Research map / Detection and segmentation / CNN features
Improved Road Connectivity by Joint Learning of Orientation and Segmentation
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| jointly learn road orientation and segmentation (ablation) | road extraction models · SpaceNet | APLS: 55.69 -> 60.77 | Helped |
| jointly learn road orientation and segmentation (ablation) | road extraction models · DeepGlobe | APLS: 65.33 -> 68.71 | Helped |
| use junction prediction instead of orientation learning (ablation) | ResNet18 road extraction · SpaceNet | APLS: 52.65 -> 52.76 | No clear effect |
| use two multi-branch stacks rather than one (ablation) | orientation-and-segmentation model · SpaceNet | APLS: 60.92 -> 63.65 | Helped |
| increase the multi-branch model from two stacks to three (ablation) | orientation-and-segmentation model · SpaceNet | APLS: 63.65 -> 62.89 | Hurt |
| use two multi-branch stacks rather than one (ablation) | orientation-and-segmentation model · DeepGlobe | APLS: 70.23 -> 73.21 | Helped |
| increase the multi-branch model from two stacks to three (ablation) | orientation-and-segmentation model · DeepGlobe | APLS: 73.21 -> 72.48 | Hurt |
| add summed cross-task feature fusion (ablation) | two-stack multi-branch model · SpaceNet | APLS: 61.78 -> 63.65 | Helped |
| add connectivity refinement after segmentation (ablation) | full road extraction pipeline · SpaceNet and DeepGlobe | APLS | Helped |
Closest papers by meaning
- Patched Line Segment Learning for Vector Road Mapping (AAAI 2024 · similarity 0.89)
- Road Network Representation Learning with the Third Law of Geography (NeurIPS 2024 · similarity 0.86)
- Sketch and Refine: Towards Fast and Accurate Lane Detection (AAAI 2024 · similarity 0.85)
- GEONet: Global Enhancement and Optimization Network for Lane Detection (AAAI 2025 · similarity 0.84)
- LaneSegNet: Map Learning with Lane Segment Perception for Autonomous Driving (ICLR 2024 · similarity 0.84)
- CVGL: Causal Learning and Geometric Topology (NeurIPS 2025 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.