Papers › Road Extraction by Deep Residual U-Net
Road Extraction by Deep Residual U-Net
Zhengxin Zhang, Qingjie Liu, Yunhong Wang
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 is two-fold: 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 dataset 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.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
13 repositories listed; official and paper-mentioned ones first.
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Lesion Segmentation | Anatomical Tracings of Lesions After Stroke (ATLAS) | ResUNet | Dice | 0.4702 | #3 of 4 | Archive leaderboard | report |
| Lesion Segmentation | Anatomical Tracings of Lesions After Stroke (ATLAS) | ResUNet | IoU | 0.3549 | #3 of 4 | Archive leaderboard | report |
| Lesion Segmentation | Anatomical Tracings of Lesions After Stroke (ATLAS) | ResUNet | Precision | 0.5941 | #3 of 4 | Archive leaderboard | report |
| Lesion Segmentation | Anatomical Tracings of Lesions After Stroke (ATLAS) | ResUNet | Recall | 0.4537 | #3 of 4 | Archive leaderboard | report |
| Lung Nodule Segmentation | LUNA | Residual U-Net | AUC | 0.9849 | #2 of 5 | Archive leaderboard | report |
| Lung Nodule Segmentation | LUNA | Residual U-Net | F1 score | 0.9690 | #2 of 5 | Archive leaderboard | report |
| Retinal Vessel Segmentation | CHASE_DB1 | Residual U-Net | AUC | 0.9779 | #12 of 16 | Archive leaderboard | report |
| Retinal Vessel Segmentation | CHASE_DB1 | Residual U-Net | F1 score | 0.7800 | #12 of 16 | Archive leaderboard | report |
| Retinal Vessel Segmentation | DRIVE | Residual U-Net | AUC | 0.9779 | #14 of 22 | Archive leaderboard | report |
| Retinal Vessel Segmentation | DRIVE | Residual U-Net | F1 score | 0.8149 | #14 of 22 | Archive leaderboard | report |
| Retinal Vessel Segmentation | ROSE-1 DVC | ResU-Net | Dice Score | 65.67 | #3 of 5 | Archive leaderboard | report |
| Retinal Vessel Segmentation | ROSE-1 SVC | ResU-Net | Dice Score | 74.61 | #4 of 5 | Archive leaderboard | report |
| Retinal Vessel Segmentation | ROSE-1 SVC-DVC | ResU-Net | Dice Score | 74.61 | #3 of 5 | Archive leaderboard | report |
| Retinal Vessel Segmentation | ROSE-2 | ResU-Net | Dice Score | 67.25 | #4 of 5 | Archive leaderboard | report |
| Retinal Vessel Segmentation | STARE | Residual U-Net | F1 score | 0.8388 | #9 of 10 | Archive leaderboard | report |
| Semantic Segmentation | BJRoad | Res-UNet | IoU | 54.24 | #10 of 11 | Archive leaderboard | report |
| Skin Cancer Segmentation | Kaggle Skin Lesion Segmentation | Residual U-Net | AUC | 0.9396 | #2 of 3 | Archive leaderboard | report |
| Skin Cancer Segmentation | Kaggle Skin Lesion Segmentation | Residual U-Net | F1 score | 0.8799 | #2 of 3 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Methods
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections