net [30], Attention-U-Net [31], U -Net + + [32], SegFormer [58], and Swin Transformer [59].”
Tian, F., Wu, B., Zeng, H., Zhang, M., Hu, Y., Xie, Y., Wen, C., Wang, Z., Qin, X., Han, W., et al. (2023) · GIScience & Remote Sensing · doi:10.1080/15481603.2023.2165256 · Cited by 23
“We found that the IOU of CPIS for U-Net and Deep ResUnet trained with multi-task was 1.16% and 0.48% higher than single task, respectively.”
BackgroundMethodInfluentialZhang, X., Jiang, Y. Y., Wang, L., Han, W., Feng, R., Fan, R., & Wang, S. (2022) · Remote Sensing · doi:10.3390/rs14194729 · Cited by 22
DFTNet: Dual-Path Feature Transfer Network for Weakly Supervised Medical Image Segmentation
Cai, W., Xie, L., Yang, W., Li, Y., Gao, Y., & Wang, T. (2022) · IEEE Transactions on Computational Biology and Bioinformatics · doi:10.1109/tcbb.2022.3198284 · Cited by 18
“To further verify the performance of the network, we also compared with ResUNet [51] and TransUNet [33] in the fully supervised conditions, as shown in Table 1, we achieved a dice score of 85.45 and a Hausdorff distance of 4.164 mm , compared to 83.09 and 4.954 mm for ResUNet and 83.44 and 5.092 mm…”
ResultInfluentialChinkamol, A., Kanjaras, V., Sawangjai, P., Zhao, Y., Sudhawiyangkul, T., Chantrapornchai, C., Guan, C.-T., & Wilaiprasitporn, T. (2022) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2022.3232102 · Cited by 17
“The comparison was made against the original OCTA-Net results and other segmentation methods [9], [23], [41], [42], [43], [44], [45], [46], [47] as reported in the original work.”
ResultSarica, B., & Şeker, D. Z. (2022) · Frontiers in Neuroscience · doi:10.3389/fnins.2022.912000 · Cited by 22
“Combinations of UNet and residual learning were also used for different image segmentation problems, such as road extraction using remote sensing data (Zhang et al., 2018).”
MethodDeep-Based Film Grain Removal and Synthesis
Ameur, Z., Hamidouche, W., François, É., Radosavljević, M., Ménard, D., & Demarty, C.-H. (2023) · IEEE Transactions on Image Processing · doi:10.1109/tip.2023.3308726 · Cited by 18
“ual blocks [53], our proposed generator consists of a five scale U-Net model with residual blocks.”
MethodCross-Attention and Deep Supervision UNet for Lesion Segmentation of Chronic Stroke
Sheng, M., Xu, W., Yang, J., & Chen, Z.-J. (2022) · Frontiers in Neuroscience · doi:10.3389/fnins.2022.836412 · Cited by 17
“, 2015), ResUNet (Zhang et al., 2018), and Attention-UNet (Oktay et al.”
InfluentialJimenez-Castaño, C. A., Álvarez-Meza, A., Aguirre-Ospina, O., Cárdenas-Peña, D., & Orozco-Gutiérrez, Á. (2021) · Italian National Conference on Sensors · doi:10.3390/s21227741 · Cited by 17
“Moreover, the U-net algorithm pretends to relieve training problems related to a limited number of samples [47].”
BackgroundOn the effect of manual rework in AFP quality control for a doubly-curved part
Sacco, C., Brasington, A., Saidy, C., Kirkpatrick, M., Halbritter, J., Wehbe, R., & Harik, R. (2021) · Composites Part B: Engineering · doi:10.1016/j.compositesb.2021.109432 · Cited by 17
McAleer, S., Fast, A., Xue, Y., Seiler, M. J., Tang, W. C., Balu, M., Baldi, P., & Browne, A. (2021) · Translational Vision Science & Technology · doi:10.1167/tvst.10.12.30 · Cited by 27
Gated Auxiliary Edge Detection Task for Road Extraction With Weight-Balanced Loss
Li, R., Gao, B., & Xu, Q.-Z. (2021) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2020.2985774 · Cited by 17
“For instance, fully convolution network (FCN)-based network architectures [5]–[7] and U-Net-based network architectures [8]–[10] achieved great improvements in road extraction.”
BackgroundCleftNet: Augmented Deep Learning for Synaptic Cleft Detection from Brain Electron Microscopy
Liu, Y., & Ji, S. (2021) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2021.3089547 · Cited by 17
Mass Estimation of Galaxy Clusters with Deep Learning. I. Sunyaev–Zel’dovich Effect
Gupta, N., & Reichardt, C. (2020) · Astrophysical Journal · doi:10.3847/1538-4357/aba694 · Cited by 17
“Such connections are called residual connections (He et al. 2015) and they are known to improve the performance of the network (e.g. Zhang et al. 2018; Caldeira et al. 2019).”
BackgroundMethodAutomated Crack Detection via Semantic Segmentation Approaches Using Advanced U-Net Architecture
Ji, H., Kim, J., Hwang, S., & Park, E. (2022) · Intelligent Automation & Soft Computing · doi:10.32604/iasc.2022.024405 · Cited by 20
“2 ResU-Net ResU-Net, which includes a residual block to exclude issues regarding training degradation in deeper hidden layers [38], was employed [36].”
MethodHuang, Z., Zhao, Z.-Y., Yu, Z., Hou, M.-Y., Zhou, S., Wang, J.-H., Yan, Y., Liu, Y.-S., & Gregersen, H. (2025) · Neural Networks · doi:10.1016/j.neunet.2025.107919 · Cited by 16
Uz, M., Akyılmaz, O., & Shum, C. (2024) · Journal of Hydrology · doi:10.1016/j.jhydrol.2024.132194 · Cited by 16
Kong, L.-F., & Wu, Y. (2024) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2024.106296 · Cited by 16
Multi-Material Decomposition Using Spectral Diffusion Posterior Sampling
Jiang, X., Gang, G., & Stayman, J. (2024) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2025.3543747 · Cited by 16
“A Residual Unet [40] was employed as the back-bone network of the diffusion model.”
Габдуллин, М. Т., Mukasheva, A., Koishiyeva, D., Umarov, T., Bissembayev, A., Kim, K.-S., & Kang, J. W. (2024) · Biotechnology and Bioprocess Engineering · doi:10.1007/s12257-024-00130-5 · Cited by 18
“This architecture [38] includes encoder blocks comprising convolution layers with different kernel sizes, max pooling operations for dimensionality reduction, and concatenation operations for combining features.”
Wagner, F., Xu, W.-T., Saha, P., Liang, Z.-Y., Whitehouse, D., Menon, D., Newcombe, V. F. J., Voets, N., Noble, J., & Kamnitsas, K. (2024) · IEEE Workshop/Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61041.2025.00045 · Cited by 16
Land use land cover classification using Sentinel imagery based on deep learning models
Sawant, S. T., & Ghosh, J. K. (2024) · Journal of Earth System Science · doi:10.1007/s12040-024-02298-z · Cited by 21
“2021), autonomous driving (Tran and Le 2019), road extraction (Zhang et al .”
Weakly-supervised learning based automatic augmentation of aerial insulator images
Jiang, D., Cao, Y., & Yang, Q. (2023) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.122739 · Cited by 16
Usman, M., Rehman, A., Masood, S., Khan, T. M., & Qadir, J. (2024) · Internet of Things · doi:10.1016/j.iot.2024.101065 · Cited by 15
Kim, J., & Kim, Y. (2024) · Remote Sensing · doi:10.3390/rs16030526 · Cited by 16
Wang, Y., Yu, X., Yang, Y.-X., Zhang, X., Zhang, Y., Zhang, L., Feng, R., & Xue, J. (2023) · Comput. Methods Programs Biomed. · doi:10.1016/j.cmpb.2023.107914 · Cited by 16
Self-citationHu, Z.-K., Yi, B.-J., Li, H., Zhong, C., Gao, P., Chen, J., Yao, Q., & Guo, H. (2023) · Italian National Conference on Sensors · doi:10.3390/s23229041 · Cited by 16
“While numerous semantic segmentation models have emerged and continue to evolve, U-Net and its variations, such as U-net 3+ [13], ResU-Net [14], and TransU-Net [15], remain the most widely used models in current semantic segmentation research due to their superior performance.”
BackgroundD-FusionNet: road extraction from remote sensing images using dilated convolutional block
Zhang, R.-X., Zhu, W., Li, Y., Song, T.-S., Li, Z.-H., Yang, W., Yang, L., Zhou, T., & Xu, X.-Y. (2023) · GIScience & Remote Sensing · doi:10.1080/15481603.2023.2270806 · Cited by 16
“Zhang et al. (2018) developed a deep residual U-Net model that reduced feature loss through the use of dense connections and residual structures.”
BackgroundGeneralizable synthetic MRI with physics‐informed convolutional networks
Jacobs, L., Mandija, S., Liu, H., van den Berg, C. A. T., Sbrizzi, A., & Maspero, M. (2023) · Medical Physics (Lancaster) · doi:10.1002/mp.16884 · Cited by 16
“2), consisting of a ResUNet generator [44] with three down-sampling operations (33M and 13M parameters, respectively) and four contrast-specific conditional PatchGAN discriminators [43] (2.”
Unsupervised CD in Satellite Image Time Series by Contrastive Learning and Feature Tracking
Chen, Y.-X., & Bruzzone, L. (2023) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2024.3354118 · Cited by 16
“The change detection model is trained from pseudo labels by the joint use of Unet [33] and ConvLSTM networks.”
MethodRastogi, D., Johri, P., & Tiwari, V. (2023) · International Journal of Mathematical Engineering and Management Sciences · doi:10.33889/ijmems.2023.8.2.020 · Cited by 16
Guan, X., Zhao, Y.-S., Nyatega, C. O., & Li, Q. (2023) · Brain Science · doi:10.3390/brainsci13040650 · Cited by 16
Amirian, M., Füchslin, R., Herzig, I., Hotz, P. E., Lichtensteiger, L., Montoya-Zegarra, J. A., Morf, M., Paysan, P., Peterlík, I., Scheib, S., et al. (2023) · Medical Physics (Lancaster) · doi:10.1002/mp.16405 · Cited by 16
Lymph node detection in CT scans using modified U-Net with residual learning and 3D deep network
Manjunatha, Y., Sharma, V., Iwahori, Y., Bhuyan, M. K., Wang, A., Ouchi, A., & Shimizu, Y. (2023) · International Journal of Computer Assisted Radiology and Surgery · doi:10.1007/s11548-022-02822-w · Cited by 16
“As a result, various other research domains [14,15] adopted residual connections in U-Net structures.”
BackgroundChen, C., Zhang, C., Wang, J., Li, D., Li, Y., & Hong, J. (2023) · Measurement · doi:10.1016/j.measurement.2023.112499 · Cited by 24
MHAU-Net: Skin Lesion Segmentation Based on Multi-Scale Hybrid Residual Attention Network
Li, Y., Xu, C., Han, J., An, Z., Wang, D., Ma, H., & Liu, C. (2022) · Italian National Conference on Sensors · doi:10.3390/s22228701 · Cited by 16
“…enhancement of feature vectors in both channel and spatial dimensions; Slicing experiments are conducted to verify the contribution of HRA, dilation convolution, and cross-validation pieces relative to the MHAU-Net model. convolution, and cross-validation pieces relative to the MHAU-Net model.”
MethodShi, W.-X., Meng, Q.-Y., Zhang, L.-L., Zhao, M.-F., Su, C., & Jancsó, T. (2022) · Remote Sensing · doi:10.3390/rs14215399 · Cited by 16
“UNet [12], which is based on an encoder-decoder architecture, enhances the FCN’s capacity to represent the multiscale features of images through contraction paths and expansion paths for achieving high-precision road [13] and coastline recognition [14] in RSIs.”
BackgroundYong, P.-F., & Wang, N. (2022) · Applied Sciences · doi:10.3390/app12147066 · Cited by 16
Lin, C., Chen, H., Huang, J., Peng, J., Guo, L., Yang, Z., Du, J., Li, S., Yin, A., & Zhao, G. (2022) · Computational Biology and Chemistry · doi:10.1016/j.compbiolchem.2022.107731 · Cited by 15
OSS-Net: Memory Efficient High Resolution Semantic Segmentation of 3D Medical Data
Reich, C., Prangemeier, T., Çetin, Ö., & Koeppl, H. (2021) · British Machine Vision Conference · doi:10.5244/c.35.405 · Cited by 16
“We employed a 2D residual U-Net [40] with group normalization [37] as a memoryefficient slicing baseline.”
MethodPatil, P. S., Holambe, R. S., & Waghmare, L. (2021) · Digit. Signal Process. · doi:10.1016/j.dsp.2021.103250 · Cited by 16
A road extraction method for intelligent dispatching based on MD-LinkNeSt network in open-pit mine
Gu, Q.-H., Xue, B., Ruan, S.-L., & Li, X. (2021) · International Journal of Mining, Reclamation and Environment · doi:10.1080/17480930.2021.1949800 · Cited by 16
Gaonkar, B., Beckett, J. S., Attiah, M. A., Ahn, C., Edwards, M., Wilson, B., Laiwalla, A. N., Salehi, B., Yoo, B. Y., Bui, A. A. T., et al. (2020) · Medical Image Anal. · doi:10.1016/j.media.2020.101834 · Cited by 16
“It was further modified by the addition of residual layers in (Zhang et al., 2018).”
BackgroundYuan, S., Yang, K., Li, X. S., & Hongyue, C. (2020) · Sensors · doi:10.3390/s20071832 · Cited by 20
A Large‐Scale Analysis of Pockets of Open Cells and Their Radiative Impact
Watson‐Parris, D., Sutherland, S., Christensen, M. W., Stier, P., & Eastman, R. M. (2021) · Geophysical Research Letters · doi:10.1029/2020gl092213 · Cited by 31
Xiang, B., Tu, J., Yao, J., & Li, L. (2019) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2019.2916625 · Cited by 22
“This type of network architecture is proven to be competitive in many tasks, such as binary image segmentation [60], [67], [68] and medical volumetric segmentation [69].”
BackgroundRGB-NIR Demosaicing Using Deep Residual U-Net
Shopovska, I., Jovanov, L., & Philips, W. (2018) · Telecommunications Forum · doi:10.1109/telfor.2018.8611819 · Cited by 16
“2) has several differences with the one in [11], and is adapted to the problem at hand: (1) A residual unit follows the first nonlinear operation (convolution + ReLU) at each resolution in the down-sampling path.”
BackgroundA novel deep learning-based automatic search workflow for CO2 sequestration surrogate flow models
Xu, J., Fu, Q., & Li, H. (2023) · Fuel · doi:10.1016/j.fuel.2023.129353 · Cited by 17
LGNet: Location-Guided Network for Road Extraction From Satellite Images
Hu, J.-T., Gao, J., Yuan, Y., Chanussot, J., & Wang, Q. (2023) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2023.3305031 · Cited by 16
“To combine with U-Net and residual units in ResNet, deep residual U-Net (ResUNet) [27] outperforms”
MethodContour-Aware Residual W-Net for Nuclei Segmentation
Das, S., Deka, A., Iwahori, Y., Bhuyan, M. K., Iwamoto, T., & Ueda, J. (2019) · International Conference on Knowledge-Based Intelligent Information & Engineering Systems · doi:10.1016/j.procs.2019.09.318 · Cited by 16
Chen, J.-H., Liang, Z.-Y., & Lu, X. (2025) · Scientific Reports · doi:10.1038/s41598-025-19563-w · Cited by 15
A Bi-Directionally Fused Boundary Aware Network for Skin Lesion Segmentation
Yuan, F., Peng, Y., Huang, Q., & Li, X. (2024) · IEEE Transactions on Image Processing · doi:10.1109/tip.2024.3482864 · Cited by 13
“In addition, other encoder-decoder architectures, such as V-Net [7], 3D U-Net [8], Residual U-Net [9], Double U-Net [10], etc., have exhibited excellent performance in multiple medical image segmentation tasks with different imaging modalities.”
BackgroundAn Edge-Enhanced Network for Polyp Segmentation
Tong, Y., Chen, Z., Zhou, Z., Hu, Y., Li, X., & Qiao, X. (2024) · Bioengineering · doi:10.3390/bioengineering11100959 · Cited by 12
“[47], ( d ) DeepLav V3+ [14], ( e ) UNet++ [15], ( f ) ResUNet [49], ( g ) ResUNet++ [16], ( h ) PraNet [21], ( i ) XNet [61], ( j ) Polyp-PVT [26], and ( k ) EENet (ours).”
BackgroundMethodJi, Z.-L., Li, X., Wang, Z., Zhang, H.-Y., Yuan, N., Zhang, X., & Ganchev, I. (2024) · International journal of imaging systems and technology (Print) · doi:10.1002/ima.23183 · Cited by 15
“…the proposed CafeNet network was evaluated in comparison to nine SOTA networks, including three medical image segmentation networks (U-Net [15], ResUnet [16], UNet++ [17]) and six polyp segmentation networks (ResUNet++ [18], ACSNet [25], PraNet [23], EU-Net [49], DCRNet [24], DilatedSegNet [50]).”
MAPFUNet: Multi-attention Perception-Fusion U-Net for Liver Tumor Segmentation
Sun, J.-D., Wang, B., Wu, X.-S., Tang, C.-S., Wang, S.-H., & Zhang, Y.-D. (2024) · Journal of Bionic Engineering · doi:10.1007/s42235-024-00562-y · Cited by 15
S3AR U-Net: A separable squeezed similarity attention-gated residual U-Net for glottis segmentation
Montalbo, F. J. P. (2024) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2024.106047 · Cited by 13
Deep learning-based image segmentation for instantaneous flame front extraction
Strässle, R. M., Faldella, F., & Doll, U. (2024) · Experiments in Fluids · doi:10.1007/s00348-024-03814-z · Cited by 19
Xu, W.-T., Moffat, M., Seale, T., Liang, Z.-Y., Wagner, F., Whitehouse, D., Menon, D., Newcombe, V. F. J., Voets, N., Banerjee, A., et al. (2024) · International Conference on Medical Imaging with Deep Learning · doi:10.48550/arxiv.2405.18511 · Cited by 15
Enhancing Road Crack Localization for Sustainable Road Safety Using HCTNet
Yadav, D. P., Sharma, B., Chauhan, S., Amin, F., & Abbasi, R. (2024) · Sustainability · doi:10.3390/su16114409 · Cited by 14
DFBU-Net: Double-branch flat bottom U-Net for efficient medical image segmentation
Yin, H., Wang, Y., Wen, J., Wang, G.-X., Lin, B., Yang, W.-B., Ruan, J., & Zhang, Y. (2024) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2023.105818 · Cited by 15
Self-citationChen, Z., Xiao, C., Liu, Y., Hassan, H., Li, D., Liu, J., Li, H., Xie, W., Zhong, W., & Huang, B.-D. (2024) · Information Systems Frontiers · doi:10.1007/s10796-024-10485-y · Cited by 15
“In the initial stage of the proposed framework, three state-of-the-art segmentation algorithms, 3D U-Net (Çiçek et al., 2016), Res U-Net (Zhang et al., 2018), and Swin UNETR (Hatamizadeh et al., 2021), were assessed and examined.”
U-SeqNet: learning spatiotemporal mapping relationships for multimodal multitemporal cloud removal
Zhang, Q., Liu, X., Peng, T., Yang, X., Tang, M., Zou, X., Liu, M., Wu, L., & Zhang, T. (2024) · GIScience & Remote Sensing · doi:10.1080/15481603.2024.2330185 · Cited by 14
“Methods of reconstructing missing information caused by cloud contamination are classified into four main categories according to the type of reference information used for reconstruction (Shen et al. 2015; Q. Zhang et al. 2018): spatial-based, spectral-based, temporal-based, and hybrid methods.”
Lightning Nowcasting Using Solely Lightning Data
Mansouri, E., Mostajabi, A., Tong, C., Rubinstein, M., & Rachidi, F. (2023) · Atmosphere · doi:10.3390/atmos14121713 · Cited by 15
SA2-Net: Scale-aware Attention Network for Microscopic Image SegmentationPreprint
Fiaz, M., Heidari, M., Anwer, R. M., & Cholakkal, H. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2309.16661 · Cited by 10
A novel image denoising algorithm combining attention mechanism and residual UNet network
Ding, S., Wang, Q., Guo, L., Zhang, J., & Ding, L. (2023) · Knowledge and Information Systems · doi:10.1007/s10115-023-01965-9 · Cited by 15
Wang, Y., Wang, M.-D., Cao, P., Wong, E., Ho, G., Lam, T., Han, L.-J., & Lee, E. Y. P. (2023) · Quantitative Imaging in Medicine and Surgery · doi:10.21037/qims-22-1135 · Cited by 15
“Most improvements based on classic U-Net structure focused on network architecture variations, such as the usage of attention gate and residual unit (14,15).”
Self-citationKaur, R., & Ranade, S. K. (2023) · International journal of information technology · doi:10.1007/s41870-023-01330-7 · Cited by 15
“Abraham et al. [26] proposed attention U-Net for efficient skin lesion segmentation.”
InfluentialNishi, H., Cancelliere, N., Rustici, A., Charbonnier, G., Chan, V., Spears, J., Marotta, T., & Pereira, V. M. (2023) · Journal of NeuroInterventional Surgery · doi:10.1136/jnis-2023-020192 · Cited by 15
Yu, J.-J., He, X.-F., Yang, P., Motagh, M., Xu, J., & Xiong, J.-C. (2023) · Remote Sensing · doi:10.3390/rs15092246 · Cited by 15
Segmentation and Classification Approaches of Clinically Relevant Curvilinear Structures: A Review
Kv, R., Prasad, K., & Yegneswaran, P. P. (2023) · Journal of medical systems · doi:10.1007/s10916-023-01927-2 · Cited by 15
“A comparative evaluation of their proposal with methods employed by other researchers [61, 101–104] for nerve fiber tracing revealed a sensitivity of 84% and FDR of 25%.”
MethodSemi-universal geo-crack detection by machine learning
Shi, Y., Ballesio, M., Johansen, K., Trentman, D., Huang, Y., McCabe, M. F., Bruhn, R. L., & Schuster, G. T. (2023) · Frontiers in Earth Science · doi:10.3389/feart.2023.1073211 · Cited by 20
“This is because the U-Net is a deep network with shortconnections between the encoder and decoder structure to enable an accurate semantic segmentation: the short connections ease information propagation in training and compensate details for high level semantic features (Zhang et al., 2018).”
BackgroundContinuous U-Net: Faster, Greater and Noiseless
Cheng, C., Runkel, C., Liu, L., Chan, R., Schönlieb, C., & Avilés-Rivero, A. (2023) · Trans. Mach. Learn. Res. · doi:10.48550/arxiv.2302.00626 · Cited by 15
“Zhang et al. introduced Re-sUNet [36], where residual blocks along with several additional mechanisms such as atrous convolutions [6], pyramid scene parse pooling [37] and multi-task inference [30] were used.”
BackgroundMethodInfluentialMed-DANet: Dynamic Architecture Network for Efficient Medical Volumetric Segmentation
Wang, W.-X., Chen, C., Wang, J., Zha, S., Zhang, Y., & Li, J. (2022) · European Conference on Computer Vision · doi:10.48550/arxiv.2206.06575 · Cited by 15
“Similarly, the 2D U-Net [32] and its variants such as [29, 42, 43] are also confronted with the same problem because of the unique architecture.”
BackgroundYerram, V., Takeshita, H., Iwahori, Y., Hayashi, Y., Bhuyan, M. K., Fukui, S., Kijsirikul, B., & Wang, A.-L. (2022) · Journal of Imaging · doi:10.3390/jimaging8050124 · Cited by 15
“[6] proposed a deep residual U-net for road semantic segmentation from high-resolution satellite imagery.”
BackgroundAugmentation Invariance and Adaptive Sampling in Semantic Segmentation of Agricultural Aerial Images
Tavera, A., Arnaudo, E., Masone, C., & Caputo, B. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw56347.2022.00172 · Cited by 15
“For example, in urban monitoring semantic segmentation is mainly used to identify infrastructures, such as roads [39] and buildings [10].”
Exploring Deep Learning Methods for Real-Time Surgical Instrument Segmentation in Laparoscopy
Jha, D., Ali, S., Tomar, N. K., Riegler, M., Johansen, D., Johansen, H., & Halvorsen, P. (2021) · 2021 IEEE EMBS International Conference on Biomedical and Health Informatics (BHI) · doi:10.1109/bhi50953.2021.9508610 · Cited by 15
“We have compared nine different state-of-the-art recent deep learning methods such as UNet [14], FCN8 [25], ResUNet [20], ResUNet++ [21], DDANet [24], ColonSegNet [23], PSPNet [26], and DeepLabv3+ [13] with ResNet50 [28] and MobileNetv2 [27] backbones.”
MethodInfluentialMartins, V., Kaleita, A., & Gelder, B. (2021) · Science of the Total Environment · doi:10.1016/j.scitotenv.2021.145191 · Cited by 15
A Deep Residual U-Type Network for Semantic Segmentation of Orchard Environments
Shang, G.-G., Liu, G., Zhu, P., Han, J.-Y., Xia, C.-G., & Jiang, K. (2020) · Applied Sciences · doi:10.3390/app11010322 · Cited by 15
“Zhang [14] combined the strengths of U-Net and residual learning to construct a seven-layer deep residual U-type network for road extraction from aerial images and achieved good results.”
Liang, W., Wu, Y., Li, M., & Cao, Y. (2020) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2019.2963699 · Cited by 24
“[60] proposed a DR_U-Net, which combines the strengths of the residual learning and the U-Net.”
High-quality Speech Synthesis Using Super-resolution Mel-SpectrogramPreprint
Sheng, L., Huang, D.-Y., & Pavlovskiy, E. N. (2019) · arXiv.org · doi:10.48550/arxiv.1912.01167 · Cited by 15
“In this work, we proposed a novel model to improve melspectrograms prediction for high-quality speech synthesis by combining the advantages of Pix2PixHD [14] and deep residual U-Net (ResUnet) [16].”
MethodPM2.5 Retrieval With Sentinel-5P Data Over Europe Exploiting Deep Learning
Mazza, A., Guarino, G., Scarpa, G., Yuan, Q., & Vivone, G. (2025) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2025.3555637 · Cited by 16
“Finally, the PMUnet model is based on the U-Net architecture proposed by [47], a popular encoder–decoder model frequently used in applications, such as image segmentation [53], [54].”
Updating Road Maps at City Scale With Remote Sensed Images and Existing Vector Maps
Chen, X., Yu, A.-Z., Sun, Q., Guo, W., Xu, Q., & Wen, B.-W. (2024) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2024.3375807 · Cited by 15
“Zhang et al. [15] proposed a u-net-based architecture to extract the road binary map.”
BackgroundFault Detection and Semantic Segmentation on Railway Track Using Deep Fusion Model
Rampriya, R. S., Jenefa, A., Prathiba, S. B., Sabarinathan, Julus, L. J., Selvaraj, A. K., & Rodrigues, J. J. P. C. (2024) · IEEE Access · doi:10.1109/access.2024.3462822 · Cited by 21
“The semantic segmentation is implemented using deep residual U-Net [31], where ResNet is used as a backbone for the U-Net model.”
MethodFerrari, F., Ferreira, M. P., Almeida, C. A., & Feitosa, R. Q. (2023) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2023.3242430 · Cited by 17
“All tested models are variants of the ResUnet [6] architecture.”
MethodInfluential
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
