SOTAVerified

Road Segmentation

Road Segmentation is a pixel wise binary classification in order to extract underlying road network. Various Heuristic and data driven models are proposed. Continuity and robustness still remains one of the major challenges in the area.

Papers

Showing 1120 of 82 papers

TitleStatusHype
Enhancing Boundary Segmentation for Topological Accuracy with Skeleton-based MethodsCode1
RS-Mamba for Large Remote Sensing Image Dense PredictionCode3
MMCert: Provable Defense against Adversarial Attacks to Multi-modal ModelsCode0
Knowledge Distillation for Road Detection based on cross-model Semi-Supervised Learning0
Exploiting Low-level Representations for Ultra-Fast Road SegmentationCode1
Seeing the roads through the trees: A benchmark for modeling spatial dependencies with aerial imageryCode2
PhilEO Bench: Evaluating Geo-Spatial Foundation ModelsCode2
AI Powered Road Network Prediction with Multi-Modal DataCode0
Fine-Grained Extraction of Road Networks via Joint Learning of Connectivity and SegmentationCode0
Active Wildfires Detection and Dynamic Escape Routes Planning for Humans through Information Fusion between Drones and Satellites0
Show:102550
← PrevPage 2 of 9Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1U-Net (ResNet-18)DWR46.5Unverified
2DeepLabV3+ (ResNet-18)DWR46.1Unverified
3U-Net (ResNet-50)DWR45.7Unverified
4FCNDWR10.7Unverified
#ModelMetricClaimedVerifiedStatus
1CoANet + PRNmIoU70.6Unverified
2SPIN Road Mapper (ours)APLS0.74Unverified
3D-LinkNetIoU0.64Unverified
#ModelMetricClaimedVerifiedStatus
1RSM-SSIoU67.35Unverified
2SPIN Road Mapper (ours)IoU65.24Unverified