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.
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
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 deep residual U-Net has already been successfully used for retinal OCT images.
“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]
The Introduction (p. 1) identifies this paper as proposing a deep residual U-Net, so it supports the citation as a reference for the architecture. The experiments (p. 3) test it on a roads dataset, not retinal OCT images; our copy does not support the claimed successful OCT use. (LLM, conf=0.86)
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.
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× · see citing works
“This somehow shares similar idea to that of residual neural network [21].”
BackgroundMethodResultInfluentialU-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× · see citing works
“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].”
BackgroundMethodInfluentialVery Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1409.1556 · Cited by 74,248 · cited 1× · see citing works
“Recently, lots of works have suggested that a deeper network would have better performance [19], [20].”
BackgroundFaster 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 56,035 · cited 1× · see citing works
“of-the-art performance on a variety of computer vision tasks, such as scene recognition [13] and object detection [14].”
BackgroundGoing 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× · see citing works
“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× · see citing works
“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× · see citing works
“[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 2,229 · see citing works
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× · see citing works
“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].”
BackgroundMethodResultInfluentialCheng, G., Wang, Y., Xu, S., Wang, H., Xiang, S., & Pan, C. (2017) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2017.2669341 · Cited by 439 · cited 1× · see citing works
“There are also methods that extract both road areas and centerline, simultaneously [9].”
MethodSelf-citationRoad Extraction Using SVM and Image Segmentation
Song, M., & Civco, D. L. (2004) · Photogrammetric Engineering & Remote Sensing · doi:10.14358/pers.70.12.1365 · Cited by 296 · cited 1× · see citing works
“For instance, Song and Civco [11] proposed a method utilizing shape index feature and support vector machine (SVM) to detect road areas.”
MethodDas, S., Mirnalinee, T. T., & Varghese, K. (2011) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2011.2136381 · Cited by 222 · cited 1× · see citing works
“[12] exploited two salient features of roads and designed a multistage framework to extract roads”
BackgroundMultiple Object Extraction from Aerial Imagery with Convolutional Neural Networks
Saito, S., Yamashita, T., & Aoki, Y. (2016) · IRIACV · doi:10.2352/issn.2470-1173.2016.10.robvis-392 · Cited by 213 · cited 5× · see citing works
“[5], U-Net [24], and the proposed ResUnet.”
BackgroundMethodResultInfluentialRoad Network Detection Using Probabilistic and Graph Theoretical Methods
Unsalan, C., & Sirmaçek, B. (2012) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2012.2190078 · Cited by 172 · see citing works
Huang, X., & Zhang, L.-P. (2009) · International Journal of Remote Sensing · doi:10.1080/01431160802546837 · Cited by 154 · cited 1× · see citing works
“Road area extraction [1]–[6] can generate pixel-level labeling of roads, while road centerline extraction [7], [8] aims at detecting skeletons of a road.”
BackgroundAlshehhi, R., & Marpu, P. (2017) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2017.02.008 · Cited by 150 · cited 3× · see citing works
“Manuscript received **, 2017; revised **, 2017. multi-spectral images using probabilistic SVM. Alshehhi and Marpu [6] proposed an unsupervised road extraction method based on hierarchical graph-based image segmentation.”
BackgroundSujatha, C., & Selvathi, D. (2015) · EURASIP Journal on Image and Video Processing · doi:10.1186/s13640-015-0062-9 · Cited by 78 · cited 1×
“Road area extraction [1]–[6] can generate pixel-level labeling of roads, while road centerline extraction [7], [8] aims at detecting skeletons of a road.”
BackgroundRoad Centerline Extraction via Semisupervised Segmentation and Multidirection Nonmaximum Suppression
Cheng, G.-L., Zhu, F.-Y., Xiang, S., & Pan, C.-H. (2016) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2016.2524025 · Cited by 59 · cited 1×
“Since road centerline can be easily obtained from road areas using algorithms such as morphological thinning [10], this letter focuses on road area extraction from high-resolution remote sensing images.”
CNN based suburban building detection using monocular high resolution Google Earth images
Zhang, Q.-C., Wang, Y.-H., Liu, Q.-J., Liu, X., & Wang, W. (2016) · IEEE International Geoscience and Remote Sensing Symposium · doi:10.1109/igarss.2016.7729166 · Cited by 52 · see citing works
Self-citationLiu, B., Wu, H.-Y., Wang, Y.-D., & Liu, W.-M. (2015) · PLoS ONE · doi:10.1371/journal.pone.0138071 · Cited by 43 · cited 1×
“Road area extraction [1]–[6] can generate pixel-level labeling of roads, while road centerline extraction [7], [8] aims at detecting skeletons of a road.”
BackgroundSelf-citationUrban road extraction via graph cuts based probability propagation
Cheng, G.-L., Wang, Y., Gong, Y., Zhu, F.-Y., & Pan, C.-H. (2014) · International Conference on Information Photonics · doi:10.1109/icip.2014.7026027 · Cited by 29
Self-citationA CNN based functional zone classification method for aerial images
Zhang, Z.-X., Wang, Y.-H., Liu, Q., Li, L., & Wang, P. (2016) · IEEE International Geoscience and Remote Sensing Symposium · doi:10.1109/igarss.2016.7730419 · Cited by 21 · cited 1× · see citing works
“lems of interpretation and understanding of remote sensing data [2], [5], [15]–[18].”
BackgroundSelf-citation
Flagged first, then by citations
5 of the 27 references couldn’t be matched to a known paper.
Research works printed but not linked: 3
- [13][13] B. Zhou, A. Lapedriza, J. Xiao, A. Torralba, and A. Oliva, 'Learning deep features for scene recognition using places database,' in NIPS , 2014, pp. 487-495. -
- [15][15] V. Mnih and G. E. Hinton, 'Learning to label aerial images from noisy data,' in ICML , 2012, pp. 567-574. -
- [26][26] M. Ehrig and J. Euzenat, 'Relaxed precision and recall for ontology matching,' in Workshop on Integrating ontology , 2005, pp. 25-32.
Cited by
Sorted by citations
Image segmentation using deep learning: A survey
Minaee, S., Boykov, Y. Y., Porikli, F., Plaza, A. J., Kehtarnavaz, N., & Terzopoulos, D. (2021) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2021.3059968 · Cited by 3,796 · see citing works
“[49] developed a road segmentation algorithm based on U-Net, and Cicek et al.”
MethodKvasir-SEG: A Segmented Polyp Dataset
Jha, D., Smedsrud, P., Riegler, M., Halvorsen, P., de Lange, T., Johansen, D., & Johansen, H. (2019) · Conference on Multimedia Modeling · doi:10.1007/978-3-030-37734-2_37 · Cited by 2,145 · see citing works
“conducted initial investigations using two dierent methods. The rst method is based on the ecient FCM [6] unsupervised clustering algorithm. The second method is based on the deep-learning ResUNet [28] architecture, utilizing the advantage of the residual block. When using basic CNN architectures to predict outcomes i…”
MethodInfluentialResUNet-a: A deep learning framework for semantic segmentation of remotely sensed data
Diakogiannis, F. I., Waldner, F., Caccetta, P. A., & Wu, C. (2020) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2020.01.013 · Cited by 2,210 · see citing works
PraNet: Parallel Reverse Attention Network for Polyp Segmentation
Fan, D.-P., Ji, G.-P., Zhou, T., Chen, G., Fu, H., Shen, J.-B., & Shao, L. (2020) · International Conference on Medical Image Computing and Computer-Assisted Intervention · doi:10.1007/978-3-030-59725-2_26 · Cited by 2,003 · see citing works
TransFuse: Fusing Transformers and CNNs for Medical Image Segmentation
Zhang, Y., Liu, H., & Hu, Q. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-87193-2_2 · Cited by 1,652 · see citing works
BASNet: Boundary-Aware Salient Object Detection
Qin, X., Zhang, Z., Huang, C., Gao, C., Dehghan, M., & Jägersand, M. (2019) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2019.00766 · Cited by 1,691 · see citing works
“In our experiments, we set the slack parameter ρ to 3 similar to the previous studies [44, 58, 77].”
ResultSelf-citationResUNet++: An Advanced Architecture for Medical Image Segmentation
Jha, D., Smedsrud, P., Riegler, M., Johansen, D., de Lange, T., Halvorsen, P., & Johansen, H. (2019) · IEEE International Symposium on Multimedia · doi:10.1109/ism46123.2019.00049 · Cited by 1,410 · see citing works
“There are various modification and extension based on U-Net architecture [4], [6], [17], [19]–[22] to achieve better segmentation results on both natural images and biomedical images.”
BackgroundMethodInfluentialAlom, M. Z., Hasan, M. M., Yakopcic, C., Taha, T. M., & Asari, V. K. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1802.06955 · Cited by 909 · see citing works
“However, U-Net is not only limited to the applications in the domain of medical imaging, nowadays this model is massively applied for computer vision tasks as well [30, 31].”
MethodPlug-and-Play Image Restoration With Deep Denoiser Prior
Zhang, K., Li, Y., Zuo, W., Lei Zhang, A., Gool, L. V., & Timofte, R. (2021) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2021.3088914 · Cited by 1,152 · see citing works
“Actually, the similar idea of combining U-Net and ResNet can also be found in other works such as [61], [62].”
ResultTransBTS: Multimodal Brain Tumor Segmentation Using Transformer
Wang, W., Chen, C., Ding, M., Li, J., Yu, H., & Zha, S. (2021) · International Conference on Medical Image Computing and Computer-Assisted Intervention · doi:10.1007/978-3-030-87193-2_11 · Cited by 1,278 · see citing works
“as U-Net++ [21] and Res-UNet [20] further improve the performance for image segmentation.”
A survey on deep learning techniques for image and video semantic segmentation
García-García, A., Orts‐Escolano, S., Oprea, S., Villena-Martínez, V., Martínez-González, P., & García‐Rodríguez, J. (2018) · Applied Soft Computing · doi:10.1016/j.asoc.2018.05.018 · Cited by 2,488 · see citing works
Medical Image Segmentation Review: The Success of U-Net
Azad, R., Aghdam, E. K., Rauland, A., Jia, Y., Avval, A. H., Bozorgpour, A., Karimijafarbigloo, S., Cohen, J., Adeli, E., & Merhof, D. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2024.3435571 · Cited by 1,069 · see citing works
“Residual U-Net [173], even with the Residual enhancements, is no exception to this rule.”
BackgroundMethodUNeXt: MLP-based Rapid Medical Image Segmentation Network
Valanarasu, J. M. J., & Patel, V. M. (2022) · International Conference on Medical Image Computing and Computer-Assisted Intervention · doi:10.48550/arxiv.2203.04967 · Cited by 1,075
“In particular, we compare with convolutional baselines like UNet [17], UNet++ [29] and ResUNet [28].”
MethodDS-TransUNet: Dual Swin Transformer U-Net for Medical Image Segmentation
Lin, A., Chen, B., Xu, J., Zhang, Z., Lu, G., & Zhang, D. D. (2022) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2022.3178991 · Cited by 905 · see citing works
Self-citationCOVID-CT-Dataset: A CT Scan Dataset about COVID-19Preprint
Yang, X., Zhao, J.-Y., Zhang, Y.-C., He, X.-H., & Xie, P.-T. (2020) · arXiv.org · doi:10.48550/arxiv.2003.13865 · Cited by 926 · see citing works
“Using the labeled lung masks in COVID-CT and COVID-Seg, we develop a lung segmentation model based on residual U-Net (Zhang et al., 2018).”
MethodZhou, L., Zhang, C., & Wu, M. (2018) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2018.00034 · Cited by 996 · see citing works
“Most of these methods can be seperated into three categories: generating pixel-level labeling of roads [1, 2], detecting skeletons of roads [3, 4] and a combination of both [5, 6].”
MethodDoubleU-Net: A Deep Convolutional Neural Network for Medical Image Segmentation
Jha, D., Riegler, M., Johansen, D., Halvorsen, P., & Johansen, H. D. (2020) · Proceedings - IEEE Symposium on Computer-Based Medical Systems · doi:10.1109/cbms49503.2020.00111 · Cited by 973 · see citing works
“[15] proposed Deep Residual U-Net, which uses residual connections better output segmentation map.”
Recurrent residual U-Net for medical image segmentation
Alom, M. Z., Yakopcic, C., Hasan, M., Taha, T. M., & Asari, V. K. (2019) · Journal of medical imaging · doi:10.1117/1.jmi.6.1.014006 · Cited by 867 · see citing works
“The proposed RU-Net and R2U-Net architectures are designed to have the same number of network parameters, when compared to U-Net and ResU-Net, and the RU-Net and R2U-Net models show better performance on segmentation tasks.”
MethodInfluentialA review of deep learning methods for semantic segmentation of remote sensing imagery
Yuan, X., Shi, J., & Gu, L. (2020) · Expert Systems with Applications · doi:10.1016/j.eswa.2020.114417 · Cited by 780 · see citing works
“Xu, Du, Zhang, and Zhang (2018) proposed a Random Patches Network that takes image patches as the convolution kernels, which requires no training.”
BackgroundFAT-Net: Feature adaptive transformers for automated skin lesion segmentation
Wu, H., Chen, S., Chen, G., Wang, W., Lei, B., & Wen, Z. (2021) · Medical Image Analysis · doi:10.1016/j.media.2021.102327 · Cited by 605 · see citing works
A global inventory of photovoltaic solar energy generating units
Kruitwagen, L., Story, K., Friedrich, J., Byers, L., Skillman, S., & Hepburn, C. (2021) · Nature · doi:10.1038/s41586-021-03957-7 · Cited by 476 · see citing works
DCSAU-Net: A deeper and more compact split-attention U-Net for medical image segmentation
Xu, Q., Ma, Z., He, N., & Duan, W. (2023) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2023.106626 · Cited by 476 · see citing works
“The VGGNet [39] and typical residual structures [23] have been applied in many previous semantic segmentation networks, such as DoubleUnet [22] and ResUnet [40].”
MethodShallow Attention Network for Polyp Segmentation
Wei, J., Hu, Y., Zhang, R., Li, Z., Zhou, S., & Cui, S. (2021) · International Conference on Medical Image Computing and Computer-Assisted Intervention · doi:10.1007/978-3-030-87193-2_66 · Cited by 447 · see citing works
“Besides, six state-of-the-art methods are used for comparison, namely U-Net [15], U-Net++ [25], ResUNet [23], ResUNet++ [11], SFA [6] and PraNet [5].”
BackgroundMethodVali, A., Comai, S., & Matteucci, M. (2020) · Remote Sensing · doi:10.3390/rs12152495 · Cited by 479 · see citing works
“In the context of remote sensing, U-Net has shown very promising results in extracting buildings [127,128], roads [129,130], clouds [131,132], and to classify other land covers [133–135] using high resolution MSI data.”
BackgroundTolan, J. M., Yang, H.-I., Nosarzewski, B., Couairon, G., Vo, H. V., Brandt, J., Spore, J., Majumdar, S., Haziza, D., Vamaraju, J., et al. (2023) · Remote Sensing of Environment · doi:10.1016/j.rse.2023.113888 · Cited by 418 · see citing works
“We utilized a ResUNet-18 architecture for our baseline (Zhang et al., 2017), which is an encoder-decoder architecture predicting a N × N canopy height map from a 3 × N × N RGB image, with N = 256.”
MethodA cloud detection algorithm for satellite imagery based on deep learning
Jeppesen, J. H., Jacobsen, R. H., Inceoglu, F., & Toftegaard, T. S. (2019) · Remote Sensing of Environment · doi:10.1016/j.rse.2019.03.039 · Cited by 402 · see citing works
Xu, Y., Quan, R., Xu, W., Huang, Y., Chen, X., & Liu, F. (2024) · Bioengineering · doi:10.3390/bioengineering11101034 · Cited by 350 · see citing works
Deep learning for topology optimization of 2D metamaterials
Kollmann, H. T., Abueidda, D., Koric, S., Guleryuz, E., & Sobh, N. (2020) · Materials & Design · doi:10.1016/j.matdes.2020.109098 · Cited by 343 · see citing works
CaraNet: context axial reverse attention network for segmentation of small medical objects
Lou, A., Guan, S., Ko, H., & Loew, M. (2021) · Journal of Medical Imaging · doi:10.1117/1.jmi.10.1.014005 · Cited by 324 · see citing works
“We compare our CaraNet with six state-of-the-art medical image segmentation methods: UNet [1], U-Net++ [2], ResUNetmod [15], ResUNet++ [3], SFA [16] and PraNet [4].”
MethodJha, D., Smedsrud, P. H., Johansen, D., de Lange, T., Johansen, H. D., Halvorsen, P., & Riegler, M. A. (2021) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2021.3049304 · Cited by 345 · see citing works
“In our previous work, we have showed that ResUNet++ outperforms the SOTA UNet [35] and ResUNet [34] models trained on Kvasir-SEG and CVC-ClinicDB dataset [1].”
MethodCS 2 -Net: Deep learning segmentation of curvilinear structures in medical imaging
Mou, L., Zhao, Y., Fu, H., Liu, Y., Cheng, J. T., Zheng, Y., Su, P., Yang, J., Chen, L., Frangi, A. F., et al. (2020) · Medical Image Analysis · doi:10.1016/j.media.2020.101874 · Cited by 441 · see citing works
“, 2015), Deep ResUNet (Zhang et al., 2018), U-Net++ (Zhou et al.”
InfluentialINet: Convolutional Networks for Biomedical Image Segmentation
Weng, W., & Zhu, X. (2021) · IEEE Access · doi:10.1109/access.2021.3053408 · Cited by 528 · see citing works
“Compared to the commonly used baseline model, UNet, the proposed INet has additional residual shortcuts, and therefore the learning task of the optimizer becomes easier [39] (We denote INet without customized residual short-cuts and the Conv-index as Plain-INet).”
MethodROSE: A Retinal OCT-Angiography Vessel Segmentation Dataset and New Model
Ma, Y., Hao, H., Xie, J.-Y., Fu, H., Zhang, J., Yang, J., Wang, Z., Liu, J., Zheng, Y., & Zhao, Y. (2020) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2020.3042802 · Cited by 309 · see citing works
“[25] modified ResU-Net [26] by introducing a weighted attention mechanism for high-quality retinal vessel segmentation.”
BackgroundMethodInfluentialReal-Time Polyp Detection, Localization and Segmentation in Colonoscopy Using Deep Learning
Jha, D., Ali, S., Tomar, N. K., Johansen, H. D., Johansen, D., Rittscher, J., Riegler, M. A., & Halvorsen, P. (2021) · IEEE Access · doi:10.1109/access.2021.3063716 · Cited by 409 · see citing works
“ResUNet [62] integrates the power of both UNet and residual neural network.”
MethodMSRF-Net: A Multi-Scale Residual Fusion Network for Biomedical Image Segmentation
Srivastava, A., Jha, D., Chanda, S., Pal, U., Johansen, H., Johansen, D., Riegler, M. A., Ali, S., & Halvorsen, P. (2021) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2021.3138024 · Cited by 329 · see citing works
“We report a mIoU of 0.9043 ± 0.1009 and a recall of 0.9567 ± 0.0620, which is 1.44% improvement in mIoU and 2.82% improvement in recall over SOTA combination of ResUNet++ and conditional random field [57] and UACANet-S [35], respectively.”
MethodInfluentialA Global Context-aware and Batch-independent Network for road extraction from VHR satellite imagery
Zhu, Q., Zhang, Y., Wang, L., Zhong, Y., Guan, Q., Lu, X., Zhang, L., & Li, D. (2021) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2021.03.016 · Cited by 300 · see citing works
Breast mass segmentation in ultrasound with selective kernel U-Net convolutional neural network
Byra, M., Jarosik, P., Szubert, A., Galperin, M. Y., Ojeda‐Fournier, H., Olson, L. K., O'Boyle, M. K., Comstock, C., & André, M. P. (2020) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2020.102027 · Cited by 328 · see citing works
CS-Net: Channel and Spatial Attention Network for Curvilinear Structure Segmentation
Mou, L., Zhao, Y., Chen, L., Cheng, J., Gu, Z.-W., Hao, H., Qi, H., Zheng, Y., Frangi, A. F., & Liu, J. (2019) · International Conference on Medical Image Computing and Computer-Assisted Intervention · doi:10.1007/978-3-030-32239-7_80 · Cited by 296 · see citing works
Cobb Angle Measurement of Spine from X-Ray Images Using Convolutional Neural Network
Horng, M.-H., Kuok, C.-P., Fu, M.-J., Lin, C.-J., & Sun, Y.-N. (2019) · Comput. Math. Methods Medicine · doi:10.1155/2019/6357171 · Cited by 296 · see citing works
“-ese results reveal that the performance of our proposed work is very close to the one in [24] and should be better than the abovementioned methods [21–23].”
MethodResultSwinBTS: A Method for 3D Multimodal Brain Tumor Segmentation Using Swin Transformer
Jiang, Y., Zhang, Y., Lin, X., Dong, J.-K., Cheng, T., & Liang, J. (2022) · Brain Science · doi:10.3390/brainsci12060797 · Cited by 291 · see citing works
de Bem, P. P., Júnior, O. A. D. C., Guimarães, R. F., & Gomes, R. A. T. (2020) · Remote Sensing · doi:10.3390/rs12060901 · Cited by 299 · see citing works
“This research used three different DL architectures available in the literature: U-Net [79], SharpMask [80], and ResUnet [81].”
MethodAbdollahi, A., Pradhan, B., Shukla, N., Chakraborty, S., & Alamri, A. M. (2020) · Remote Sensing · doi:10.3390/rs12091444 · Cited by 292 · see citing works
“[60] developed a deep residual U-net model similar to a U-net architecture for road semantic segmentation from high-resolution remote sensing imagery.”
MethodRoad Extraction from High-Resolution Remote Sensing Imagery Using Deep Learning
Xu, Y.-Y., Xie, Z., Feng, Y., & Chen, Z.-L. (2018) · Remote Sensing · doi:10.3390/rs10091461 · Cited by 245 · see citing works
“Zhang et al. combined deep residual networks (ResNet) [32] and U-Net [33], which allow for networks to be designed with fewer parameters, but obtain better results [4].”
BackgroundResultFast Camouflaged Object Detection via Edge-based Reversible Re-calibration Network
Ji, G.-P., Zhu, L., Zhuge, M.-C., & Fu, K.-R. (2021) · Pattern Recognition · doi:10.1016/j.patcog.2021.108414 · Cited by 233 · see citing works
“Note that “ † ” represents evaluation scores from [73] and “N/A” means the result is not available. tion methods: UNet [67], UNet++ [22], ResUNet-mod [75], ResUNet++ [73], SFA [72] and PraNet [13].”
MethodCoANet: Connectivity Attention Network for Road Extraction From Satellite Imagery
Mei, J., Li, R., Gao, W., & Cheng, M. (2021) · IEEE Transactions on Image Processing · doi:10.1109/tip.2021.3117076 · Cited by 237 · see citing works
“[22] propose a semantic segmentation neural network called ResUnet, which is combined with residual learning and U-Net for road area extraction.”
BackgroundMethodImproved Road Connectivity by Joint Learning of Orientation and Segmentation
Batra, A., Singh, S., Pang, G., Basu, S., Jawahar, C. V., & Paluri, M. (2019) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2019.01063 · Cited by 244 · see citing works
An RDAU-NET model for lesion segmentation in breast ultrasound images
Zhuang, Z., Li, N., Raj, A. N. J., Mahesh, V. G. V., & Qiu, S. (2019) · PLoS ONE · doi:10.1371/journal.pone.0221535 · Cited by 240 · see citing works
FANet: A Feedback Attention Network for Improved Biomedical Image Segmentation
Tomar, N. K., Jha, D., Riegler, M. A., Johansen, H. D., Johansen, D., Rittscher, J., Halvorsen, P., & Ali, S. (2022) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2022.3159394 · Cited by 260 · see citing works
Left-Ventricle Quantification Using Residual U-Net
Kerfoot, E., Clough, J. R., Öksüz, I., Lee, J., King, A., & Schnabel, J. (2018) · STACOM@MICCAI · doi:10.1007/978-3-030-12029-0_40 · Cited by 221 · see citing works
PoreFlow-Net: A 3D convolutional neural network to predict fluid flow through porous media
Santos, J. E., Xu, D., Jo, H., Landry, C., Prodanović, M., & Pyrcz, M. (2020) · Advances in Water Resources · doi:10.1016/j.advwatres.2020.103539 · Cited by 220 · see citing works
FCN-Transformer Feature Fusion for Polyp Segmentation
Sanderson, E., & Matuszewski, B. (2022) · Annual Conference on Medical Image Understanding and Analysis · doi:10.1007/978-3-031-12053-4_65 · Cited by 218 · see citing works
“U-Net [25] 0.7821 0.8141 0.7241 0.8450 0.8464 0.7730 0.8496 0.8796 ResUNet [38] 0.5133 0.3792 0.5937 0.5968 0.5221 0.4120 0.6151 0.5895 ResUNet++ [17] 0.8074 0.7231 0.8991 0.7874 0.5211 0.4126 0.5633 0.5693 MSRF-Net [28] 0.8586 0.7906 0.8933 0.8774 0.9198 0.8729 0.9222 0.9308 PraNet [8] 0.9011…”
BackgroundMethodInfluentialEdge U-Net: Brain Tumor Segmentation using MRI based on Deep U-Net Model with boundary information
Allah, A. M. G., Sarhan, A. M., & Elshennawy, N. M. (2022) · Expert systems with applications · doi:10.1016/j.eswa.2022.118833 · Cited by 215 · see citing works
Yi, Y., Zhang, Z., Zhang, W., Zhang, C., Li, W., & Zhao, T. (2019) · Remote Sensing · doi:10.3390/rs11151774 · Cited by 229 · see citing works
“Although some combined approaches of the U-Net with the deep residual network have been reported in recent studies [51,57,58], significant differences can be found between their network architectures and that of ours.”
BackgroundSelf-citationStructure and Illumination Constrained GAN for Medical Image Enhancement
Ma, Y., Liu, J., Liu, Y., Fu, H., Hu, Y., Cheng, J. T., Qi, H., Wu, Y., Zhang, J., & Zhao, Y. (2021) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2021.3101937 · Cited by 225 · see citing works
Road Detection and Centerline Extraction Via Deep Recurrent Convolutional Neural Network U-Net
Yang, X., Li, X., Ye, Y., Lau, R. Y. K., Zhang, X., & Huang, X. (2019) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2019.2912301 · Cited by 227 · see citing works
“Although spurs are rarely seen, discontinuities and false positive parts still appear in the results produced by ResUNet.”
BackgroundMethodInfluentialLandslide detection using deep learning and object-based image analysis
Ghorbanzadeh, O., Shahabi, H., Crivellari, A., Homayouni, S., Blaschke, T., & Ghamisi, P. (2022) · Landslides · doi:10.1007/s10346-021-01843-x · Cited by 205 · see citing works
“Each has a batch normalization layer and a ReLU activation layer in advance (Liu et al. 2020; Zhang et al. 2018).”
BackgroundMethodInfluentialTopology optimization of 2D structures with nonlinearities using deep learning
Abueidda, D., Korić, S., & Sobh, N. (2020) · Computers & Structures · doi:10.1016/j.compstruc.2020.106283 · Cited by 224 · see citing works
Landslide4Sense: Reference Benchmark Data and Deep Learning Models for Landslide Detection
Ghorbanzadeh, O., Xu, Y., Ghamisi, P., Kopp, M. K., & Kreil, D. P. (2022) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2022.3215209 · Cited by 202 · see citing works
“This variant of the U-Net features structures based on residual learning blocks that are replaced with the plain convolution layers [86].”
BackgroundRoad Segmentation in SAR Satellite Images With Deep Fully Convolutional Neural Networks
Henry, C., Azimi, S., & Merkle, N. (2018) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2018.2864342 · Cited by 202 · see citing works
“This letter presents the evaluation of three FCNNs for road segmentation in high-resolution SAR satellite images: FCN-8s [4], Deep Residual U-Net [5], and DeepLabv3+ [9].”
BackgroundMethodLin, J.-W., Lin, J., Lu, C., Chen, H., Lin, H., Zhao, B.-C., Shi, Z.-W., Qiu, B., Pan, X., Xu, Z.-Y., et al. (2022) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2023.3250474 · Cited by 200 · see citing works
“We compare our proposed CKD-TransBTS model with several SOTA models, including five CNN-based models ( VNet [45], ResUNet [46], UNet++ [47] AttentionUNet [48] and DynUNet [20]) and six transformer-based models (Trans-BTS [28], TransUNet [27], UNETR [7], VTNet [30], Seg-TransVAE [49] and Swin UNETR [32]).”
MethodTang, Y.-C., Huang, Z.-F., Chen, Z., Chen, M.-Y., Zhou, H., Zhang, H.-X., & Sun, J.-B. (2023) · Engineering structures · doi:10.1016/j.engstruct.2022.115158 · Cited by 198 · see citing works
TransDeepLab: Convolution-Free Transformer-based DeepLab v3+ for Medical Image Segmentation
Azad, R., Heidari, M., Shariatnia, M., Aghdam, E. K., Karimijafarbigloo, S., Adeli, E., & Merhof, D. (2022) · PRIME@MICCAI · doi:10.48550/arxiv.2208.00713 · Cited by 197
“Following this technical route, many U-Net variants such as U-Net++ [37] and Res-UNet [36] have emerged to improve the segmentation performance.”
MethodInfluentialRoad extraction in remote sensing data: A survey
Chen, Z., Deng, L., Luo, Y., Li, D., Marcato, J., Gonçalves, W. N., Nurunnabi, A., Li, J., Wang, C., & Li, D. (2022) · International Journal of Applied Earth Observation and Geoinformation · doi:10.1016/j.jag.2022.102833 · Cited by 186 · see citing works
Sparse Dynamic Volume TransUNet with multi-level edge fusion for brain tumor segmentation
Zhu, Z.-Q., Sun, M.-W., Qi, G.-Q., Li, Y., Gao, X.-B., & Liu, Y. (2024) · Comput. Biol. Medicine · doi:10.1016/j.compbiomed.2024.108284 · Cited by 195 · see citing works
Highly Accurate Dichotomous Image Segmentation
Qin, X., Dai, H., Hu, X.-B., Fan, D.-P., Shao, L., & Gool, L. V. (2022) · European Conference on Computer Vision · doi:10.48550/arxiv.2203.03041 · Cited by 192
“For example, IoU and F-measure mainly rely on the object components with large areas while neglecting the fine details with relatively small areas.”
BackgroundInfluentialA multi-centre polyp detection and segmentation dataset for generalisability assessment
Ali, S., Jha, D., Ghatwary, N., Realdon, S., Cannizzaro, R., Salem, O. E., Lamarque, D., Daul, C., Riegler, M., Ånonsen, K., et al. (2021) · Scientific Data · doi:10.1038/s41597-023-01981-y · Cited by 192 · see citing works
R oot P ainter : deep learning segmentation of biological images with corrective annotation
Smith, A. G., Han, E., Petersen, J., Olsen, N. A. F., Giese, C., Athmann, M., Dresbøll, D. B., & Thorup‐Kristensen, K. (2022) · New Phytologist · doi:10.1111/nph.18387 · Cited by 213 · see citing works
“Roots Dataset We downloaded the 867 grid counted images and manual root length measurements from (67) which were made available as part of the evaluation of U-Net for segmenting roots in soil (40) and originally captured as part of a study on chicory drought stress (4) using a 4 m rhizobox laboratory described in (68).”
MethodInfluentialCrackFormer Network for Pavement Crack Segmentation
Liu, H., Yang, J., Miao, X., Mertz, C., & Kong, H. (2023) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2023.3266776 · Cited by 201 · see citing works
“example, UNet [20], [21] and FusionNet [22] usually for medical images segmentation can be used to pixel-level crack”
MethodZhang, P.-B., Ke, Y., Zhang, Z., Wang, M., Li, P., & Zhang, S. (2018) · Italian National Conference on Sensors · doi:10.3390/s18113717 · Cited by 187 · see citing works
“It combines low level features with detailed spatial information with high level features with semantic information to improve segmentation accuracy, and has attained promising results in one-class segmentation tasks such as biomedical image segmentation [30], road network extraction from aerial imagery [31,32], build…”
BackgroundSelf-citationUNet-based model for crack detection integrating visual explanations
Liu, F., & Wang, L. (2022) · Construction and Building Materials · doi:10.1016/j.conbuildmat.2021.126265 · Cited by 194 · see citing works
Abdollahi, A., Pradhan, B., & Alamri, A. M. (2020) · IEEE Access · doi:10.1109/access.2020.3026658 · Cited by 196 · see citing works
MSU-Net: Multi-Scale U-Net for 2D Medical Image Segmentation
Su, R. Z., Zhang, D., Liu, J., & Cheng, C. (2021) · Frontiers in Genetics · doi:10.3389/fgene.2021.639930 · Cited by 171 · see citing works
“Zhang et al. (2018) proposed a semantic segmentation neural network based on residual learning and U-Net for road area extraction.”
BackgroundHSNet: A hybrid semantic network for polyp segmentation
Zhang, W.-C., Fu, C., Zheng, Y., Zhang, F., Zhao, Y., & Sham, C.-W. (2022) · Comput. Biol. Medicine · doi:10.1016/j.compbiomed.2022.106173 · Cited by 168 · see citing works
Wang, Q., Huang, W. F., Xiong, Z., & Li, X. (2020) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2020.3042276 · Cited by 188 · see citing works
“BENEFITING from the remote sensing imaging equipments and technologies, in recent years, many semanticlevel tasks of remote sensing images have developed rapidly, such as object detection [1], image retrieval [2], image captioning [3] [4], road extraction [5] and the others.”
BackgroundLi, C., Tan, Y., Chen, W., Luo, X., He, Y., Gao, Y., & Li, F. (2020) · Computers & Graphics · doi:10.1016/j.cag.2020.05.003 · Cited by 178 · see citing works
Fully Convolutional Network for Automatic Road Extraction from Satellite Imagery
Buslaev, A. P., Seferbekov, S., Iglovikov, V., & Shvets, A. A. (2018) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2018.00035 · Cited by 186 · see citing works
“This type of network architecture proven themselves in binary image segmentation competitions for satellite image analyses [6, 7, 8, 15, 16] and other applications [13, 12].”
BackgroundMulti-Scale and Multi-Task Deep Learning Framework for Automatic Road Extraction
Lu, X.-Y., Zhong, Y.-F., Zheng, Z., Liu, Y., Zhao, J., Ma, A., & Yang, J. (2019) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2019.2926397 · Cited by 163 · see citing works
“In recent years, various methods have been applied to road extraction, which can be divided into two types: road detection methods [6]–[8] and road centerline extraction methods [9]–[12].”
BackgroundMethodInfluentialZhou, G., Chen, W., Gui, Q., Li, X., & Wang, L. (2021) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2021.3128033 · Cited by 176 · see citing works
“Furthermore, these traditional approaches, which involve mathematical morphology and texture analysis, are proving less effective for handling multiscale roads [13]–[16].”
BackgroundFrom W-Net to CDGAN: Bitemporal Change Detection via Deep Learning Techniques
Hou, B., Liu, Q.-J., Wang, H., & Wang, Y.-H. (2020) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2019.2948659 · Cited by 159 · see citing works
“Deep learning techniques have gained wide success in many vision tasks in recent years[27], [28], [29].”
BackgroundSelf-citationJiao, J., Zhou, J., Li, X., Xia, M., Huang, Y., Huang, L., Wang, N., Zhang, X., Zhou, S., Wang, Y., et al. (2024) · Medical Image Analysis · doi:10.1016/j.media.2024.103202 · Cited by 119 · see citing works
“In the segmentation of Neck brachial plexus structure and Breast tumor, Unet, ResUnet, Seg-Former, and UperNet under-segment or over-segment due to their limited ability to resolve blurred edges.”
MethodInfluentialSelf-citationQi, K., Yang, H., Li, C., Liu, Z., Wang, M., Liu, Q., & Wang, S. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-32248-9_28 · Cited by 159 · see citing works
“ResUNet [16] 0.”
Self-citationHe, H., Yang, D., Wang, S., Wang, S., & Li, Y. (2019) · Remote Sensing · doi:10.3390/rs11091015 · Cited by 174 · see citing works
“As a classical Encoder-Decoder model, the U-net is widely used in medical and remote sensing imagery segmentation [15,20,22,30].”
MethodGhorbanzadeh, O., Crivellari, A., Ghamisi, P., Shahabi, H., & Blaschke, T. (2021) · Scientific Reports · doi:10.1038/s41598-021-94190-9 · Cited by 169 · see citing works
Bangaru, S. S., Wang, C., Zhou, X., & Hassan, M. (2022) · Automation in Construction · doi:10.1016/j.autcon.2022.104602 · Cited by 150 · see citing works
Sat2Graph: Road Graph Extraction through Graph-Tensor Encoding
He, S., Bastani, F., Jagwani, S., Alizadeh, M., Balakrishnan, H., Chawla, S., Elshrif, M., Madden, S., & Sadeghi, M. (2020) · European Conference on Computer Vision · doi:10.1007/978-3-030-58586-0_4 · Cited by 149 · see citing works
Müller, D., & Kramer, F. (2019) · BMC Medical Imaging · doi:10.1186/s12880-020-00543-7 · Cited by 149 · see citing works
Multi-Temporal SAR Data Large-Scale Crop Mapping Based on U-Net Model
Wei, S., Zhang, H., Wang, C., Wang, Y., & Xu, L. (2019) · Remote Sensing · doi:10.3390/rs11010068 · Cited by 148 · see citing works
Self-citationLesion-Aware Dynamic Kernel for Polyp Segmentation
Zhang, R., Lai, P., Wan, X., Fan, D., Gao, F., Wu, X.-J., & Li, G.-B. (2023) · International Conference on Medical Image Computing and Computer-Assisted Intervention · doi:10.1007/978-3-031-16437-8_10 · Cited by 146 · see citing works
Dense Dilated Network With Probability Regularized Walk for Vessel Detection
Mou, L., Chen, L., Cheng, J. T., Gu, Z., Zhao, Y., & Liu, J. (2019) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2019.2950051 · Cited by 164 · see citing works
“[65], we replace the original blocks in the UNet with ResNet [27] blocks to extract feature in our method.”
MethodLandslide Recognition by Deep Convolutional Neural Network and Change Detection
Shi, W., Zhang, M., Ke, H., Fang, X., Zhan, Z., & Chen, S. (2020) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2020.3015826 · Cited by 182 · see citing works
“Keeping this in mind and inspired by [42], we proposed an improved CNN with unpooling layers, as shown in Fig.”
MethodA review of remote sensing image segmentation by deep learning methods
Li, J., Cai, Y., Li, Q., Kou, M., & Zhang, T. (2024) · International Journal of Digital Earth · doi:10.1080/17538947.2024.2328827 · Cited by 131 · see citing works
MSCA-Net: Multi-scale contextual attention network for skin lesion segmentation
Sun, Y., Dai, D.-W., Zhang, Q.-N., Wang, Y.-Q., Xu, S.-Y., & Lian, C. (2023) · Pattern Recognition · doi:10.1016/j.patcog.2023.109524 · Cited by 142 · see citing works
Self-citationFully transformer network for skin lesion analysis
He, X.-Z., Tan, E.-L., Bi, H.-W., Zhang, X., Zhao, S., & Lei, B.-Y. (2022) · Medical Image Anal. · doi:10.1016/j.media.2022.102357 · Cited by 142 · see citing works
Kuras, A., Brell, M., Rizzi, J., & Burud, I. (2021) · Remote Sensing · doi:10.3390/rs13173393 · Cited by 150 · see citing works
“Niemeyer et al. [283] applied an RF classification framework with conditional random fields on lidar data to discriminate vegetation and buildings from each other. vegetation and artificial (roads) and natural ground (grass), respectively.”
BackgroundA Novel Deep Structure U-Net for Sea-Land Segmentation in Remote Sensing Images
Shamsolmoali, P., Zareapoor, M., Wang, R., Zhou, H., & Yang, J. (2019) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2019.2925841 · Cited by 159 · see citing works
“Somewhat surprisingly, our model even has better computation efficiency compared to DeepUNet [5] and RU-Net [37].”
MethodResultRoad Extraction Methods in High-Resolution Remote Sensing Images: A Comprehensive Review
Lian, R., Wang, W., Mustafa, N., & Huang, L. (2020) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2020.3023549 · Cited by 173 · see citing works
“On the basis of the different outputs of these methods, they can be divided into road segmentation and road centerline extraction [15].”
BackgroundMethodScatterNet: A convolutional neural network for cone‐beam CT intensity correction
Hansen, D., Landry, G., Kamp, F., Li, M.-L., Belka, C., Parodi, K., & Kurz, C. (2018) · Medical Physics (Lancaster) · doi:10.1002/mp.13175 · Cited by 135 · see citing works
“Compared with Zhang et al.30, we do not employ batch-normalization, as it would introduce an unwanted scaling of the scatter.”
MethodInfluentialPixel-wise regression using U-Net and its application on pansharpening
Yao, W., Zeng, Z., Lian, C., & Tang, H. (2018) · Neurocomputing · doi:10.1016/j.neucom.2018.05.103 · Cited by 133 · see citing works
“, 2018) and remote sensing image segmentation (Zhang et al., 2018).”
BackgroundZhou, Y., Huang, J., Wang, C., Song, L., & Yang, G. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.01928 · Cited by 145 · see citing works
“We compare XNet with supervised state-of-the-arts, including UNet [42], UNet++ [67], Att-UNet [38], HRNet-W18 [47], Res-UNet [63], U 2 -Net [40], UNet 3+ [21], SwinUnet [5] and nnUNet [23].”
MethodLi, M., Long, J., Stein, A., & Wang, X.-Q. (2023) · Isprs Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2023.04.019 · Cited by 131 · see citing works
“…it with four existing methods for agricultural parcel delineation, corresponding to two single-task networks R2UNet (Zhang et al. 2021), ResUNet (Taravat et al. 2021; Zhang et al. 2018), and two multi-task networks, i. e., ResUNet-a (Waldner and Diakogiannis 2020) and BsiNet (Long et al. 2022).”
BackgroundMethod
- 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 › Engineering › Ocean Engineering › 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
