The DOI matches its Crossref record; 23 of the 27 references it cites were found in a registry or an index.
Road Extraction by Deep Residual U-Net
Open accessAbstract
Road extraction from aerial images has been a hot research topic in the field of remote sensing image analysis. In this letter, a semantic segmentation neural network, which combines the strengths of residual learning and U-Net, is proposed for road area extraction. The network is built with residual units and has similar architecture to that of U-Net. The benefits of this model are twofold: first, residual units ease training of deep networks. Second, the rich skip connections within the network could facilitate information propagation, allowing us to design networks with fewer parameters, however, better performance. We test our network on a public road data set and compare it with U-Net and other two state-of-the-art deep-learning-based road extraction methods. The proposed approach outperforms all the comparing methods, which demonstrates its superiority over recently developed state of the arts.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“In this study, we opt for a deep residual U-Net [15], [44], which has already been successfully used for retinal OCT images.”
From Interactive Deep Learning-Based Retinal OCT Layer Segmentation Refinement by Regressing Translation Maps (2024) · cites this paper as [44]
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · cited 5×
“This somehow shares similar idea to that of residual neural network [21].”
BackgroundMethodResultInfluentialVery Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1409.1556 · Cited by 114,148 · cited 1×
“Recently, lots of works have suggested that a deeper network would have better performance [19], [20].”
BackgroundU-Net: Convolutional Networks for Biomedical Image Segmentation
Ronneberger, O., Fischer, P., & Brox, T. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-24574-4_28 · Cited by 99,404 · cited 7×
“1) U-Net: In semantic segmentation, to get a finer result, it is very important to use low-level details, while retaining high-level semantic information [23], [24].”
BackgroundMethodInfluentialFaster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2577031 · Cited by 73,472 · cited 1×
“of-the-art performance on a variety of computer vision tasks, such as scene recognition [13] and object detection [14].”
BackgroundFaster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2015) · arXiv · doi:10.48550/arxiv.1506.01497 · Cited by 70,812
Going deeper with convolutions
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298594 · Cited by 48,562 · cited 1×
“Recently, lots of works have suggested that a deeper network would have better performance [19], [20].”
BackgroundFully convolutional networks for semantic segmentation
Long, J., Shelhamer, E., & Darrell, T. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298965 · Cited by 38,834 · cited 3×
“One way to solve this problem is employing a pretrained network and then finetuning it on the target data set, as done in [23].”
BackgroundMethodIdentity mappings in deep residual networks
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46493-0_38 · Cited by 10,741 · cited 2×
“[22] presented a detailed discussion on impacts of different combinations and suggested a full preactivation design as shown in Fig.”
BackgroundMethodDeep Learning for Remote Sensing Data: A Technical Tutorial on the State of the Art
Zhang, L., Zhang, L., & Du, B. (2016) · IEEE Geoscience and Remote Sensing Magazine · doi:10.1109/mgrs.2016.2540798 · Cited by 2,272
Learning to Detect Roads in High-Resolution Aerial Images
Mnih, V., & Hinton, G. E. (2010) · European Conference on Computer Vision · doi:10.1007/978-3-642-15567-3_16 · Cited by 681 · cited 11×
“To demonstrate the accuracy and efficiency of the proposed deep ResUnet, we test it on Massachusetts roads data set2 and compare it with three state of the art methods, including Mnih’s [2] method, Saito’s method [5], and U-Net [24].”
BackgroundMethodResultInfluential
Research works printed but not linked: 4
- zhou, 2014, Learning deep features for scene recognition using places database, Proc NIPS, 487
- mnih, 2012, Learning to label aerial images from noisy data, Proc ICML, 567
- ehrig, 2005, Relaxed precision and recall for ontology matching, Proc Workshop Integr Ontol, 25
- chollet, 2015, Keras
Cited by
Sorted by citations
Items 701–800 of 1,001
CPNet: A Context Preserver Convolutional Neural Network for Detecting Shadows in Single RGB Images
Mohajerani, S., & Saeedi, P. (2018) · IEEE International Workshop on Multimedia Signal Processing · doi:10.1109/mmsp.2018.8547080 · Cited by 21
“In contrast to the recent modified versions of the U-Net [10], [17], the CPNet utilizes the analogous features of the contracting path for two purposes: first, reconstruction of the contexts inside of each block of the expanding path and second, transferring these features to the next block.”
MethodDeep-Learning-Based Semantic Segmentation for Remote Sensing: A Bibliometric Literature Review
Hasan, K. R., Tuli, A., Khan, M., Kee, S.-H., Samad, M. A., & Nahid, A. A. (2024) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2023.3328315 · Cited by 21
“1 [5], [23], [36], [37], and [38] are the most cited papers in our data collection period.”
BackgroundMethodToward Accurate and Efficient Road Extraction by Leveraging the Characteristics of Road Shapes
Wang, C., Xu, R., Xu, S., Meng, W.-L., Wang, R.-S., Zhang, J.-G., & Zhang, X. (2023) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2023.3284478 · Cited by 21
“Zhang et al. [6] extended UNet by introducing the short-cut connections from ResNet [46] and built a method called ResUNet to extract roads.”
BackgroundMethodDual-Task Network for Road Extraction From High-Resolution Remote Sensing Images
Lin, Y., Jin, F., Wang, D., Wang, S., & Liu, X. (2023) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2023.3289217 · Cited by 26
“Forexample,theresidualmodule [15]isusedasthebasicunitofthenetwork[16]avoidingthe problemofnetworkdegradationduringdeepfeatureextraction.”
Road and Car Extraction Using UAV Images via Efficient Dual Contextual Parsing Network
Sun, Y., Shao, Z.-F., Cheng, G., Huang, X., & Wang, Z.-Y. (2022) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2022.3214246 · Cited by 21
“Zhang et al. [19] improved the U-net by combining residual learning to improve the generalization ability of the network model while reducing the number of parameters by multilayer jump connections.”
BackgroundLogavitool, G., Horanont, T., Thapa, A., Intarat, K., & Wuttiwong, K.-O. (2025) · PLoS ONE · doi:10.1371/journal.pone.0314535 · Cited by 20
HSMix: Hard and soft mixing data augmentation for medical image segmentation
Sun, D.-Y., Dornaika, F., & Barrena, N. (2024) · Information Fusion · doi:10.1016/j.inffus.2024.102741 · Cited by 20
“These variations include Attention U-Net [31], V-Net [32], and Residual U-Net [33], among others.”
Wang, Y., Zhang, Y., Zhang, L., Xu, Y., Feng, R., Cai, H., Xue, J., Zhao, Z., Guo, X., Wei, Y., et al. (2024) · Expert systems with applications · doi:10.1016/j.eswa.2024.124179 · Cited by 20
Self-citationFeng, Y., Deng, S., Lyu, J., Cai, J., Wei, M.-Q., & Qin, J. (2024) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2024.3445969 · Cited by 20
“The label correction module adopts the default setting of ResUNet [60] as the backbone structure.”
MM-UNet: A novel cross-attention mechanism between modules and scales for brain tumor segmentation
Lin, C.-W., & Chen, Z. (2024) · Engineering applications of artificial intelligence · doi:10.1016/j.engappai.2024.108591 · Cited by 20
CNNs for remote extraction of urban features: A survey-driven benchmarking
Neupane, B., Aryal, J., & Rajabifard, A. (2024) · Expert Systems with Applications · doi:10.1016/j.eswa.2024.124751 · Cited by 20
Swin-TransUper: Swin Transformer-based UperNet for medical image segmentation
Yin, J., Chen, Y., Li, C., Zheng, Z., Gu, Y., & Zhou, J. (2024) · Multimedia Tools and Applications · doi:10.1007/s11042-024-19009-x · Cited by 23
“Similarly, the Swin-TransUper model tends to be lightweight compared with Deeplabv3+ (Xception) [8], UperNet (ResNet50) [36], ResUNet [42], and UNet [29].”
Kaur, R., & Kaur, S. (2024) · Multimedia Tools and Applications · doi:10.1007/s11042-024-18895-5 · Cited by 21
“Popular among these are fully convolutional neural network (FCN) [22], U-Net [23], residual U-Net (ResU-Net) [24], attention U-Net (AU-Net) [25], recurrent neural network (RNN) [26], and region-based convolutional neural network (RCNN) [27].”
InfluentialFu, C., Zhou, Z., Feng, Y., & Weibel, R. (2023) · Cartography and Geographic Information Science · doi:10.1080/15230406.2023.2264757 · Cited by 19
“Feng et al. (2019) suggested that Residual U-Net (ResU-Net, Zhang et al., 2018) performs better than regular U-Net and GAN, while Courtial et al. (2022a) suggested that CycleGAN (Zhu et al., 2017) is better than U-Net and GAN-backed pix2pix model (Isola et al., 2017).”
BackgroundWhere does floating Sargassum in the East China Sea come from?
Qi, L., Cheng, P., Wang, M., Hu, C.-M., Xie, Y., & Mao, K. (2023) · Harmful Algae · doi:10.1016/j.hal.2023.102523 · Cited by 20
Pal, S. C., Toumpanakis, D., Wikström, J., Ahuja, C., Strand, R., & Dhara, A. (2023) · IEEE Transactions on Nanobioscience · doi:10.1109/tnb.2023.3298444 · Cited by 20
“In the comparison of network architectures presented in Table I, we evaluate our proposed network alongside U-Net and its variant models, namely Residual-U-Net [22], Attention-U-Net [23], and V-Net [24].”
MethodSound Demixing Challenge 2023 Music Demixing Track Technical Report: TFC-TDF-UNet v3
Kim, M., Lee, J. H., & Jung, S. (2023) · arXiv.org · doi:10.48550/arxiv.2306.09382 · Cited by 20
“• Change overall structure to a ResUnet[4]-like structure and add a TDF block[5] to each Residual Block.”
BackgroundHassanzadeh, T., Essam, D., & Sarker, R. A. (2023) · Applied Soft Computing · doi:10.1016/j.asoc.2023.110405 · Cited by 20
Silva, B., Oliveira, B., Morais, P., Buschle, L., Correia-Pinto, J., Lima, E., & Vilaça, J. (2022) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society · doi:10.1109/embc48229.2022.9871583 · Cited by 20
“Because of its effectiveness in segmenting medical images and its simplicity, this network has become the basis for several other variants tailored to different problems such as Residual U-Net [8], Dense U-Net [9], U-Net++ [10], and Dynamic U-Net (DynUNet) [11].”
BackgroundDeep learning synthesized pseudo-CT for MR High-Resolution Pediatric Cranial Bone Imaging (MR-HiPCB)
Boroojeni, P. E., Chen, Y.-S., Commean, P. K., Eldeniz, C., Skolnick, G., Merrill, C. M., Patel, K. B., & An, H. (2022) · Magnetic Resonance in Medicine · doi:10.1002/mrm.29356 · Cited by 20
Automatic Polyp Segmentation with Multiple Kernel Dilated Convolution Network
Tomar, N. K., Srivastava, A., Bagci, U., & Jha, D. (2022) · 2022 IEEE 35th International Symposium on Computer-Based Medical Systems (CBMS) · doi:10.1109/cbms55023.2022.00063 · Cited by 20
Maximum Entropy on Erroneous Predictions: Improving Model Calibration for Medical Image Segmentation
Larrazabal, A. J., Martínez, C. E., Dolz, J., & Ferrante, E. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-43898-1_27 · Cited by 10
“We benchmark our proposed method with two state-of-the-art DNN architectures (UNet [29] and ResUNet [39]) which were implemented using Tensorflow 2.”
MethodInfluentialAggregation-and-Attention Network for brain tumor segmentation
Lin, C.-W., Hong, Y., & Liu, J.-F. (2021) · BMC Medical Imaging · doi:10.1186/s12880-021-00639-8 · Cited by 20
DFENet: A Novel Dimension Fusion Edge Guided Network for Brain MRI Segmentation
Basak, H., Hussain, R., & Rana, A. (2021) · SN Computer Science · doi:10.1007/s42979-021-00835-x · Cited by 20
“Table 2 depicts this comparison of our results with UNet [32], SegNet [1], ResUNet [37], PSPNet [40], DeepLab V3 [8], XNet [30], 3D CNN+CRF [18], and Brain SegNet3D [15].”
BackgroundResultInfluentialApplication and Evaluation of a Deep Learning Architecture to Urban Tree Canopy Mapping
Wang, Z., Fan, C., & Xian, M. (2021) · Remote Sensing · doi:10.3390/rs13091749 · Cited by 20
“Numerous studies have made modifications to the U-net architecture in an attempt to improve the model performance [42,62,63].”
Ghosal, P., Chowdhury, T., Kumar, A., Bhadra, A. K., Chakraborty, J., & Nandi, D. (2020) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2020.105841 · Cited by 19
Deep Learning with Open Data for Desert Road Mapping
Stewart, C., Lazzarini, M., Luna, A., & Albani, S. (2020) · Remote Sensing · doi:10.3390/rs12142274 · Cited by 20
Cira, C.-I., Alcarria, R., Manso-Callejo, M.-Á., & Serradilla, F. (2020) · Remote Sensing · doi:10.3390/rs12050765 · Cited by 20
“Inspired by residual learning, the authors of [22] developed a deep-residual network similar to U-Net for the semantic segmentation of roads and tested it on a public roads dataset.”
MethodLane-Level Road Extraction from High-Resolution Optical Satellite Images
Dai, J.-G., Zhu, T., Zhang, Y., Ma, R.-C., & Li, W.-T. (2019) · Remote Sensing · doi:10.3390/rs11222672 · Cited by 20
“Since 2012, scholars have introduced deep learning methods into the field of road extraction [10–12].”
BackgroundMethodIge, A., Tomar, N. K., Aranuwa, F., Oriola, O., Akingbesote, A., Noor, M. H. M., Mazzara, M., & Aribisala, B. (2023) · IEEE Access · doi:10.1109/access.2023.3244789 · Cited by 20
“Similar to the results on the CVC-ClinicDB dataset, the proposed ConvSegNet model achieved a better Jac-card score of 0.7936 compared to the U-Net, ResU-Net, U-Net ++ , HardDNet-MSEG, FANet and UNeXt architectures, which recorded 0.7472, 0.6634, 0.7419, 0.7459, 0.6941 and 0.6284 respectively.”
MethodInfluentialCosta, T. B. D. S., Dias, F. M., Cárdenas, D. A. C., de Toledo, M. A. F., de Lima, D. M., Krieger, J. E., & Gutierrez, M. A. (2023) · IEEE Access · doi:10.1109/access.2023.3284458 · Cited by 21
“information propagation between layers [81].”
Cheng, H., Song, L., Ouyang, Y., Zeng, F., & Guo, Z.-D. (2026) · Aerospace Science and Technology · doi:10.1016/j.ast.2026.112351 · Cited by 19
SpaGAN: A spatially-aware generative adversarial network for building generalization in image maps
Zhou, Z., Fu, C., & Weibel, R. (2024) · International Journal of Applied Earth Observation and Geoinformation · doi:10.1016/j.jag.2024.104236 · Cited by 15
Frontiers in Intelligent Colonoscopy
Ji, G.-P., Liu, J., Xu, P., Barnes, N. M., Khan, F. S., Khan, S. H., & Fan, D.-P. (2026) · Machine Intelligence Research · doi:10.1007/s11633-025-1597-6 · Cited by 19
“This issue stems from the different categorical goals pursued by individual studies, such as identifying polyps from white-light and narrow-band imaging pairs [47], [111], images [106], or videos [59], evaluating polyp size [116], and recognising colonic diseases [112] or landmarks [119].”
Qi, H., Wang, W., Shi, Y., & Wang, X. (2024) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2024.106397 · Cited by 19
Fan, X., Lin, B., & Guo, Z. (2024) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2024.3383405 · Cited by 28
“Thereafter, Zhang et al. integrated residual learning and U-Net to design a road semantic segmentation neural networks called ResUNet [22] and achieved good results.”
MethodKhankeshizadeh, E., Mohammadzadeh, A., Mohsenifar, A., Moghimi, A., Pirasteh, S., Feng, S., Hu, K., & Li, J. (2024) · Remote Sensing Applications Society and Environment · doi:10.1016/j.rsase.2024.101336 · Cited by 19
TransDehaze: transformer-enhanced texture attention for end-to-end single image dehaze
Zhao, X., Xu, F., & Liu, Z. (2024) · The Visual Computer · doi:10.1007/s00371-024-03458-4 · Cited by 20
“Zhang [56] used U-Net in road extraction from aerial images by combining with residual learning.”
Selvaraj, J., & Jayanthy, A. K. (2024) · International Journal of Imaging Systems and Technology · doi:10.1002/ima.23034 · Cited by 20
“31 The MultiResU-Net (2019) architecture deviates from the conventional U-net design by utilizing MultiRes block and Res Path instead of convolutional blocks and skip connections.”
MethodInvestigations on extraction of buildings from RS imagery using deep learning models
Srivastava, V., Avudaiammal, R., & George, S. V. (2024) · International Journal of Remote Sensing · doi:10.1080/01431161.2023.2292016 · Cited by 19
“The prediction masks attained using UNet, SegNet, UNet ++ , ENRUNe and Dilated ResUNet models are shown in Figure 4.”
MethodInfluentialPancreatic cancer pathology image segmentation with channel and spatial long-range dependencies
Chen, Z., Liao, Y., Zhou, X., Yu, W., Zhang, G., Ge, Y., Tan, K., & Shi, K. (2023) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2023.107844 · Cited by 25
Mukasheva, A., Koishiyeva, D., Suimenbayeva, Z., Rakhmetulayeva, S., Bolshibayeva, A., & Sadikova, G. (2023) · Eastern-European Journal of Enterprise Technologies · doi:10.15587/1729-4061.2023.289044 · Cited by 19
Yang, B.-Y., Liu, Z.-Y., Duan, G.-F., & Tan, J.-R. (2023) · Pattern Recognition · doi:10.1016/j.patcog.2023.110073 · Cited by 19
Deep Learning based Systems for Crater Detection: A Review
Tewari, A., Prateek, K., Singh, A., & Khanna, N. (2023) · arXiv.org · doi:10.48550/arxiv.2310.07727 · Cited by 19
“[62] used the ResUnet [63] architecture, which also uses residual connections in U-Net to enhance the network’s learning ability.”
MethodInfluentialSwin-ResUNet+: An edge enhancement module for road extraction from remote sensing images
Jing, Y., Zhang, T., Liu, Z.-Y., Hou, Y., & Sun, C. (2023) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2023.103807 · Cited by 19
Meng, D.-D., Li, S., Sheng, B., Wu, H., Tian, S., Ma, W., Wang, G.-P., & Yan, X. (2023) · The Visual Computer · doi:10.1007/s00371-023-02965-0 · Cited by 19
“In recent years, a variety of learning-based semi-automatic and automatic methods have been widely used in multimodal medical image segmentation, such as UNet [33], 3D UNet [34], ResUNet [35], andVNet [36].”
MethodInfluentialContactless Palm Vein Recognition Based on Attention-Gated Residual U-Net and ECA-ResNet
Htet, A., & Lee, H. (2023) · Applied Sciences · doi:10.3390/app13116363 · Cited by 19
“Inspired by the residual U-Net [10], the segmentation model introduces residual learning into each convolutional block.”
MethodFEGNet: A Feedback Enhancement Gate Network for Automatic Polyp Segmentation
Jin, Q., Hou, H., Zhang, G., & Li, Z. (2023) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2023.3272168 · Cited by 22
Brain Tumor Segmentation from MRI Images using Deep Learning Techniques
Gupta, A., Dixit, M., Mishra, V., Singh, A., & Dayal, A. (2023) · arXiv.org · doi:10.48550/arxiv.2305.00257 · Cited by 19
“Zhang et al. [16], suggest the use of ResUnet in their research.”
BackgroundFang, J., Jiang, H., Zhang, S.-Q., Sun, L., Hu, X.-D., Liu, J., Gong, M., Liu, H.-X., & Fu, Y.-Y. (2023) · Frontiers in Plant Science · doi:10.3389/fpls.2023.1123410 · Cited by 19
“U-Net and its variants (Shen et al., 2017) have achieved competitive performance in many computer vision tasks, such as ResU-Net (Zhang et al., 2018), U-Net++ (Zhou et al., 2019), DenseNet (Huang et al., 2017), 3D U-Net (Li et al., 2020), V-Net (Milletari et al., 2016).”
BackgroundOnojeghuo, A. O., & Onojeghuo, A. R. (2023) · Remote Sensing in Earth Systems Sciences · doi:10.1007/s41976-023-00080-1 · Cited by 19
“The deep residual U-Net (ResU-Net) network integrates seven residual blocks throughout the U-Net framework [47].”
BackgroundMethodEfficient Knowledge Distillation for Brain Tumor Segmentation
Qi, Y., Zhang, W., Wang, X., You, X.-Y., Hu, S.-B., & Chen, J. (2022) · Applied Sciences · doi:10.3390/app122311980 · Cited by 19
Gastrointestinal Tract Polyp Anomaly Segmentation on Colonoscopy Images Using Graft-U-Net
Ramzan, M., Raza, M., Sharif, M. I., & Kadry, S. (2022) · Journal of Personalized Medicine · doi:10.3390/jpm12091459 · Cited by 19
“The results are matched to the existing results of UNet [25], ResUNet models [26], and ResUNet++ [27], which shows that the suggested method outperforms the existing methods.”
ResultMapping wheel-ruts from timber harvesting operations using deep learning techniques in drone imagery
Bhatnagar, S., Puliti, S., Talbot, B., Heppelmann, J., Breidenbach, J., & Astrup, R. (2022) · Forestry: An International Journal of Forest Research · doi:10.1093/forestry/cpac023 · Cited by 19
Learning self-calibrated optic disc and cup segmentation from multi-rater annotations
Wu, J.-D., Fang, H., Shang, F.-X., Wang, Z.-W., Yang, D., Zhou, W.-S., Yang, Y., & Xu, Y.-W. (2022) · International Conference on Medical Image Computing and Computer-Assisted Intervention · doi:10.48550/arxiv.2206.05092 · Cited by 19
“We use ResUnet [31] as the backbone for ConM and DivM.”
MethodOno, S., Komatsu, M., Sakai, A., Arima, H., Ochida, M., Aoyama, R., Yasutomi, S., Asada, K., Kaneko, S., Sasano, T., et al. (2022) · Biomedicines · doi:10.3390/biomedicines10051082 · Cited by 21
“We employed four segmentation methods: U-Net [24], UNet++ [25], UNet3+ [26], and Deep Residual U-Net (ResUNet) [27].”
MethodEfficient Occluded Road Extraction from High-Resolution Remote Sensing Imagery
Feng, D.-J., Shen, X., Xie, Y.-K., Liu, Y., & Wang, J. (2021) · Remote Sensing · doi:10.3390/rs13244974 · Cited by 19
“, proposed a semantic segmentation neural network by combining residual learning and U-Net to extract road information from high-resolution remote sensing images [52].”
An unsupervised approach of colonic polyp segmentation using adaptive markov random fields
Sasmal, P., Bhuyan, M. K., Dutta, S., & Iwahori, Y. (2021) · Pattern Recognition Letters · doi:10.1016/j.patrec.2021.12.014 · Cited by 19
CoKe: Contrastive Learning for Robust Keypoint Detection
Bai, Y., Wang, A., Kortylewski, A., & Yuille, A. (2020) · IEEE Workshop/Winter Conference on Applications of Computer Vision · doi:10.1109/wacv56688.2023.00015 · Cited by 19
“In particular, the table shows the keypoint detection results for CoKe-Res-UNet on the car category of the PASCAL3D+ dataset.”
BackgroundInfluentialAttention-Based Road Registration for GPS-Denied UAS Navigation
Wang, T., Zhao, Y., Wang, J.-W., Somani, A. K., & Sun, C.-Y. (2020) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2020.3015660 · Cited by 19
“Besides, road extraction in aerial images itself is difficult [5]–[7], which further degrades matching/registration accuracy.”
BackgroundDeep Learning for Neuroimaging Segmentation with a Novel Data Augmentation Strategy
Wu, W.-S., Lu, Y.-H., Mane, R., & Guan, C. (2020) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society · doi:10.1109/embc44109.2020.9176537 · Cited by 19
“ResUNet [21] 0.”
Zhang, Y., Wang, X.-W., Sun, L., Lei, P., Chen, J.-N., He, J., Zhou, Y., & Liu, Y.-L. (2024) · Optics & Laser Technology · doi:10.1016/j.optlastec.2023.110402 · Cited by 19
A Deep Cross-Modal Fusion Network for Road Extraction With High-Resolution Imagery and LiDAR Data
Luo, H., Wang, Z.-J., Du, B., & Dong, Y.-N. (2024) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2024.3360963 · Cited by 19
“Road extraction from high-resolution images using deep convolutional networks has become a popular research direction [5], [6], [7], [8], [9].”
BackgroundAdaptive Fourier Convolution Network for Road Segmentation in Remote Sensing Images
Liu, H.-J., Wang, C., Zhao, J.-D., Chen, S., & Kong, H. (2024) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2024.3384059 · Cited by 19
“R OAD segmentation in remote sensing (RS) images, which is essential for geographic information systems (GIS), urban road planning, and autonomous driving, is a fundamental research topic for cartography, traffic control, and intelligent transportation [1].”
BackgroundAn Evolutionary DenseRes Deep Convolutional Neural Network for Medical Image Segmentation
Hassanzadeh, T., Essam, D., & Sarker, R. A. (2020) · IEEE Access · doi:10.1109/access.2020.3039496 · Cited by 23
“In this paper, we proposed the first evolutionary DenseRes model for medical image segmentation, leveraging from U–Net [32], Res U–Net [35], Dense U–Net [36], and GA [11], such that our proposed automatic model can uncover an accurate network structure along with its training parameters for each dataset precisely and q…”
MethodResultInfluentialFan, Y., Mai, J., Xue, F., Lau, S., Jiang, S., Tao, Y.-Q., Zhang, X., & Tsang, W. (2025) · Italian National Conference on Sensors · doi:10.3390/s25237118 · Cited by 18
“Several excellent image segmentation architectures have been developed, including the classical U-Net [1], FCN [2], PspNet [3], K-Net [4], DeepLabv3 [5], and Mask2Former [6].”
Multi-directional attention: a lightweight attention module for slender structures
Liu, D., Zhang, Y., Ren, Y., Pan, D., He, X., Cong, M., & Yu, G. (2025) · Intelligence & Robotics · doi:10.20517/ir.2025.42 · Cited by 18
Early detection of Alzheimer’s disease in structural and functional MRI
Maity, R., Sankari, V. M. R., Umapathy, S., Velu, S. R., Alahmadi, T. J., Alhababi, Z. A., & Alkahtani, H. K. (2024) · Frontiers in Medicine · doi:10.3389/fmed.2024.1520878 · Cited by 23
Arjmandi, N., Mosleh-Shirazi, M. A., Mohebbi, S., Nasseri, S., Mehdizadeh, A., Pishevar, Z., Hosseini, S., Tehranizadeh, A. A., & Momennezhad, M. (2024) · Journal of Applied Clinical Medical Physics · doi:10.1002/acm2.14569 · Cited by 18
Detection-guided deep learning-based model with spatial regularization for lung nodule segmentation
Zhang, J.-S., Yang, M.-R., Guo, W.-H., Xavier, B. A., Bolen, M., & Li, X.-J. (2024) · Quantitative Imaging in Medicine and Surgery · doi:10.21037/qims-2024-2511 · Cited by 18
“The original ResU-Net model Zhang et al. (2018) consists of an encoder (blocks S1 to S5) and a decoder (blocks S6 to S9).”
Designing a TPMS metamaterial via deep learning and topology optimization
Viswanath, A., Abueidda, D., Modrek, M., Al-Rub, R. K. A., Koric, S., & Khan, K. (2024) · Frontiers of Mechanical Engineering · doi:10.3389/fmech.2024.1417606 · Cited by 18
Li, X.-B., Ouyang, X., Zhang, J., Ding, Z., Zhang, Y.-Y., Xue, Z., Shi, F., & Shen, D. (2024) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2024.3424884 · Cited by 18
“However, the separate encoding of different modality images triggers a domain shift issue, making it less effective by directly concatenating feature maps from each encoder via skip connections, as in the original design of ResUNet [42].”
Yanzhen, M., Song, C., Li, W., Zufang, Y., & Wang, A. (2024) · Frontiers in Neuroscience · doi:10.3389/fnins.2024.1401329 · Cited by 18
Aggregate-aware model with bidirectional edge generation for medical image segmentation
Ma, S.-Q., Li, X., Tang, J.-J., & Guo, F. (2024) · Applied Soft Computing · doi:10.1016/j.asoc.2024.111918 · Cited by 18
AgileFormer: Spatially Agile Transformer UNet for Medical Image Segmentation
Qiu, P.-J., Yang, J., Kumar, S., Ghosh, S., & Sotiras, A. (2024) · arXiv.org · doi:10.48550/arxiv.2404.00122 · Cited by 18
“Another line of works modified the convolution building block in UNet by introducing residual connection [18, 45], deformable convolution [22], and large kernel convolution [20, 21, 43].”
MethodEnhancing medical image segmentation with a multi-transformer U-Net
Dan, Y.-P., Jin, W., Yue, X., & Wang, Z. (2024) · PeerJ · doi:10.7717/peerj.17005 · Cited by 18
“…of the U-Net attracts researchers to extend this idea, and many researchers have proposed U-Net++ ( Cui, Liu & Huang, 2019 ), Residual U-Net ( Zhang, Liu & Wang, 2018 ), Dense U-Net ( Wang et al., 2019 ), and Attention U-Net ( Oktay et al., 2018 ) for 2D medical image segmentation ( Gu et…”
BackgroundPCB-Vision: A Multiscene RGB-Hyperspectral Benchmark Dataset of Printed Circuit Boards
Arbash, E., Fuchs, M., Rasti, B., Lorenz, S., Ghamisi, P., & Gloaguen, R. (2024) · IEEE Sensors Journal · doi:10.1109/jsen.2024.3380826 · Cited by 17
“This is particularly important to mitigate the impact of amplified class imbalance in HSI on model training.”
BackgroundMC-DC: An MLP-CNN Based Dual-path Complementary Network for Medical Image Segmentation
Jiang, X., Zhu, Y., Liu, Y., Wang, N., & Yi, L. (2023) · Comput. Methods Programs Biomed. · doi:10.1016/j.cmpb.2023.107846 · Cited by 18
Li, G., Jin, D., Yu, Q., Zheng, Y., & Qi, M. (2023) · Medical Physics · doi:10.1002/mp.16662 · Cited by 21
TransResU-Net: A Transformer based ResU-Net for Real-Time Colon Polyp Segmentation
Tomar, N. K., Shergill, A., Rieders, B., Bagci, U., & Jha, D. (2023) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society · doi:10.1109/embc40787.2023.10340572 · Cited by 18
“One of the promising extensions of UNet is ResUNet [20].”
BackgroundDB-UNet: MLP Based Dual Branch UNet for Accurate Vessel Segmentation in OCTA Images
Wang, C., Ning, H., Chen, X.-R., & Li, S. (2023) · IEEE International Conference on Acoustics, Speech, and Signal Processing · doi:10.1109/icassp49357.2023.10095868 · Cited by 18
TCU-Net: Transformer Embedded in Convolutional U-Shaped Network for Retinal Vessel Segmentation
Shi, Z., Li, Y., Zou, H., & Zhang, X.-D. (2023) · Italian National Conference on Sensors · doi:10.3390/s23104897 · Cited by 18
“However, ResU-Net [20] utilizes more convolutional layers and parameters, which might be overfitted.”
PG-VTON: A Novel Image-Based Virtual Try-On Method via Progressive Inference Paradigm
Fang, N., Qiu, L.-M., Zhang, S.-Y., Wang, Z.-L., & Hu, K. (2023) · IEEE transactions on multimedia · doi:10.1109/tmm.2024.3354622 · Cited by 18
TANet: Triple Attention Network for medical image segmentation
Wei, X., Ye, F., Wan, H., Xu, J., & Min, W. (2023) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2023.104608 · Cited by 18
Simeth, J., Jiang, J., Nosov, A., Wibmer, A. G., Zeléfsky, M. J., Tyagi, N., & Veeraraghavan, H. (2023) · Medical Physics · doi:10.1002/mp.16320 · Cited by 21
“The Res-Unet 47 improves upon the Unet through the replacement of the simple convolution blocks with residual units (compare the Unet to the ResUnet in Figure 1).”
Fractional derivative based weighted skip connections for satellite image road segmentation
Arora, S., Suman, H., Mathur, T., Pandey, H. M., & Tiwari, K. (2023) · Neural Networks · doi:10.1016/j.neunet.2023.01.031 · Cited by 18
Nachmani, R., Nidal, I., Robinson, D., Yassin, M., & Abookasis, D. (2023) · Journal of Pathology Informatics · doi:10.1016/j.jpi.2023.100197 · Cited by 18
“Recently, encoder – decoder models such as U-Net, 13 ResUNet, 14 and ResUNet++, 7 have achieved better performance compared to previous methods.”
ResultPrediction of Lung Nodule Progression with an Uncertainty-Aware Hierarchical Probabilistic Network
Rafael-Palou, X., Aubanell, A., Ceresa, M., Ribas, V. J., Piella, G., & Ballester, M. G. (2022) · Diagnostics · doi:10.3390/diagnostics12112639 · Cited by 18
“Regarding the core architecture of the U-HPNet, as in the original HPU framework, both subnets were implemented with 2D U-ResNets adapted to the proposed input/output size (32 × 32) and the additional described parameters.”
InfluentialICGNet: Integration Context-based Reverse-Contour Guidance Network for Polyp Segmentation
Du, X., Xu, X.-B., & Ma, K.-P. (2022) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2022/123 · Cited by 18
“…capability between our method and several advanced methods, including U-Net++ [Zhou et al. , 2018], U-Net [Ronneberger et al. , 2015], ResUNet [Zhang et al. , 2018], SFANet [Fang et al. , 2019], PraNet [Fan et al. , 2020], ACSNet [Zhang et al. , 2020] and CCBANet [ Nguyen et al. , 2021 ] .”
A Deep Learning Approach for Automatic Scoliosis Cobb Angle Identification
Maaliw, R. R., Susa, J. A. B., Alon, A., Lagman, A., Ambat, S., García, M. B., Piad, K., & Fernando-Raguro, M. C. (2022) · 2022 IEEE World AI IoT Congress (AIIoT) · doi:10.1109/aiiot54504.2022.9817290 · Cited by 18
“The results confirmed that a residual unit helps when training deep architectures for better image analysis representation [31 – 33].”
Remote sensing of brine shrimp cysts in salt lakes
Qi, L., Yao, Y., English, D., Ma, R., Luft, J., & Hu, C.-M. (2021) · Remote Sensing of Environment · doi:10.1016/j.rse.2021.112695 · Cited by 18
Segmentation of dermoscopy images based on deformable 3D convolution and ResU-NeXt + +
Zhao, C., Shuai, R., Ma, L., Liu, W., & Wu, M. (2021) · Medical & Biological Engineering & Computing · doi:10.1007/s11517-021-02397-9 · Cited by 17
“The ResUNet++ architecture is based on the deep residual U-Net (ResUNet) [38], which is an architecture that uses the strength of the deep residual network [39] and U-Net++ [40].”
MethodAdorno, W., Catalano, A., Ehsan, L., von Eckstaedt, H. V., Barnes, B., McGowan, E., Syed, S., & Brown, D. E. (2021) · Bioimaging (Bristol. Print) · doi:10.5220/0010241900002865 · Cited by 18
“It incorporates residual blocks into the architecture to increase the depth of the model while still propagating information quickly (Zhang et al., 2018).”
Alis, D. C., Yergin, M., Aliş, C., Topel, Ç., Asmakutlu, O., Bağcılar, Ö., Senli, Y. D., Üstündağ, A., Salt, V., Doğan, S. N., et al. (2021) · Scientific Reports · doi:10.1038/s41598-021-91467-x · Cited by 22
Recent Studies on Void Shrinkage in Metallic Materials Subjected to In Situ Heavy Ion Irradiations
Niu, T., Nasim, M., Annadanam, R. G. S., Fan, C., Li, J., Shang, Z., Xue, Y., El-Azab, A., Wang, H., & Zhang, X.-H. (2020) · JOM · doi:10.1007/s11837-020-04358-3 · Cited by 18
Band-Independent Encoder–Decoder Network for Pan-Sharpening of Remote Sensing Images
Liu, C., Zhang, Y., Wang, S., Sun, M., Ou, Y., Wan, Y., & Liu, X. (2020) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2020.2975230 · Cited by 24
Detecting Hardly Visible Roads in Low-Resolution Satellite Time Series Data
Oehmcke, S., Thrysøe, C., Borgstad, A., Salles, M. A. V., Brandt, M., & Gieseke, F. C. (2019) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata47090.2019.9006251 · Cited by 25
“This approach has been adapted by Zhang and Liu [19], who propose a network architecture called Deep ResUNet that yielded slightly better results.”
ResultDing, K.-M., Yang, Z., Wang, Y., & Liu, Y. (2019) · Applied Sciences · doi:10.3390/app9152972 · Cited by 18
“The robust The robust edge features and the gray images constitute the training data of the modified U-net model. edge features and the gray images constitute the training data of the modified U-net model.”
MethodSelf-citationDense Refinement Residual Network for Road Extraction From Aerial Imagery Data
Eerapu, K. K., Ashwath, B., Lal, S., Dell'acqua, F., & Narasimhadhan, A. V. (2019) · IEEE Access · doi:10.1109/access.2019.2928882 · Cited by 18
“The resulting model failed however to segment small roads in parking lots [18].”
BackgroundMethodInfluentialSCGC-Net: Spatial Context-Guided Calibration Network for Multisource RSI Landslides Detection
Fan, Y.-K., Ma, P.-F., Hu, Q., Liu, G.-W., Guo, Z., Tang, Y.-X., Wu, F., & Zhang, H. (2025) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2025.3528750 · Cited by 18
“Specifically, the comparison includes FCN [12], UNet [13], ResUNet [55], PSPNet [44], DeepLab V3 + [42], HRNet [56], ICNet [57], CCNet [58], DANet [59], GCNet [60], SegNext [61], PIDNet [62], SegFormer [36], Swin Transformer [35], Con-vNeXt [63], ST-UNet [64], and VMamba [20].”
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
